Check out my publication’s list and citation index online at my Google Scholar and Scopus
Find publications related to:
Journal Articles
36.
Ch. D. Korkas; Ch. D. Tsaknakis; A. Ch. Kapoutsis; E. B. Kosmatopoulos
Distributed and Multi-Agent Reinforcement Learning Framework for Optimal Electric Vehicle Charging Scheduling Journal Article
In: Energies, vol. 17, iss. 15, no. 15, pp. 3694, 2024.
@article{Korkas2024,
title = {Distributed and Multi-Agent Reinforcement Learning Framework for Optimal Electric Vehicle Charging Scheduling},
author = {Ch. D. Korkas and Ch. D. Tsaknakis and A. Ch. Kapoutsis and E. B. Kosmatopoulos},
url = {https://www.mdpi.com/1996-1073/17/15/3694},
doi = {doi.org/10.3390/en17153694},
year = {2024},
date = {2024-07-26},
urldate = {2024-07-26},
journal = {Energies},
volume = {17},
number = {15},
issue = {15},
pages = {3694},
abstract = {The increasing number of electric vehicles (EVs) necessitates the installation of more charging stations. The challenge of managing these grid-connected charging stations leads to a multi-objective optimal control problem where station profitability, user preferences, grid requirements and stability should be optimized. However, it is challenging to determine the optimal charging/discharging EV schedule, since the controller should exploit fluctuations in the electricity prices, available renewable resources and available stored energy of other vehicles and cope with the uncertainty of EV arrival/departure scheduling. In addition, the growing number of connected vehicles results in a complex state and action vectors, making it difficult for centralized and single-agent controllers to handle the problem. In this paper, we propose a novel Multi-Agent and distributed Reinforcement Learning (MARL) framework that tackles the challenges mentioned above, producing controllers that achieve high performance levels under diverse conditions. In the proposed distributed framework, each charging spot makes its own charging/discharging decisions toward a cumulative cost reduction without sharing any type of private information, such as the arrival/departure time of a vehicle and its state of charge, addressing the problem of cost minimization and user satisfaction. The framework significantly improves the scalability and sample efficiency of the underlying Deep Deterministic Policy Gradient (DDPG) algorithm. Extensive numerical studies and simulations demonstrate the efficacy of the proposed approach compared with Rule-Based Controllers (RBCs) and well-established, state-of-the-art centralized RL (Reinforcement Learning) algorithms, offering performance improvements of up to 25% and 20% in reducing the energy cost and increasing user satisfaction, respectively.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The increasing number of electric vehicles (EVs) necessitates the installation of more charging stations. The challenge of managing these grid-connected charging stations leads to a multi-objective optimal control problem where station profitability, user preferences, grid requirements and stability should be optimized. However, it is challenging to determine the optimal charging/discharging EV schedule, since the controller should exploit fluctuations in the electricity prices, available renewable resources and available stored energy of other vehicles and cope with the uncertainty of EV arrival/departure scheduling. In addition, the growing number of connected vehicles results in a complex state and action vectors, making it difficult for centralized and single-agent controllers to handle the problem. In this paper, we propose a novel Multi-Agent and distributed Reinforcement Learning (MARL) framework that tackles the challenges mentioned above, producing controllers that achieve high performance levels under diverse conditions. In the proposed distributed framework, each charging spot makes its own charging/discharging decisions toward a cumulative cost reduction without sharing any type of private information, such as the arrival/departure time of a vehicle and its state of charge, addressing the problem of cost minimization and user satisfaction. The framework significantly improves the scalability and sample efficiency of the underlying Deep Deterministic Policy Gradient (DDPG) algorithm. Extensive numerical studies and simulations demonstrate the efficacy of the proposed approach compared with Rule-Based Controllers (RBCs) and well-established, state-of-the-art centralized RL (Reinforcement Learning) algorithms, offering performance improvements of up to 25% and 20% in reducing the energy cost and increasing user satisfaction, respectively.
35.
A. Stefanopoulou; E. K.Raptis; S. D. Apostolidis; S. Gkelios; A. Ch. Kapoutsis; S. A. Chatzichristofis; S. Vrochidis; E. B. Kosmatopoulos
Improving time and energy efficiency in multi-UAV coverage operations by optimizing the UAVs’ initial positions Journal Article
In: International Journal of Intelligent Robotics and Applications, 2024.
@article{Stefanopoulou2024,
title = {Improving time and energy efficiency in multi-UAV coverage operations by optimizing the UAVs’ initial positions},
author = {A. Stefanopoulou and E. K.Raptis and S. D. Apostolidis and S. Gkelios and A. Ch. Kapoutsis and S. A. Chatzichristofis and S. Vrochidis and E. B. Kosmatopoulos},
url = {https://link.springer.com/article/10.1007/s41315-024-00333-2
https://www.researchsquare.com/article/rs-3671974/v1
https://github.com/alice-st/DARP_Optimal_Initial_Positions
https://github.com/emmarapt/RealWorld2AirSim-DARP},
doi = {https://doi.org/10.1007/s41315-024-00333-2},
year = {2024},
date = {2024-04-22},
urldate = {2024-04-01},
journal = {International Journal of Intelligent Robotics and Applications},
abstract = {This paper focuses on Coverage Path Planning (CPP) methodologies, particularly in the context of multi-robot missions, to efficiently cover user-defined Regions of Interest (ROIs) using groups of UAVs, while emphasizing on the reduction of energy consumption and mission duration. Optimizing the efficiency of multi-robot CPP missions involves addressing critical factors such as path length, the number of turns, re-visitations, and launch positions. Achieving these goals, particularly in complex and concave ROIs with No-Go Zones, is a challenging task. This work introduces a novel approach to address these challenges, emphasizing the selection of launch points for UAVs. By optimizing launch points, the mission’s energy and time efficiency are significantly enhanced, leading to more efficient coverage of the selected ROIs. To further support our research and foster further exploration on this topic, we provide the open-source implementation of our algorithm and our evaluation mechanisms.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper focuses on Coverage Path Planning (CPP) methodologies, particularly in the context of multi-robot missions, to efficiently cover user-defined Regions of Interest (ROIs) using groups of UAVs, while emphasizing on the reduction of energy consumption and mission duration. Optimizing the efficiency of multi-robot CPP missions involves addressing critical factors such as path length, the number of turns, re-visitations, and launch positions. Achieving these goals, particularly in complex and concave ROIs with No-Go Zones, is a challenging task. This work introduces a novel approach to address these challenges, emphasizing the selection of launch points for UAVs. By optimizing launch points, the mission’s energy and time efficiency are significantly enhanced, leading to more efficient coverage of the selected ROIs. To further support our research and foster further exploration on this topic, we provide the open-source implementation of our algorithm and our evaluation mechanisms.
34.
M. Krestenitis; E. K.Raptis; A. Ch. Kapoutsis; K. Ioannidis; E. B. Kosmatopoulos; S. Vrochidis
Overcome the Fear Of Missing Out: Active sensing UAV scanning for precision agriculture Journal Article
In: Robotics and Autonomous Systems, vol. 172, pp. 104581, 2024.
@article{Krestenitis2024,
title = {Overcome the Fear Of Missing Out: Active sensing UAV scanning for precision agriculture},
author = {M. Krestenitis and E. K.Raptis and A. Ch. Kapoutsis and K. Ioannidis and E. B. Kosmatopoulos and S. Vrochidis},
url = {https://www.sciencedirect.com/science/article/abs/pii/S0921889023002208
https://arxiv.org/abs/2312.09730
https://zenodo.org/records/10202929
https://github.com/emmarapt/OverFOMO
},
doi = {https://doi.org/10.1016/j.robot.2023.104581},
year = {2024},
date = {2024-02-01},
urldate = {2024-02-01},
journal = {Robotics and Autonomous Systems},
volume = {172},
pages = {104581},
abstract = {This paper deals with the problem of informative path planning for a UAV deployed for precision agriculture applications. First, we observe that the “fear of missing out” data lead to uniform, conservative scanning policies over the whole agricultural field. Consequently, employing a non-uniform scanning approach can mitigate the expenditure of time in areas with minimal or negligible real value, while ensuring heightened precision in information-dense regions. Turning to the available informative path planning methodologies, we discern that certain methods entail intensive computational requirements, while others necessitate training on an ideal world simulator. To address the aforementioned issues, we propose an active sensing coverage path planning approach, named OverFOMO, that regulates the speed of the UAV in accordance with both the relative quantity of the identified classes, i.e. crops and weeds, and the confidence level of such detections. To identify these instances, a robust Deep Learning segmentation model is deployed. The computational needs of the proposed algorithm are independent of the size of the agricultural field, rendering its applicability on modern UAVs quite straightforward. The proposed algorithm was evaluated with a simu-realistic pipeline, combining data from real UAV missions and the high-fidelity dynamics of AirSim simulator, showcasing its performance improvements over the established state of affairs for this type of missions. An open-source implementation of the algorithm and the evaluation pipeline is also available: https://github.com/emmarapt/OverFOMO.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper deals with the problem of informative path planning for a UAV deployed for precision agriculture applications. First, we observe that the “fear of missing out” data lead to uniform, conservative scanning policies over the whole agricultural field. Consequently, employing a non-uniform scanning approach can mitigate the expenditure of time in areas with minimal or negligible real value, while ensuring heightened precision in information-dense regions. Turning to the available informative path planning methodologies, we discern that certain methods entail intensive computational requirements, while others necessitate training on an ideal world simulator. To address the aforementioned issues, we propose an active sensing coverage path planning approach, named OverFOMO, that regulates the speed of the UAV in accordance with both the relative quantity of the identified classes, i.e. crops and weeds, and the confidence level of such detections. To identify these instances, a robust Deep Learning segmentation model is deployed. The computational needs of the proposed algorithm are independent of the size of the agricultural field, rendering its applicability on modern UAVs quite straightforward. The proposed algorithm was evaluated with a simu-realistic pipeline, combining data from real UAV missions and the high-fidelity dynamics of AirSim simulator, showcasing its performance improvements over the established state of affairs for this type of missions. An open-source implementation of the algorithm and the evaluation pipeline is also available: https://github.com/emmarapt/OverFOMO.
33.
Th. Petsanis; Ch. Keroglou; A. Ch. Kapoutsis; E. B. Kosmatopoulos; G. Ch. Sirakoulis
Decomposing User-Defined Tasks in a Reinforcement Learning setup using TextWorld Journal Article
In: Frontiers in Robotics and AI, vol. 10, pp. 1280578, 2023.
@article{nokey,
title = {Decomposing User-Defined Tasks in a Reinforcement Learning setup using TextWorld},
author = {Th. Petsanis and Ch. Keroglou and A. Ch. Kapoutsis and E. B. Kosmatopoulos and G. Ch. Sirakoulis},
url = {https://www.frontiersin.org/articles/10.3389/frobt.2023.1280578/full
https://github.com/AthanasiosPetsanis/DiplomaClone
https://github.com/AthanasiosPetsanis/DiplomaClone/blob/main/Main.ipynb},
doi = {10.3389/frobt.2023.1280578},
year = {2023},
date = {2023-12-22},
urldate = {2023-12-22},
journal = {Frontiers in Robotics and AI},
volume = {10},
pages = {1280578},
abstract = {The current paper proposes a Hierarchical Reinforcement Learning (HRL) method to decompose a complex task into simpler sub-tasks and leverage those to improve training of an autonomous agent in a simulated environment. For practical reasons (i.e., illustrating purposes, easy implementation, user friendly interface, useful functionalities), we employ two python frameworks called TextWorld and MiniGrid. MiniGrid functions as a 2D simulated representation of the real environment while TextWorld functions as a high-level abstraction of this simulated environment.Training on this abstraction disentangles manipulation from navigation actions and allows us to design a dense reward function instead of a sparse reward function for the lower-level environment which, as we show, improves performance of training. Formal methods are utilized throughout the paper to establish that our algorithm is not prevented to derive to solutions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The current paper proposes a Hierarchical Reinforcement Learning (HRL) method to decompose a complex task into simpler sub-tasks and leverage those to improve training of an autonomous agent in a simulated environment. For practical reasons (i.e., illustrating purposes, easy implementation, user friendly interface, useful functionalities), we employ two python frameworks called TextWorld and MiniGrid. MiniGrid functions as a 2D simulated representation of the real environment while TextWorld functions as a high-level abstraction of this simulated environment.Training on this abstraction disentangles manipulation from navigation actions and allows us to design a dense reward function instead of a sparse reward function for the lower-level environment which, as we show, improves performance of training. Formal methods are utilized throughout the paper to establish that our algorithm is not prevented to derive to solutions.
32.
A. Ch. Kapoutsis; D. I. Koutras; Ch. D. Korkas; E. B. Kosmatopoulos
ACRE: Actor-Critic with Reward-Preserving Exploration Journal Article
In: Neural Computing and Applications, 2023.
@article{Kapoutsis2023,
title = {ACRE: Actor-Critic with Reward-Preserving Exploration},
author = {A. Ch. Kapoutsis and D. I. Koutras and Ch. D. Korkas and E. B. Kosmatopoulos},
url = {https://link.springer.com/article/10.1007/s00521-023-08845-x
https://github.com/athakapo/ACRE
https://paperswithcode.com/paper/acre-actor-critic-with-reward-preserving
https://www.youtube.com/watch?v=epBwZb5kpTc},
doi = {https://doi.org/10.1007/s00521-023-08845-x},
year = {2023},
date = {2023-08-14},
urldate = {2023-08-14},
journal = {Neural Computing and Applications},
abstract = {While reinforcement learning (RL) algorithms have generated impressive strategies for a wide range of tasks, the performance improvements in continuous-domain, real-world problems do not follow the same trend. Poor exploration and quick convergence to locally optimal solutions play a dominant role. Advanced RL algorithms attempt to mitigate this issue by introducing exploration signals during the training procedure. This successful integration has paved the way to introduce signals from the intrinsic exploration branch. ACRE algorithm is a framework that concretely describes the conditions for such an integration, avoiding transforming the Markov decision process into time varying, and as a result, making the whole optimization scheme brittle and susceptible to instability. The key distinction of ACRE lies in the way of handling and storing both extrinsic and intrinsic rewards. ACRE is an off-policy, actor-critic style RL algorithm that separately approximates the forward novelty return. ACRE is shipped with a Gaussian mixture model to calculate the instantaneous novelty; however, different options could also be integrated. Using such an effective early exploration, ACRE results in substantial improvements over alternative RL methods, in a range of continuous control RL environments, such as learning from policy-misleading reward signals. Open-source implementation is available here: https://github.com/athakapo/ACRE.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
While reinforcement learning (RL) algorithms have generated impressive strategies for a wide range of tasks, the performance improvements in continuous-domain, real-world problems do not follow the same trend. Poor exploration and quick convergence to locally optimal solutions play a dominant role. Advanced RL algorithms attempt to mitigate this issue by introducing exploration signals during the training procedure. This successful integration has paved the way to introduce signals from the intrinsic exploration branch. ACRE algorithm is a framework that concretely describes the conditions for such an integration, avoiding transforming the Markov decision process into time varying, and as a result, making the whole optimization scheme brittle and susceptible to instability. The key distinction of ACRE lies in the way of handling and storing both extrinsic and intrinsic rewards. ACRE is an off-policy, actor-critic style RL algorithm that separately approximates the forward novelty return. ACRE is shipped with a Gaussian mixture model to calculate the instantaneous novelty; however, different options could also be integrated. Using such an effective early exploration, ACRE results in substantial improvements over alternative RL methods, in a range of continuous control RL environments, such as learning from policy-misleading reward signals. Open-source implementation is available here: https://github.com/athakapo/ACRE.
31.
S. D. Apostolidis; G. Vougiatzis; A. Ch. Kapoutsis; S. A. Chatzichristofis; E. B. Kosmatopoulos
Systematically Improving the Efficiency of Grid-Based Coverage Path Planning Methodologies in Real-World UAVs' Operations Journal Article
In: Drones, 2023.
@article{Apostolidis2023,
title = {Systematically Improving the Efficiency of Grid-Based Coverage Path Planning Methodologies in Real-World UAVs' Operations},
author = {S. D. Apostolidis and G. Vougiatzis and A. Ch. Kapoutsis and S. A. Chatzichristofis and E. B. Kosmatopoulos},
url = {https://www.mdpi.com/2504-446X/7/6/399},
doi = {https://dx.doi.org/10.3390/drones7060399},
year = {2023},
date = {2023-06-15},
urldate = {2023-06-15},
journal = {Drones},
abstract = { This work focuses on the efficiency improvement of grid-based Coverage Path Planning (CPP) methodologies in real-world applications with UAVs. While several sophisticated approaches are met in literature, grid-based methods are not commonly used in real-life operations. This happens mostly due to the error that is introduced during the region's representation on the grid, a step mandatory for such methods, that can have a great negative impact on their overall coverage efficiency. A previous work on UAVs' coverage operations for remote sensing, has introduced a novel optimization procedure for finding the optimal relative placement between the region of interest and the grid, improving the coverage and resource utilization efficiency of the generated trajectories, but still, incorporating flaws that can affect certain aspects of the method's effectiveness. This work goes one step forward and introduces a CPP method, that provides three different ad-hoc coverage modes: the Geo-fenced Coverage Mode, the Better Coverage Mode and the Complete Coverage Mode, each incorporating features suitable for specific types of vehicles and real-world applications. For the design of the coverage trajectories, user-defined percentages of overlap (sidelap and frontlap) are taken into consideration, so that the collected data will be appropriate for applications like orthomosaicing and 3D mapping. The newly introduced modes are evaluated through simulations, using 20 publicly available benchmark regions as testbed, demonstrating their stenghts and weaknesses in terms of coverage and efficiency. The proposed method with its ad-hoc modes can handle even the most complex-shaped, concave regions with obstacles, ensuring complete coverage, no-sharp-turns, non-overlapping trajectories and strict geo-fencing. The achieved results demonstrate that the common issues encountered in grid-based methods can be overcome by considering the appropriate parameters, so that such methods can provide robust solutions in the CPP domain.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This work focuses on the efficiency improvement of grid-based Coverage Path Planning (CPP) methodologies in real-world applications with UAVs. While several sophisticated approaches are met in literature, grid-based methods are not commonly used in real-life operations. This happens mostly due to the error that is introduced during the region's representation on the grid, a step mandatory for such methods, that can have a great negative impact on their overall coverage efficiency. A previous work on UAVs' coverage operations for remote sensing, has introduced a novel optimization procedure for finding the optimal relative placement between the region of interest and the grid, improving the coverage and resource utilization efficiency of the generated trajectories, but still, incorporating flaws that can affect certain aspects of the method's effectiveness. This work goes one step forward and introduces a CPP method, that provides three different ad-hoc coverage modes: the Geo-fenced Coverage Mode, the Better Coverage Mode and the Complete Coverage Mode, each incorporating features suitable for specific types of vehicles and real-world applications. For the design of the coverage trajectories, user-defined percentages of overlap (sidelap and frontlap) are taken into consideration, so that the collected data will be appropriate for applications like orthomosaicing and 3D mapping. The newly introduced modes are evaluated through simulations, using 20 publicly available benchmark regions as testbed, demonstrating their stenghts and weaknesses in terms of coverage and efficiency. The proposed method with its ad-hoc modes can handle even the most complex-shaped, concave regions with obstacles, ensuring complete coverage, no-sharp-turns, non-overlapping trajectories and strict geo-fencing. The achieved results demonstrate that the common issues encountered in grid-based methods can be overcome by considering the appropriate parameters, so that such methods can provide robust solutions in the CPP domain.
30.
E. K.Raptis; K. Egglezos; O. Kypris; M. Krestenitis; A. Ch. Kapoutsis; K. Ioannidis; S. Vrochidis; E. B. Kosmatopoulos
CoFly: An automated, AI-based open-source platform for UAV precision agriculture applications Journal Article
In: SoftwareX, 2023.
@article{K.Raptis2023b,
title = {CoFly: An automated, AI-based open-source platform for UAV precision agriculture applications},
author = {E. K.Raptis and K. Egglezos and O. Kypris and M. Krestenitis and A. Ch. Kapoutsis and K. Ioannidis and S. Vrochidis and E. B. Kosmatopoulos},
url = {https://www.sciencedirect.com/science/article/pii/S2352711023001103
https://github.com/CoFly-Project/cofly-gui},
doi = {https://doi.org/10.1016/j.softx.2023.101414},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
journal = {SoftwareX},
abstract = {This paper presents a modular and holistic Precision Agriculture platform, named CoFly, incorporating custom-developed AI and ICT technologies with pioneering functionalities in a UAV-agnostic system. Cognitional operations of micro Flying vehicles are utilized for data acquisition incorporating advanced coverage path planning and obstacle avoidance functionalities. Photogrammetric outcomes are extracted by processing UAV data into 2D fields and crop health maps, enabling the extraction of high-level semantic information about seed yields and quality. Based on vegetation health, CoFly incorporates a pixel-wise processing pipeline to detect and classify crop health deterioration sources. On top of that, a novel UAV mission planning scheme is employed to enable site-specific treatment by providing an automated solution for a targeted, on-the-spot, inspection. Upon the acquired inspection footage, a weed detection module is deployed, utilizing deep-learning methods, enabling weed classification. All of these capabilities are integrated inside a cost-effective and user-friendly end-to-end platform functioning on mobile devices. CoFly was tested and validated with extensive experimentation in agricultural fields with lucerne and wheat crops in Chalkidiki, Greece showcasing its performance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper presents a modular and holistic Precision Agriculture platform, named CoFly, incorporating custom-developed AI and ICT technologies with pioneering functionalities in a UAV-agnostic system. Cognitional operations of micro Flying vehicles are utilized for data acquisition incorporating advanced coverage path planning and obstacle avoidance functionalities. Photogrammetric outcomes are extracted by processing UAV data into 2D fields and crop health maps, enabling the extraction of high-level semantic information about seed yields and quality. Based on vegetation health, CoFly incorporates a pixel-wise processing pipeline to detect and classify crop health deterioration sources. On top of that, a novel UAV mission planning scheme is employed to enable site-specific treatment by providing an automated solution for a targeted, on-the-spot, inspection. Upon the acquired inspection footage, a weed detection module is deployed, utilizing deep-learning methods, enabling weed classification. All of these capabilities are integrated inside a cost-effective and user-friendly end-to-end platform functioning on mobile devices. CoFly was tested and validated with extensive experimentation in agricultural fields with lucerne and wheat crops in Chalkidiki, Greece showcasing its performance.
29.
E. K.Raptis; M. Krestenitis; K. Egglezos; O. Kypris; K. Ioannidis; L. Doitsidis; A. Ch. Kapoutsis; S. Vrochidis; I. Kompatsiaris; E. B. Kosmatopoulos
End-to-end Precision Agriculture UAV-Based Functionalities Tailored to Field Characteristics Journal Article
In: Journal of Intelligent & Robotic Systems volume , vol. 107, iss. 2, no. 23, 2023.
@article{K.Raptis2023c,
title = {End-to-end Precision Agriculture UAV-Based Functionalities Tailored to Field Characteristics},
author = {E. K.Raptis and M. Krestenitis and K. Egglezos and O. Kypris and K. Ioannidis and L. Doitsidis and A. Ch. Kapoutsis and S. Vrochidis and I. Kompatsiaris and E. B. Kosmatopoulos},
url = {https://link.springer.com/article/10.1007/s10846-022-01761-7
https://www.youtube.com/watch?v=C0hdCu-ZRQk},
doi = {https://doi.org/10.1007/s10846-022-01761-7},
year = {2023},
date = {2023-01-27},
urldate = {2023-01-27},
journal = {Journal of Intelligent & Robotic Systems volume },
volume = {107},
number = {23},
issue = {2},
abstract = {This paper presents a novel, low-cost, user-friendly Precision Agriculture platform that attempts to alleviate the drawbacks of limited battery life by carefully designing missions tailored to each field’s specific, time-changing characteristics. The proposed system is capable of designing coverage missions for any type of UAV, integrating field characteristics into the resulting trajectory, such as irregular field shape and obstacles. The collected images are automatically processed to create detailed orthomosaics of the field and extract the corresponding vegetation indices. A novel mechanism is then introduced that automatically extracts possible problematic areas of the field and subsequently designs a follow-up UAV mission to acquire extra information on these regions. The toolchain is finished by using a deep learning module that was made just for finding weeds in the close-examination flight. For the development of such a deep-learning module, a new weed dataset from the UAV’s perspective, which is publicly available for download, was collected and annotated. All the above functionalities are enclosed in an open-source, end-to-end platform, named Cognitional Operations of micro Flying vehicles (CoFly). The effectiveness of the proposed system was tested and validated with extensive experimentation in agricultural fields with cotton in Larissa, Greece during two different crop sessions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper presents a novel, low-cost, user-friendly Precision Agriculture platform that attempts to alleviate the drawbacks of limited battery life by carefully designing missions tailored to each field’s specific, time-changing characteristics. The proposed system is capable of designing coverage missions for any type of UAV, integrating field characteristics into the resulting trajectory, such as irregular field shape and obstacles. The collected images are automatically processed to create detailed orthomosaics of the field and extract the corresponding vegetation indices. A novel mechanism is then introduced that automatically extracts possible problematic areas of the field and subsequently designs a follow-up UAV mission to acquire extra information on these regions. The toolchain is finished by using a deep learning module that was made just for finding weeds in the close-examination flight. For the development of such a deep-learning module, a new weed dataset from the UAV’s perspective, which is publicly available for download, was collected and annotated. All the above functionalities are enclosed in an open-source, end-to-end platform, named Cognitional Operations of micro Flying vehicles (CoFly). The effectiveness of the proposed system was tested and validated with extensive experimentation in agricultural fields with cotton in Larissa, Greece during two different crop sessions.
28.
M. Krestenitis; E. K.Raptis; A. Ch. Kapoutsis; K. Ioannidis; E. B. Kosmatopoulos; S. Vrochidis; I. Kompatsiaris
CoFly-WeedDB: A UAV image dataset for weed detection and species identification Journal Article
In: Data in Brief, vol. 45, pp. 108575, 2022, ISSN: 2352-3409.
@article{Krestenitis2022b,
title = {CoFly-WeedDB: A UAV image dataset for weed detection and species identification},
author = {M. Krestenitis and E. K.Raptis and A. Ch. Kapoutsis and K. Ioannidis and E. B. Kosmatopoulos and S. Vrochidis and I. Kompatsiaris},
url = {https://www.sciencedirect.com/science/article/pii/S235234092200782X
https://github.com/CoFly-Project/CoFly-WeedDB
https://zenodo.org/record/6697343#.YrQpwHhByV4},
doi = {https://doi.org/10.1016/j.dib.2022.108575},
issn = {2352-3409},
year = {2022},
date = {2022-09-05},
urldate = {2022-09-05},
journal = {Data in Brief},
volume = {45},
pages = {108575},
abstract = {The CoFly-WeedDB contains 201 RGB images (∼436MB) from the attached camera of DJI Phantom Pro 4 from a cotton field in Larissa, Greece during the first stages of plant growth. The 1280×720 RGB images were collected while the Unmanned Aerial Vehicle (UAV) was performing a coverage mission over the field's area. During the designed mission, the camera angle was adjusted to -87°, vertically with the field. The flight altitude and speed of the UAV were equal to 5m and 3m/s, respectively, aiming to provide a close and clear view of the weed instances. All images have been annotated by expert agronomists using the LabelMe annotation tool, providing the exact boundaries of 3 types of common weeds in this type of crop, namely (i) Johnson grass, (ii) Field bindweed, and (iii) Purslane. The dataset can be used alone and in combination with other datasets to develop AI-based methodologies for automatic weed segmentation and classification purposes.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The CoFly-WeedDB contains 201 RGB images (∼436MB) from the attached camera of DJI Phantom Pro 4 from a cotton field in Larissa, Greece during the first stages of plant growth. The 1280×720 RGB images were collected while the Unmanned Aerial Vehicle (UAV) was performing a coverage mission over the field's area. During the designed mission, the camera angle was adjusted to -87°, vertically with the field. The flight altitude and speed of the UAV were equal to 5m and 3m/s, respectively, aiming to provide a close and clear view of the weed instances. All images have been annotated by expert agronomists using the LabelMe annotation tool, providing the exact boundaries of 3 types of common weeds in this type of crop, namely (i) Johnson grass, (ii) Field bindweed, and (iii) Purslane. The dataset can be used alone and in combination with other datasets to develop AI-based methodologies for automatic weed segmentation and classification purposes.
27.
G. D. Karatzinis; P. Michailidis; I. T. Michailidis; A. Ch. Kapoutsis; E. B. Kosmatopoulos; Y. S. Boutalis
Coordinating heterogeneous mobile sensing platforms for effectively monitoring a dispersed gas plume Journal Article
In: Integrated Computer-Aided Engineering, 2022.
@article{Karatzinis2022,
title = {Coordinating heterogeneous mobile sensing platforms for effectively monitoring a dispersed gas plume},
author = {G. D. Karatzinis and P. Michailidis and I. T. Michailidis and A. Ch. Kapoutsis and E. B. Kosmatopoulos and Y. S. Boutalis},
url = {https://www.researchgate.net/publication/362883988_Coordinating_heterogeneous_mobile_sensing_platforms_for_effectively_monitoring_a_dispersed_gas_plume
https://github.com/athakapo/A-distributed-plug-n-play-algorithm-for-multi-robot-applications},
doi = {http://dx.doi.org/10.3233/ICA-220690},
year = {2022},
date = {2022-08-19},
urldate = {2022-08-19},
journal = { Integrated Computer-Aided Engineering},
abstract = {In order to sufficiently protect active personnel and physical environment from hazardous leaks, recent industrial practices integrate innovative multi-modalities so as to maximize response efficiency. Since the early detection of such incidents portrays the most critical factor for providing efficient response measures, the continuous and reliable surveying of industrial spaces is of primary importance. Current study develops a surveying mechanism, utilizing a swarm of heterogeneous aerial mobile sensory platforms, for the continuous monitoring and detection of CH4 dispersed gas plumes. In order to timely represent the CH4 diffusion progression incident, the research concerns a simulated indoor, geometrically complex environment, where early detection and timely response are critical. The primary aim was to evaluate the efficiency of a novel multi-agent, closed-loop, algorithm responsible for the UAV path-planning of the swarm, in comparison with an efficient a state-of-the-art path-planning EGO methodology, acting as a benchmark. Abbreviated as Block Coordinate Descent Cognitive Adaptive Optimization (BCD-CAO) the novel algorithm outperformed the Efficient Global Optimization (EGO) algorithm, in seven simulation scenarios, demonstrating improved dynamic adaptation of the aerial UAV swarm towards its heterogeneous operational capabilities. The evaluation results presented herein, exhibit the efficiency of the proposed algorithm for continuously conforming the mobile sensing platforms’ formation towards maximizing the total measured density of the diffused volume plume.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In order to sufficiently protect active personnel and physical environment from hazardous leaks, recent industrial practices integrate innovative multi-modalities so as to maximize response efficiency. Since the early detection of such incidents portrays the most critical factor for providing efficient response measures, the continuous and reliable surveying of industrial spaces is of primary importance. Current study develops a surveying mechanism, utilizing a swarm of heterogeneous aerial mobile sensory platforms, for the continuous monitoring and detection of CH4 dispersed gas plumes. In order to timely represent the CH4 diffusion progression incident, the research concerns a simulated indoor, geometrically complex environment, where early detection and timely response are critical. The primary aim was to evaluate the efficiency of a novel multi-agent, closed-loop, algorithm responsible for the UAV path-planning of the swarm, in comparison with an efficient a state-of-the-art path-planning EGO methodology, acting as a benchmark. Abbreviated as Block Coordinate Descent Cognitive Adaptive Optimization (BCD-CAO) the novel algorithm outperformed the Efficient Global Optimization (EGO) algorithm, in seven simulation scenarios, demonstrating improved dynamic adaptation of the aerial UAV swarm towards its heterogeneous operational capabilities. The evaluation results presented herein, exhibit the efficiency of the proposed algorithm for continuously conforming the mobile sensing platforms’ formation towards maximizing the total measured density of the diffused volume plume.
26.
S. D. Apostolidis; P. Ch. Kapoutsis; A. Ch. Kapoutsis; E. B. Kosmatopoulos
Cooperative Multi-UAV Coverage Mission Planning Platform for Remote Sensing Applications Journal Article
In: Autonomous Robots, 2022.
@article{Apostolidis2022b,
title = {Cooperative Multi-UAV Coverage Mission Planning Platform for Remote Sensing Applications},
author = {S. D. Apostolidis and P. Ch. Kapoutsis and A. Ch. Kapoutsis and E. B. Kosmatopoulos},
editor = {Gaurav Sukhatme},
url = {https://link.springer.com/article/10.1007/s10514-021-10028-3
https://arxiv.org/abs/2201.07030
http://choosepath.ddns.net/
https://kapoutsis.info/wp-content/uploads/2022/02/mCPP-flyer.pdf
https://github.com/savvas-ap/mCPP-optimized-DARP
https://github.com/savvas-ap/cpp-simulated-evaluations
https://paperswithcode.com/paper/cooperative-multi-uav-coverage-mission
https://paperswithcode.com/dataset/cpp-simulated-evaluation
https://www.youtube.com/watch?v=JQrqt1dS4A8},
doi = {10.1007/s10514-021-10028-3},
year = {2022},
date = {2022-00-15},
urldate = {2022-00-15},
journal = {Autonomous Robots},
abstract = {This paper proposes a novel mission planning platform, capable of efficiently deploying a team of UAVs to cover complex-shaped areas, in various remote sensing applications. Under the hood lies a novel optimization scheme for grid-based methods, utilizing Simulated Annealing algorithm, that significantly increases the achieved percentage of coverage and improves the qualitative features of the generated paths. Extensive simulated evaluation in comparison with a state-of-the-art alternative methodology, for coverage path planning (CPP) operations, establishes the performance gains in terms of achieved coverage and overall duration of the generated missions. On top of that, DARP algorithm is employed to allocate sub-tasks to each member of the swarm, taking into account each UAV's sensing and operational capabilities, their initial positions and any no-fly-zones possibly defined inside the operational area. This feature is of paramount importance in real-life applications, as it has the potential to achieve tremendous performance improvements in terms of time demanded to complete a mission, while at the same time it unlocks a wide new range of applications, that was previously not feasible due to the limited battery life of UAVs. In order to investigate the actual efficiency gains that are introduced by the multi-UAV utilization, a simulated study is performed as well. All of these capabilities are packed inside an end-to-end platform that eases the utilization of UAVs' swarms in remote sensing applications. Its versatility is demonstrated via two different real-life applications: (i) a photogrametry for precision agriculture and (ii) an indicative search and rescue for first responders missions, that were performed utilizing a swarm of commercial UAVs. An implementation of the mCPP methodology introduced in this work, as well as a link for a demonstrative video and a link for a fully functional, on-line hosted instance of the presented platform can be found here: https://github.com/savvas-ap/mCPP-optimized-DARP.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper proposes a novel mission planning platform, capable of efficiently deploying a team of UAVs to cover complex-shaped areas, in various remote sensing applications. Under the hood lies a novel optimization scheme for grid-based methods, utilizing Simulated Annealing algorithm, that significantly increases the achieved percentage of coverage and improves the qualitative features of the generated paths. Extensive simulated evaluation in comparison with a state-of-the-art alternative methodology, for coverage path planning (CPP) operations, establishes the performance gains in terms of achieved coverage and overall duration of the generated missions. On top of that, DARP algorithm is employed to allocate sub-tasks to each member of the swarm, taking into account each UAV's sensing and operational capabilities, their initial positions and any no-fly-zones possibly defined inside the operational area. This feature is of paramount importance in real-life applications, as it has the potential to achieve tremendous performance improvements in terms of time demanded to complete a mission, while at the same time it unlocks a wide new range of applications, that was previously not feasible due to the limited battery life of UAVs. In order to investigate the actual efficiency gains that are introduced by the multi-UAV utilization, a simulated study is performed as well. All of these capabilities are packed inside an end-to-end platform that eases the utilization of UAVs' swarms in remote sensing applications. Its versatility is demonstrated via two different real-life applications: (i) a photogrametry for precision agriculture and (ii) an indicative search and rescue for first responders missions, that were performed utilizing a swarm of commercial UAVs. An implementation of the mCPP methodology introduced in this work, as well as a link for a demonstrative video and a link for a fully functional, on-line hosted instance of the presented platform can be found here: https://github.com/savvas-ap/mCPP-optimized-DARP.
- https://link.springer.com/article/10.1007/s10514-021-10028-3
- https://arxiv.org/abs/2201.07030
- http://choosepath.ddns.net/
- https://kapoutsis.info/wp-content/uploads/2022/02/mCPP-flyer.pdf
- https://github.com/savvas-ap/mCPP-optimized-DARP
- https://github.com/savvas-ap/cpp-simulated-evaluations
- https://paperswithcode.com/paper/cooperative-multi-uav-coverage-mission
- https://paperswithcode.com/dataset/cpp-simulated-evaluation
- https://www.youtube.com/watch?v=JQrqt1dS4A8
- doi:10.1007/s10514-021-10028-3
25.
D. I. Koutras; A. Ch. Kapoutsis; A. A. Amanatiadis; E. B. Kosmatopoulos
MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments Journal Article
In: Electronics, vol. 10, no. 22, pp. 2751, 2021.
@article{Koutras2021,
title = {MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments},
author = {D. I. Koutras and A. Ch. Kapoutsis and A. A. Amanatiadis and E. B. Kosmatopoulos},
url = {https://www.mdpi.com/2079-9292/10/22/2751/
https://arxiv.org/abs/2107.09996
https://github.com/dimikout3/MarsExplorer
https://paperswithcode.com/paper/marsexplorer-exploration-of-unknown-terrains
https://www.azom.com/news.aspx?newsID=57311},
doi = {https://doi.org/10.3390/electronics10222751},
year = {2021},
date = {2021-11-11},
urldate = {2021-11-11},
journal = {Electronics},
volume = {10},
number = {22},
pages = {2751},
publisher = {mdpi},
abstract = {This paper is an initial endeavor to bridge the gap between powerful Deep Reinforcement Learning methodologies and the problem of exploration/coverage of unknown terrains. Within this scope, MarsExplorer, an openai-gym compatible environment tailored to exploration/coverage of unknown areas, is presented. MarsExplorer translates the original robotics problem into a Reinforcement Learning setup that various off-the-shelf algorithms can tackle. Any learned policy can be straightforwardly applied to a robotic platform without an elaborate simulation model of the robot's dynamics to apply a different learning/adaptation phase. One of its core features is the controllable multi-dimensional procedural generation of terrains, which is the key for producing policies with strong generalization capabilities. Four different state-of-the-art RL algorithms (A3C, PPO, Rainbow, and SAC) are trained on the MarsExplorer environment, and a proper evaluation of their results compared to the average human-level performance is reported. In the follow-up experimental analysis, the effect of the multi-dimensional difficulty setting on the learning capabilities of the best-performing algorithm (PPO) is analyzed. A milestone result is the generation of an exploration policy that follows the Hilbert curve without providing this information to the environment or rewarding directly or indirectly Hilbert-curve-like trajectories. The experimental analysis is concluded by evaluating PPO learned policy algorithm side-by-side with frontier-based exploration strategies. A study on the performance curves revealed that PPO-based policy was capable of performing adaptive-to-the-unknown-terrain sweeping without leaving expensive-to-revisit areas uncovered, underlying the capability of RL-based methodologies to tackle exploration tasks efficiently. The source code can be found at: https://github.com/dimikout3/MarsExplorer.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper is an initial endeavor to bridge the gap between powerful Deep Reinforcement Learning methodologies and the problem of exploration/coverage of unknown terrains. Within this scope, MarsExplorer, an openai-gym compatible environment tailored to exploration/coverage of unknown areas, is presented. MarsExplorer translates the original robotics problem into a Reinforcement Learning setup that various off-the-shelf algorithms can tackle. Any learned policy can be straightforwardly applied to a robotic platform without an elaborate simulation model of the robot's dynamics to apply a different learning/adaptation phase. One of its core features is the controllable multi-dimensional procedural generation of terrains, which is the key for producing policies with strong generalization capabilities. Four different state-of-the-art RL algorithms (A3C, PPO, Rainbow, and SAC) are trained on the MarsExplorer environment, and a proper evaluation of their results compared to the average human-level performance is reported. In the follow-up experimental analysis, the effect of the multi-dimensional difficulty setting on the learning capabilities of the best-performing algorithm (PPO) is analyzed. A milestone result is the generation of an exploration policy that follows the Hilbert curve without providing this information to the environment or rewarding directly or indirectly Hilbert-curve-like trajectories. The experimental analysis is concluded by evaluating PPO learned policy algorithm side-by-side with frontier-based exploration strategies. A study on the performance curves revealed that PPO-based policy was capable of performing adaptive-to-the-unknown-terrain sweeping without leaving expensive-to-revisit areas uncovered, underlying the capability of RL-based methodologies to tackle exploration tasks efficiently. The source code can be found at: https://github.com/dimikout3/MarsExplorer.
24.
A. Ch. Kapoutsis; I. T. Michailidis; Y. Boutalis; E. B. Kosmatopoulos
Building synergetic consensus for dynamic gas-plume tracking applications using UAV platforms Journal Article
In: Computers & Electrical Engineering, vol. 91, 2021.
@article{Kapoutsis2021,
title = {Building synergetic consensus for dynamic gas-plume tracking applications using UAV platforms},
author = {A. Ch. Kapoutsis and I. T. Michailidis and Y. Boutalis and E. B. Kosmatopoulos},
url = {https://www.sciencedirect.com/science/article/pii/S0045790621000525
https://kapoutsis.info/wp-content/uploads/2021/03/Building-Synergetic-Consensus-for-Dynamic-Gas-Plume-Tracking-Applications-using-UAV-Platforms.pdf
https://www.youtube.com/watch?v=9jKD6ORLxgQ&feature=youtu.be
https://www.youtube.com/watch?v=sJeSuCd8ciw
https://github.com/athakapo/A-distributed-plug-n-play-algorithm-for-multi-robot-applications},
doi = {10.1016/j.compeleceng.2021.107029},
year = {2021},
date = {2021-03-09},
urldate = {2021-03-09},
journal = {Computers & Electrical Engineering},
volume = {91},
abstract = {This article investigates the problem of deploying a swarm of UAVs equipped with gas sensors for industrial remote gas-plume sensing. This setup’s objective is to continuously adjust the swarm formation to maximize the combined perception for the dynamically evolved plume’s cloud, focusing around areas with the highest concentration/intensity. Initially, such a setup is formulated into an optimization problem, the solution of which could be acquired by the maximization of an appropriately defined objective function. Due to the model-free approach, this objective function’s analytical form is not available, prohibiting standard gradient descent methodologies. To this end, a tracking algorithm is developed and studied, which operates in a distributed manner and enables the UAV swarm to build a common consensus dynamically, during the evolution of the leakage phenomenon. The overall performance is tested in a simulative yet realistic environment using ANSYS Fluent suite, considering a simultaneous gas-leak incident at two different points. Aside from the standalone evaluation study, the proposed gas-plume tracking scheme is able to outperform a state-of-the-art alternative algorithm, namely Efficient Global Optimization (EGO), in various simulation setups, deploying a different number of UAVs on the field.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This article investigates the problem of deploying a swarm of UAVs equipped with gas sensors for industrial remote gas-plume sensing. This setup’s objective is to continuously adjust the swarm formation to maximize the combined perception for the dynamically evolved plume’s cloud, focusing around areas with the highest concentration/intensity. Initially, such a setup is formulated into an optimization problem, the solution of which could be acquired by the maximization of an appropriately defined objective function. Due to the model-free approach, this objective function’s analytical form is not available, prohibiting standard gradient descent methodologies. To this end, a tracking algorithm is developed and studied, which operates in a distributed manner and enables the UAV swarm to build a common consensus dynamically, during the evolution of the leakage phenomenon. The overall performance is tested in a simulative yet realistic environment using ANSYS Fluent suite, considering a simultaneous gas-leak incident at two different points. Aside from the standalone evaluation study, the proposed gas-plume tracking scheme is able to outperform a state-of-the-art alternative algorithm, namely Efficient Global Optimization (EGO), in various simulation setups, deploying a different number of UAVs on the field.
- https://www.sciencedirect.com/science/article/pii/S0045790621000525
- https://kapoutsis.info/wp-content/uploads/2021/03/Building-Synergetic-Consensus-[...]
- https://www.youtube.com/watch?v=9jKD6ORLxgQ&feature=youtu.be
- https://www.youtube.com/watch?v=sJeSuCd8ciw
- https://github.com/athakapo/A-distributed-plug-n-play-algorithm-for-multi-robot-[...]
- doi:10.1016/j.compeleceng.2021.107029
23.
I. T. Michailidis; A. Ch. Kapoutsis; Ch. D. Korkas; P. T. Michailidis K. A. Alexandridou; Ch. Ravanis; E. B. Kosmatopoulos
Embedding autonomy in large-scale IoT ecosystems using CAO and L4G-CAO Journal Article
In: Discover Internet of Things, vol. 1, no. 8, 2021.
@article{Michailidis2021,
title = {Embedding autonomy in large-scale IoT ecosystems using CAO and L4G-CAO},
author = {I. T. Michailidis and A. Ch. Kapoutsis and Ch. D. Korkas and P. T. Michailidis K. A. Alexandridou and Ch. Ravanis and E. B. Kosmatopoulos},
url = {https://link.springer.com/article/10.1007/s43926-021-00003-w
https://kapoutsis.info/wp-content/uploads/2021/03/Discover_IoT___Springer___Revision.pdf},
doi = {10.1007/s43926-021-00003-w},
year = {2021},
date = {2021-02-24},
journal = {Discover Internet of Things},
volume = {1},
number = {8},
abstract = {Recently, special attention has been paid in developing methodologies and systems for embedding autonomy within smart devices (Things). Moreover, as Things typically operate in an interconnected IoT ecosystem, autonomous operation must be performed in a cooperative fashion so the different Things coordinate their autonomous actions towards meeting high-level objectives and policies. Embedding Things with cooperative autonomy typically requires a tedious and costly effort not only during the original ecosystem deployment but throughout its lifetime. The current study describes CAO (Cognitive Adaptive Optimization)—and its distributed counterpart L4G-CAO (Local for Global Cognitive Adaptive Optimization)—which can overcome this shortcoming. CAO and L4G-CAO—which have recently been introduced and tested in a variety of IoT applications—can embed Things with cooperative autonomy in a plug-n-play fashion, i.e., without requiring the aforementioned tedious and costly effort. Results of the application of the aforementioned approaches in three different application domains (smart homes and districts, intelligent traffic systems and coordinated swarms of robots) are also presented. The presented results demonstrate the potential, of both approaches, to exploit the IoT automation functionalities in order to significantly improve the overall IoT performance without tedious effort.
},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Recently, special attention has been paid in developing methodologies and systems for embedding autonomy within smart devices (Things). Moreover, as Things typically operate in an interconnected IoT ecosystem, autonomous operation must be performed in a cooperative fashion so the different Things coordinate their autonomous actions towards meeting high-level objectives and policies. Embedding Things with cooperative autonomy typically requires a tedious and costly effort not only during the original ecosystem deployment but throughout its lifetime. The current study describes CAO (Cognitive Adaptive Optimization)—and its distributed counterpart L4G-CAO (Local for Global Cognitive Adaptive Optimization)—which can overcome this shortcoming. CAO and L4G-CAO—which have recently been introduced and tested in a variety of IoT applications—can embed Things with cooperative autonomy in a plug-n-play fashion, i.e., without requiring the aforementioned tedious and costly effort. Results of the application of the aforementioned approaches in three different application domains (smart homes and districts, intelligent traffic systems and coordinated swarms of robots) are also presented. The presented results demonstrate the potential, of both approaches, to exploit the IoT automation functionalities in order to significantly improve the overall IoT performance without tedious effort.
22.
D. I. Koutras; A. Ch. Kapoutsis; E. B. Kosmatopoulos
Autonomous and Cooperative Design of the Monitor Positions for a Team of UAVs to Maximize the Quantity and Quality of Detected Objects Journal Article
In: IEEE Robotics and Automation Letters, vol. 5, no. 3, pp. 4986-4993, 2020, ISSN: 2377-3766.
@article{koutras2020autonomous,
title = {Autonomous and Cooperative Design of the Monitor Positions for a Team of UAVs to Maximize the Quantity and Quality of Detected Objects},
author = {D. I. Koutras and A. Ch. Kapoutsis and E. B. Kosmatopoulos},
editor = { Jonathan Roberts},
url = {https://ieeexplore.ieee.org/document/9126171
https://arxiv.org/abs/2007.01247
https://paperswithcode.com/paper/autonomous-and-cooperative-design-of-the
https://www.youtube.com/watch?v=L8ycmS20rZs
https://kapoutsis.info/wp-content/uploads/2020/11/IROS_Main_Presentation.pptx
https://github.com/dimikout3/ConvCAOAirSim
},
doi = {10.1109/LRA.2020.3004780},
issn = {2377-3766},
year = {2020},
date = {2020-07-01},
urldate = {2020-07-01},
journal = {IEEE Robotics and Automation Letters},
volume = {5},
number = {3},
pages = {4986-4993},
abstract = {This paper tackles the problem of positioning a swarm of UAVs inside a completely unknown terrain, having as objective to maximize the overall situational awareness. The situational awareness is expressed by the number and quality of unique objects of interest, inside the UAVs’ fields of view. YOLOv3 and a system to identify duplicate objects of interest were employed to assign a single score to each UAVs’ configuration. Then, a novel navigation algorithm, capable of optimizing the previously defined score, without taking into consideration the dynamics of either UAVs or environment, is proposed. A cornerstone of the proposed approach is that it shares the same convergence characteristics as the block coordinate descent (BCD) family of approaches. The effectiveness and performance of the proposed navigation scheme were evaluated utilizing a series of experiments inside the AirSim simulator. The experimental evaluation indicates that the proposed navigation algorithm was able to consistently navigate the swarm of UAVs to “strategic” monitoring positions and also adapt to the different number of swarm sizes. Source code is available at https://github.com/dimikout3/ConvCAOAirSim.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper tackles the problem of positioning a swarm of UAVs inside a completely unknown terrain, having as objective to maximize the overall situational awareness. The situational awareness is expressed by the number and quality of unique objects of interest, inside the UAVs’ fields of view. YOLOv3 and a system to identify duplicate objects of interest were employed to assign a single score to each UAVs’ configuration. Then, a novel navigation algorithm, capable of optimizing the previously defined score, without taking into consideration the dynamics of either UAVs or environment, is proposed. A cornerstone of the proposed approach is that it shares the same convergence characteristics as the block coordinate descent (BCD) family of approaches. The effectiveness and performance of the proposed navigation scheme were evaluated utilizing a series of experiments inside the AirSim simulator. The experimental evaluation indicates that the proposed navigation algorithm was able to consistently navigate the swarm of UAVs to “strategic” monitoring positions and also adapt to the different number of swarm sizes. Source code is available at https://github.com/dimikout3/ConvCAOAirSim.
- https://ieeexplore.ieee.org/document/9126171
- https://arxiv.org/abs/2007.01247
- https://paperswithcode.com/paper/autonomous-and-cooperative-design-of-the
- https://www.youtube.com/watch?v=L8ycmS20rZs
- https://kapoutsis.info/wp-content/uploads/2020/11/IROS_Main_Presentation.pptx
- https://github.com/dimikout3/ConvCAOAirSim
- doi:10.1109/LRA.2020.3004780
21.
A. Ch. Kapoutsis; S. A. Chatzichristofis; E. B. Kosmatopoulos
A distributed, plug-n-play algorithm for multi-robot applications with a priori non-computable objective functions Journal Article
In: The International Journal of Robotics Research, vol. 38, no. 7, pp. 813-832, 2019, ISSN: 1573-0409.
@article{kapoutsis2019distributed,
title = {A distributed, plug-n-play algorithm for multi-robot applications with a priori non-computable objective functions},
author = {A. Ch. Kapoutsis and S. A. Chatzichristofis and E. B. Kosmatopoulos},
editor = {John M Hollerbach},
url = {https://journals.sagepub.com/doi/10.1177/0278364919845054
https://arxiv.org/abs/2111.07441
https://www.youtube.com/watch?v=HTYfnbRvf5U
https://github.com/athakapo/A-distributed-plug-n-play-algorithm-for-multi-robot-applications
https://paperswithcode.com/paper/a-distributed-plug-n-play-algorithm-for-multi
},
doi = {https://doi.org/10.1177/0278364919845054},
issn = {1573-0409},
year = {2019},
date = {2019-05-08},
urldate = {2019-05-08},
journal = {The International Journal of Robotics Research},
volume = {38},
number = {7},
pages = {813-832},
abstract = {This paper presents a distributed algorithm applicable to a wide range of practical multi-robot applications. In such multi-robot applications, the user-defined objectives of the mission can be cast as a general optimization problem, without explicit guidelines of the subtasks per different robot. Owing to the unknown environment, unknown robot dynamics, sensor nonlinearities, etc., the analytic form of the optimization cost function is not available a priori. Therefore, standard gradient-descent-like algorithms are not applicable to these problems. To tackle this, we introduce a new algorithm that carefully designs each robot’s subcost function, the optimization of which can accomplish the overall team objective. Upon this transformation, we propose a distributed methodology based on the cognitive-based adaptive optimization (CAO) algorithm, that is able to approximate the evolution of each robot’s cost function and to adequately optimize its decision variables (robot actions). The latter can be achieved by online learning only the problem-specific characteristics that affect the accomplishment of mission objectives. The overall, low-complexity algorithm can straightforwardly incorporate any kind of operational constraint, is fault tolerant, and can appropriately tackle time-varying cost functions. A cornerstone of this approach is that it shares the same convergence characteristics as those of block coordinate descent algorithms. The proposed algorithm is evaluated in three heterogeneous simulation set-ups under multiple scenarios, against both general-purpose and problem-specific algorithms.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper presents a distributed algorithm applicable to a wide range of practical multi-robot applications. In such multi-robot applications, the user-defined objectives of the mission can be cast as a general optimization problem, without explicit guidelines of the subtasks per different robot. Owing to the unknown environment, unknown robot dynamics, sensor nonlinearities, etc., the analytic form of the optimization cost function is not available a priori. Therefore, standard gradient-descent-like algorithms are not applicable to these problems. To tackle this, we introduce a new algorithm that carefully designs each robot’s subcost function, the optimization of which can accomplish the overall team objective. Upon this transformation, we propose a distributed methodology based on the cognitive-based adaptive optimization (CAO) algorithm, that is able to approximate the evolution of each robot’s cost function and to adequately optimize its decision variables (robot actions). The latter can be achieved by online learning only the problem-specific characteristics that affect the accomplishment of mission objectives. The overall, low-complexity algorithm can straightforwardly incorporate any kind of operational constraint, is fault tolerant, and can appropriately tackle time-varying cost functions. A cornerstone of this approach is that it shares the same convergence characteristics as those of block coordinate descent algorithms. The proposed algorithm is evaluated in three heterogeneous simulation set-ups under multiple scenarios, against both general-purpose and problem-specific algorithms.
- https://journals.sagepub.com/doi/10.1177/0278364919845054
- https://arxiv.org/abs/2111.07441
- https://www.youtube.com/watch?v=HTYfnbRvf5U
- https://github.com/athakapo/A-distributed-plug-n-play-algorithm-for-multi-robot-[...]
- https://paperswithcode.com/paper/a-distributed-plug-n-play-algorithm-for-multi
- doi:https://doi.org/10.1177/0278364919845054
20.
A. Ch. Kapoutsis; S. A. Chatzichristofis; E. B. Kosmatopoulos
DARP: Divide Areas Algorithm for Optimal Multi-Robot Coverage Path Planning Journal Article
In: Journal of Intelligent & Robotic Systems, vol. 86, no. 3, pp. 663–680, 2017, ISSN: 1573-0409.
@article{kapoutsis2017darp,
title = {DARP: Divide Areas Algorithm for Optimal Multi-Robot Coverage Path Planning},
author = {A. Ch. Kapoutsis and S. A. Chatzichristofis and E. B. Kosmatopoulos},
editor = {Spyros Tzafestas and Kimon P. Valavanis},
url = {https://link.springer.com/article/10.1007/s10846-016-0461-x
https://kapoutsis.info/wp-content/uploads/2017/02/j3.pdf
https://medium.com/@athanasios.kapoutsis/darp-divide-areas-algorithm-for-optimal-multi-robot-coverage-path-planning-2fed77b990a3
https://www.youtube.com/watch?v=LrGfvma41Ak
https://kapoutsis.info/wp-content/uploads/2021/06/DARP.pptx
https://kapoutsis.info/wp-content/uploads/2017/01/DARP.zip
https://github.com/athakapo/DARP
https://github.com/alice-st/DARP-Python
https://github.com/cpswarm/swarm_functions/tree/kinetic-devel/area_division},
doi = {10.1007/s10846-016-0461-x},
issn = {1573-0409},
year = {2017},
date = {2017-04-01},
journal = {Journal of Intelligent & Robotic Systems},
volume = {86},
number = {3},
pages = {663–680},
abstract = {This paper deals with the path planning problem of a team of mobile robots, in order to cover an area of interest, with prior-defined obstacles. For the single robot case, also known as single robot coverage path planning (CPP), an O(n) optimal methodology has already been proposed and evaluated in the literature, where n is the grid size. The majority of existing algorithms for the multi robot case (mCPP), utilize the aforementioned algorithm. Due to the complexity, however, of the mCPP, the best the existing mCPP algorithms can perform is at most 16 times the optimal solution, in terms of time needed for the robot team to accomplish the coverage task, while the time required for calculating the solution is polynomial. In the present paper, we propose a new algorithm which converges to the optimal solution, at least in cases where one exists. The proposed technique transforms the original integer programming problem (mCPP) into several single-robot problems (CPP), the solutions of which constitute the optimal mCPP solution, alleviating the original mCPP explosive combinatorial complexity. Although it is not possible to analytically derive bounds regarding the complexity of the proposed algorithm, extensive numerical analysis indicates that the complexity is bounded by polynomial curves for practical sized inputs. In the heart of the proposed approach lies the DARP algorithm, which divides the terrain into a number of equal areas each corresponding to a specific robot, so as to guarantee complete coverage, non-backtracking solution, minimum coverage path, while at the same time does not need any preparatory stage (video demonstration and standalone application are available on-line http://tinyurl.com/DARP-app).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper deals with the path planning problem of a team of mobile robots, in order to cover an area of interest, with prior-defined obstacles. For the single robot case, also known as single robot coverage path planning (CPP), an O(n) optimal methodology has already been proposed and evaluated in the literature, where n is the grid size. The majority of existing algorithms for the multi robot case (mCPP), utilize the aforementioned algorithm. Due to the complexity, however, of the mCPP, the best the existing mCPP algorithms can perform is at most 16 times the optimal solution, in terms of time needed for the robot team to accomplish the coverage task, while the time required for calculating the solution is polynomial. In the present paper, we propose a new algorithm which converges to the optimal solution, at least in cases where one exists. The proposed technique transforms the original integer programming problem (mCPP) into several single-robot problems (CPP), the solutions of which constitute the optimal mCPP solution, alleviating the original mCPP explosive combinatorial complexity. Although it is not possible to analytically derive bounds regarding the complexity of the proposed algorithm, extensive numerical analysis indicates that the complexity is bounded by polynomial curves for practical sized inputs. In the heart of the proposed approach lies the DARP algorithm, which divides the terrain into a number of equal areas each corresponding to a specific robot, so as to guarantee complete coverage, non-backtracking solution, minimum coverage path, while at the same time does not need any preparatory stage (video demonstration and standalone application are available on-line http://tinyurl.com/DARP-app).
- https://link.springer.com/article/10.1007/s10846-016-0461-x
- https://kapoutsis.info/wp-content/uploads/2017/02/j3.pdf
- https://medium.com/@athanasios.kapoutsis/darp-divide-areas-algorithm-for-optimal[...]
- https://www.youtube.com/watch?v=LrGfvma41Ak
- https://kapoutsis.info/wp-content/uploads/2021/06/DARP.pptx
- https://kapoutsis.info/wp-content/uploads/2017/01/DARP.zip
- https://github.com/athakapo/DARP
- https://github.com/alice-st/DARP-Python
- https://github.com/cpswarm/swarm_functions/tree/kinetic-devel/area_division
- doi:10.1007/s10846-016-0461-x
19.
A. Ch. Kapoutsis; S. A. Chatzichristofis; L. Doitsidis; J. Sousa; J. Pinto; J. Braga; E. B. Kosmatopoulos
Real-Time Adaptive Multi-Robot Exploration with Application to Underwater Map Construction Journal Article
In: Autonomous Robots, vol. 40, no. 6, pp. 987–1015, 2016, ISSN: 0929-5593.
@article{kapoutsis2015real,
title = {Real-Time Adaptive Multi-Robot Exploration with Application to Underwater Map Construction},
author = {A. Ch. Kapoutsis and S. A. Chatzichristofis and L. Doitsidis and J. Sousa and J. Pinto and J. Braga and E. B. Kosmatopoulos},
url = {https://link.springer.com/article/10.1007/s10514-015-9510-8
https://kapoutsis.info/wp-content/uploads/2016/04/noptilus_Final.pdf
https://www.youtube.com/watch?v=menK5tMRw-s
},
doi = {https://doi.org/10.1007/s10514-015-9510-8},
issn = {0929-5593},
year = {2016},
date = {2016-08-15},
journal = {Autonomous Robots},
volume = {40},
number = {6},
pages = {987–1015},
abstract = {This paper deals with the problem of autonomous exploration of unknown areas using teams of Autonomous X Vehicles (AXVs)—with X standing for Aerial, Underwater or Sea-surface—where the AXVs have to autonomously navigate themselves so as to construct an accurate map of the unknown area. Such a problem can be transformed into a dynamic optimization problem which, however, is NP-complete and thus infeasible to be solved. A usual attempt is to relax this problem by employing greedy (optimal one-step-ahead) solutions which may end-up quite problematic. In this paper, we first show that optimal one-step-ahead exploration schemes that are based on a transformed optimization criterion can lead to highly efficient solutions to the multi-AXV exploration. Such a transformed optimization criterion is constructed using both theoretical analysis and experimental investigations and attempts to minimize the “disturbing” effect of deadlocks and nonlinearities to the overall exploration scheme. As, however, optimal one-step-ahead solutions to the transformed optimization criterion cannot be practically obtained using conventional optimization schemes, the second step in our approach is to combine the use of the transformed optimization criterion with the cognitive adaptive optimization (CAO): CAO is a practicably feasible computational methodology which adaptively provides an accurate approximation of the optimal one-step-ahead solutions. The combination of the transformed optimization criterion with CAO results in a multi-AXV exploration scheme which is both practically implementable and provides with quite efficient solutions as it is shown both by theoretical analysis and, most importantly, by extensive simulation experiments and real-life underwater sea-floor mapping experiments in the Leixes port, Portugal.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper deals with the problem of autonomous exploration of unknown areas using teams of Autonomous X Vehicles (AXVs)—with X standing for Aerial, Underwater or Sea-surface—where the AXVs have to autonomously navigate themselves so as to construct an accurate map of the unknown area. Such a problem can be transformed into a dynamic optimization problem which, however, is NP-complete and thus infeasible to be solved. A usual attempt is to relax this problem by employing greedy (optimal one-step-ahead) solutions which may end-up quite problematic. In this paper, we first show that optimal one-step-ahead exploration schemes that are based on a transformed optimization criterion can lead to highly efficient solutions to the multi-AXV exploration. Such a transformed optimization criterion is constructed using both theoretical analysis and experimental investigations and attempts to minimize the “disturbing” effect of deadlocks and nonlinearities to the overall exploration scheme. As, however, optimal one-step-ahead solutions to the transformed optimization criterion cannot be practically obtained using conventional optimization schemes, the second step in our approach is to combine the use of the transformed optimization criterion with the cognitive adaptive optimization (CAO): CAO is a practicably feasible computational methodology which adaptively provides an accurate approximation of the optimal one-step-ahead solutions. The combination of the transformed optimization criterion with CAO results in a multi-AXV exploration scheme which is both practically implementable and provides with quite efficient solutions as it is shown both by theoretical analysis and, most importantly, by extensive simulation experiments and real-life underwater sea-floor mapping experiments in the Leixes port, Portugal.
18.
C. Iakovidou; N. Anagnostopoulos; A. Ch. Kapoutsis; Y. Boutalis; M. Lux; S. A. Chatzichristofis
Localizing Global Descriptors for Content Based Image Retrieval Journal Article
In: EURASIP Journal on Advances in Signal Processing, no. 80, pp. 1-20, 2015.
@article{iakovidou2015localizing,
title = {Localizing Global Descriptors for Content Based Image Retrieval},
author = {C. Iakovidou and N. Anagnostopoulos and A. Ch. Kapoutsis and Y. Boutalis and M. Lux and S. A. Chatzichristofis},
url = {https://link.springer.com/article/10.1186/s13634-015-0262-6
},
doi = {https://doi.org/10.1186/s13634-015-0262-6},
year = {2015},
date = {2015-09-07},
journal = {EURASIP Journal on Advances in Signal Processing},
number = {80},
pages = {1-20},
abstract = {In this paper, we explore, extend and simplify the localization of the description ability of the well-established MPEG-7 (Scalable Colour Descriptor (SCD), Colour Layout Descriptor (CLD) and Edge Histogram Descriptor (EHD)) and MPEG-7-like (Color and Edge Directivity Descriptor (CEDD)) global descriptors, which we call the SIMPLE family of descriptors. Sixteen novel descriptors are introduced that utilize four different sampling strategies for the extraction of image patches to be used as points of interest. Designing with focused attention for content-based image retrieval tasks, we investigate, analyse and propose the preferred process for the definition of the parameters involved (point detection, description, codebook sizes and descriptors’ weighting strategies). The experimental results conducted on four different image collections reveal an astonishing boost in the retrieval performance of the proposed descriptors compared to their performance in their original global form. Furthermore, they manage to outperform common SIFT- and SURF-based approaches while they perform comparably, if not better, against recent state-of-the-art methods that base their success on much more complex data manipulation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we explore, extend and simplify the localization of the description ability of the well-established MPEG-7 (Scalable Colour Descriptor (SCD), Colour Layout Descriptor (CLD) and Edge Histogram Descriptor (EHD)) and MPEG-7-like (Color and Edge Directivity Descriptor (CEDD)) global descriptors, which we call the SIMPLE family of descriptors. Sixteen novel descriptors are introduced that utilize four different sampling strategies for the extraction of image patches to be used as points of interest. Designing with focused attention for content-based image retrieval tasks, we investigate, analyse and propose the preferred process for the definition of the parameters involved (point detection, description, codebook sizes and descriptors’ weighting strategies). The experimental results conducted on four different image collections reveal an astonishing boost in the retrieval performance of the proposed descriptors compared to their performance in their original global form. Furthermore, they manage to outperform common SIFT- and SURF-based approaches while they perform comparably, if not better, against recent state-of-the-art methods that base their success on much more complex data manipulation.
Conferences
17.
A. Stefanopoulou; S. Gkelios; A. Ch. Kapoutsis; E. B. Kosmatopoulos; Y. S. Boutalis
Spline-Based Dynamic Object Handling in Autonomous Vehicles: A Model-Based Path Planning Algorithm Conference
2023 31st Mediterranean Conference on Control and Automation (MED), IEEExplore, 2023, ISBN: 979-8-3503-1543-1.
@conference{Stefanopoulou2023,
title = {Spline-Based Dynamic Object Handling in Autonomous Vehicles: A Model-Based Path Planning Algorithm},
author = {A. Stefanopoulou and S. Gkelios and A. Ch. Kapoutsis and E. B. Kosmatopoulos and Y. S. Boutalis},
url = {https://ieeexplore.ieee.org/abstract/document/10185762
https://kapoutsis.info/wp-content/uploads/2023/08/Spline-Based_Dynamic_Object_Handling_in_Autonomous_Vehicles_A_Model-Based_Path_Planning_Algorithm.pdf},
doi = {10.1109/MED59994.2023.10185762},
isbn = {979-8-3503-1543-1},
year = {2023},
date = {2023-06-26},
urldate = {2023-06-26},
booktitle = {2023 31st Mediterranean Conference on Control and Automation (MED)},
pages = {348-355},
publisher = {IEEExplore},
abstract = {In this study we propose a model-based dynamic path planning algorithm that is designed to navigate Autonomous Vehicles through complex and dynamic environments. To achieve that, a novel spline-based approach is utilized for the production of several candidate paths along a predetermined route and a Gaussian-based function is utilized for their evaluation. Our algorithm takes into account various factors, such as static and dynamic objects, to make the appropriate decisions for the vehicle’s path, making it a promising solution for such objects during an autonomous vehicle navigation. The algorithm was tested in high-fidelity scenarios using CARLA Simulator, which is a powerful tool for simulating autonomous vehicle scenarios. The results indicate that the proposed algorithm is capable of generating efficient and safe paths for the vehicle to follow.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In this study we propose a model-based dynamic path planning algorithm that is designed to navigate Autonomous Vehicles through complex and dynamic environments. To achieve that, a novel spline-based approach is utilized for the production of several candidate paths along a predetermined route and a Gaussian-based function is utilized for their evaluation. Our algorithm takes into account various factors, such as static and dynamic objects, to make the appropriate decisions for the vehicle’s path, making it a promising solution for such objects during an autonomous vehicle navigation. The algorithm was tested in high-fidelity scenarios using CARLA Simulator, which is a powerful tool for simulating autonomous vehicle scenarios. The results indicate that the proposed algorithm is capable of generating efficient and safe paths for the vehicle to follow.
16.
G. Kyprianou; L. Doitsidis; A. Ch. Kapoutsis; Z. Zinonos; S. A. Chatzichristofis
Bin-Picking in the Industry 4.0 Era Conference
2023 IEEE International Conference on Consumer Electronics (ICCE), IEEE, 2023, ISBN: 978-1-6654-9130-3.
@conference{Kyprianou2023,
title = {Bin-Picking in the Industry 4.0 Era},
author = {G. Kyprianou and L. Doitsidis and A. Ch. Kapoutsis and Z. Zinonos and S. A. Chatzichristofis},
url = {https://www.researchgate.net/publication/368620028_Bin-Picking_in_the_Industry_40_Era
https://kapoutsis.info/wp-content/uploads/2023/03/Bin-Picking_in_the_Industry_4.0_Era.pdf},
doi = {doi.org/10.1109/ICCE56470.2023.10043452},
isbn = {978-1-6654-9130-3},
year = {2023},
date = {2023-02-17},
booktitle = {2023 IEEE International Conference on Consumer Electronics (ICCE)},
publisher = {IEEE},
abstract = {In this paper, we are trying to examine the role of robots in the Industry 4.0 Era. After a brief chronology and an updated literature review on the field, we are trying to examine one of the biggest problems in today's industrial automation, namely in Robotic bin-picking. Its objective is to manage to control a robot with multiple sensory motors attached and be able to collect identified objects with random poses out of a bin, containing a collection of those objects, using any kind of robot-end effector and place it in a predetermined location in the working area. As we observe, the Robotic bin-picking task is divided into three main subcategories: i) perception of the environment, ii) the tooling and iii) the processing architecture. These subcategories are observed thoroughly in the paper and the state-of-the-art techniques used are presented.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In this paper, we are trying to examine the role of robots in the Industry 4.0 Era. After a brief chronology and an updated literature review on the field, we are trying to examine one of the biggest problems in today's industrial automation, namely in Robotic bin-picking. Its objective is to manage to control a robot with multiple sensory motors attached and be able to collect identified objects with random poses out of a bin, containing a collection of those objects, using any kind of robot-end effector and place it in a predetermined location in the working area. As we observe, the Robotic bin-picking task is divided into three main subcategories: i) perception of the environment, ii) the tooling and iii) the processing architecture. These subcategories are observed thoroughly in the paper and the state-of-the-art techniques used are presented.
15.
E. K.Raptis; G. D. Karatzinis; M. Krestenitis; A. Ch. Kapoutsis; K. Ioannidis; S. Vrochidis; I. Kompatsiaris; E. B. Kosmatopoulos
Multimodal Data Collection System for UAV-based Precision Agriculture Applications Conference
2022 Sixth IEEE International Conference on Robotic Computing (IRC), IEEE, 2023, ISBN: 978-1-6654-7260-9.
@conference{K.Raptis2023,
title = {Multimodal Data Collection System for UAV-based Precision Agriculture Applications},
author = {E. K.Raptis and G. D. Karatzinis and M. Krestenitis and A. Ch. Kapoutsis and K. Ioannidis and S. Vrochidis and I. Kompatsiaris and E. B. Kosmatopoulos},
url = {https://ieeexplore.ieee.org/document/10023715
https://www.researchgate.net/publication/367399373_Multimodal_Data_Collection_System_for_UAV-based_Precision_Agriculture_Applications},
doi = {10.1109/IRC55401.2022.00007},
isbn = {978-1-6654-7260-9},
year = {2023},
date = {2023-01-24},
urldate = {2023-01-24},
booktitle = {2022 Sixth IEEE International Conference on Robotic Computing (IRC)},
pages = {1-7},
publisher = {IEEE},
abstract = {Unmanned Aerial Vehicles (UAVs) consist of emerging technologies that have the potential to be used gradually in various sectors providing a wide range of applications. In agricultural tasks, the UAV-based solutions are supplanting the labor and time-intensive traditional crop management practices. In this direction, this work proposes an automated framework for efficient data collection in crops employing autonomous path planning operational modes. The first method assures an optimal and collision-free path route for scanning the under examination area. The collected data from the oversight perspective are used for orthomocaic creation and subsequently, vegetation indices are extracted to assess the health levels of crops. The second operational mode is considered as an inspection extension for further on-site enriched information collection, performing fixed radius cycles around the central points of interest. A real-world weed detection application is performed verifying the acquired information using both operational modes. The weed detection performance has been evaluated utilizing a well-known Convolutional Neural Network (CNN), named Feature Pyramid Network (FPN), providing sufficient results in terms of Intersection over Union (IoU).},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Unmanned Aerial Vehicles (UAVs) consist of emerging technologies that have the potential to be used gradually in various sectors providing a wide range of applications. In agricultural tasks, the UAV-based solutions are supplanting the labor and time-intensive traditional crop management practices. In this direction, this work proposes an automated framework for efficient data collection in crops employing autonomous path planning operational modes. The first method assures an optimal and collision-free path route for scanning the under examination area. The collected data from the oversight perspective are used for orthomocaic creation and subsequently, vegetation indices are extracted to assess the health levels of crops. The second operational mode is considered as an inspection extension for further on-site enriched information collection, performing fixed radius cycles around the central points of interest. A real-world weed detection application is performed verifying the acquired information using both operational modes. The weed detection performance has been evaluated utilizing a well-known Convolutional Neural Network (CNN), named Feature Pyramid Network (FPN), providing sufficient results in terms of Intersection over Union (IoU).
14.
I. T. Michailidis; A. Ch. Kapoutsis; E. B. Kosmatopoulos; Y. Boutalis
Dynamic Plume Tracking Utilizing Symbiotic Heterogeneous Remote Sensing Platforms Conference
IFIP International Conference on Artificial Intelligence Applications and Innovations, vol. 627, Springer, 2021, ISBN: 978-3-030-79150-6.
@conference{Michailidis2021b,
title = {Dynamic Plume Tracking Utilizing Symbiotic Heterogeneous Remote Sensing Platforms},
author = {I. T. Michailidis and A. Ch. Kapoutsis and E. B. Kosmatopoulos and Y. Boutalis},
url = {https://link.springer.com/chapter/10.1007%2F978-3-030-79150-6_48
https://kapoutsis.info/wp-content/uploads/2021/06/aiai2021.pdf
https://kapoutsis.info/wp-content/uploads/2021/06/AIAI2021_or.pptx
https://github.com/athakapo/A-distributed-plug-n-play-algorithm-for-multi-robot-applications},
doi = {10.1007/978-3-030-79150-6_48},
isbn = {978-3-030-79150-6},
year = {2021},
date = {2021-06-22},
urldate = {2021-06-22},
booktitle = {IFIP International Conference on Artificial Intelligence Applications and Innovations},
volume = {627},
pages = {607-618},
publisher = {Springer},
abstract = {The current study focuses on the problem of continuously tracking a dynamically evolving CH4 plume utilizing a mutually built consensus by heterogeneous sensing platforms: mobile and static sensors. Identifying the major complexities and emergent dynamics (leakage source, intensity, time) of such problem, a distributed, multi-agent, optimization algorithm was developed and evaluated in an indoor continuous plume-tracking application (where reaction time is critical due to the limited volume available for air saturation by the CH4 dispersion). The high-fidelity ANSYS Fluent suite realistic simulation environment was used to acquire the gas diffusion evolution through time. The analysis of the simulation results indicated that the proposed algorithm was capable of continuously readapting the mobile sensing platforms formation according to the density and the dispersed volume plume; combining additive information from the static sensors. Moreover, a scalability analysis with respect to the number of mobile platforms revealed the flexibility of the proposed algorithm to different numbers of available assets.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The current study focuses on the problem of continuously tracking a dynamically evolving CH4 plume utilizing a mutually built consensus by heterogeneous sensing platforms: mobile and static sensors. Identifying the major complexities and emergent dynamics (leakage source, intensity, time) of such problem, a distributed, multi-agent, optimization algorithm was developed and evaluated in an indoor continuous plume-tracking application (where reaction time is critical due to the limited volume available for air saturation by the CH4 dispersion). The high-fidelity ANSYS Fluent suite realistic simulation environment was used to acquire the gas diffusion evolution through time. The analysis of the simulation results indicated that the proposed algorithm was capable of continuously readapting the mobile sensing platforms formation according to the density and the dispersed volume plume; combining additive information from the static sensors. Moreover, a scalability analysis with respect to the number of mobile platforms revealed the flexibility of the proposed algorithm to different numbers of available assets.
- https://link.springer.com/chapter/10.1007%2F978-3-030-79150-6_48
- https://kapoutsis.info/wp-content/uploads/2021/06/aiai2021.pdf
- https://kapoutsis.info/wp-content/uploads/2021/06/AIAI2021_or.pptx
- https://github.com/athakapo/A-distributed-plug-n-play-algorithm-for-multi-robot-[...]
- doi:10.1007/978-3-030-79150-6_48
13.
G. L. Maglione; L. Berretta; S. Godfrey; S. D. Apostolidis; A. Ch. Kapoutsis; E. B. Kosmatopoulos; A. Tremori
M&S Based Testbed to Support V&V of Autonomous Resources Task Coordinator Conference
International Conference on Modelling and Simulation for Autonomous Systems, Springer, 2021, ISBN: 978-3-030-70740-8.
@conference{Maglione2021,
title = {M&S Based Testbed to Support V&V of Autonomous Resources Task Coordinator},
author = {G. L. Maglione and L. Berretta and S. Godfrey and S. D. Apostolidis and A. Ch. Kapoutsis and E. B. Kosmatopoulos and A. Tremori },
url = {https://link.springer.com/chapter/10.1007%2F978-3-030-70740-8_8
https://kapoutsis.info/wp-content/uploads/2021/03/MesasPaper_ROBORDER_CMRE_CERTH.pdf},
doi = {10.1007/978-3-030-70740-8_8},
isbn = {978-3-030-70740-8},
year = {2021},
date = {2021-03-05},
booktitle = {International Conference on Modelling and Simulation for Autonomous Systems},
pages = {123-138},
publisher = {Springer},
abstract = {Political instability around the world continues to place a significant emphasis on border control. Monitoring these borders requires persistent surveillance in a variety of remote, hazardous and hostile environments. While recent developments in autonomous and unmanned systems promise to provide a new generation of tools to assist in border control missions, the complexity of designing, testing and operating large-scale systems limits their adoption.
A seam of research is developing around the use of Modelling and Simulation (M&S) methodologies to support the development, testing and operation of complex, multi-domain autonomous systems deployments. This paper builds upon recent progress in the use of M&S to conduct Verification and Validation (V&V) of complex software functionalities.
Specifically, the authors have designed and developed an HLA (High Level Architecture) interoperable M&S testbed capability applied in support of the European Union’s ROBORDER H2020 project. V&V has been completed on the Autonomous Resources Task Coordinator (ARTC) software, a module that will be employed in live demonstrations to automatically design missions for heterogeneous autonomous assets.
The development and the employment of the interoperable simulation capability is discussed in a scenario designed to test the ARTC. The scenario involves aerial (fixed wing and rotary wing) and underwater assets mounting Electro-Optical/Infra-Red (EO/IR) cameras and pollution detection sensors. Asset and sensor performance is affected by realistic environmental conditions.
The M&S-based test-bed capability has shown the correct operation of the ARTC, efficiently communicating the key findings to a range of stakeholder groups. The work has resulted in the creation and testing of an interoperable, modular, reusable testbed capability that will be reused to further support the wide-spread adoption of autonomous and unmanned systems in a range of operations.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Political instability around the world continues to place a significant emphasis on border control. Monitoring these borders requires persistent surveillance in a variety of remote, hazardous and hostile environments. While recent developments in autonomous and unmanned systems promise to provide a new generation of tools to assist in border control missions, the complexity of designing, testing and operating large-scale systems limits their adoption.
A seam of research is developing around the use of Modelling and Simulation (M&S) methodologies to support the development, testing and operation of complex, multi-domain autonomous systems deployments. This paper builds upon recent progress in the use of M&S to conduct Verification and Validation (V&V) of complex software functionalities.
Specifically, the authors have designed and developed an HLA (High Level Architecture) interoperable M&S testbed capability applied in support of the European Union’s ROBORDER H2020 project. V&V has been completed on the Autonomous Resources Task Coordinator (ARTC) software, a module that will be employed in live demonstrations to automatically design missions for heterogeneous autonomous assets.
The development and the employment of the interoperable simulation capability is discussed in a scenario designed to test the ARTC. The scenario involves aerial (fixed wing and rotary wing) and underwater assets mounting Electro-Optical/Infra-Red (EO/IR) cameras and pollution detection sensors. Asset and sensor performance is affected by realistic environmental conditions.
The M&S-based test-bed capability has shown the correct operation of the ARTC, efficiently communicating the key findings to a range of stakeholder groups. The work has resulted in the creation and testing of an interoperable, modular, reusable testbed capability that will be reused to further support the wide-spread adoption of autonomous and unmanned systems in a range of operations.
A seam of research is developing around the use of Modelling and Simulation (M&S) methodologies to support the development, testing and operation of complex, multi-domain autonomous systems deployments. This paper builds upon recent progress in the use of M&S to conduct Verification and Validation (V&V) of complex software functionalities.
Specifically, the authors have designed and developed an HLA (High Level Architecture) interoperable M&S testbed capability applied in support of the European Union’s ROBORDER H2020 project. V&V has been completed on the Autonomous Resources Task Coordinator (ARTC) software, a module that will be employed in live demonstrations to automatically design missions for heterogeneous autonomous assets.
The development and the employment of the interoperable simulation capability is discussed in a scenario designed to test the ARTC. The scenario involves aerial (fixed wing and rotary wing) and underwater assets mounting Electro-Optical/Infra-Red (EO/IR) cameras and pollution detection sensors. Asset and sensor performance is affected by realistic environmental conditions.
The M&S-based test-bed capability has shown the correct operation of the ARTC, efficiently communicating the key findings to a range of stakeholder groups. The work has resulted in the creation and testing of an interoperable, modular, reusable testbed capability that will be reused to further support the wide-spread adoption of autonomous and unmanned systems in a range of operations.
12.
G. D. Karatzinis; S. D. Apostolidis; A. Ch. Kapoutsis; L. Panagiotopoulou; Y. Boutalis; E. B. Kosmatopoulos
Towards an Integrated Low-Cost Agricultural Monitoring System with Unmanned Aircraft System Conference
International Conference on Unmanned Aircraft Systems (ICUAS), IEEE, 2020, ISBN: 978-1-7281-4279-1.
@conference{karatzinis2020towards,
title = {Towards an Integrated Low-Cost Agricultural Monitoring System with Unmanned Aircraft System},
author = {G. D. Karatzinis and S. D. Apostolidis and A. Ch. Kapoutsis and L. Panagiotopoulou and Y. Boutalis and E. B. Kosmatopoulos},
editor = {Kimon P. Valavanis},
url = {https://ieeexplore.ieee.org/document/9213900
https://kapoutsis.info/wp-content/uploads/2020/09/Vino_Paper_Proceedings_ICUAS2020.pdf
https://kapoutsis.info/wp-content/uploads/2020/09/FINAL_vino.pptx
},
doi = {10.1109/ICUAS48674.2020.9213900},
isbn = {978-1-7281-4279-1},
year = {2020},
date = {2020-09-01},
booktitle = {International Conference on Unmanned Aircraft Systems (ICUAS)},
publisher = {IEEE},
abstract = {Over the last years, an intensified interest has been shown in many studies for precision agriculture. Unmanned Aircraft Systems (UASs) are capable of solving a plethora of surveying tasks due to their flexibility, independence and customization. The incorporation of UASs remote sensing in precision agriculture enhances the abilities of crop mapping, management and identification through vegetation indices. In addition to this, different image analysis and computer vision processes were adopted trying to facilitate field operations in cooperation with human intervention to enhance the overall performance. In this paper, we present a practically oriented application on vineyards towards an integrated low-cost system which utilizes Spiral-STC (Spanning Tree Coverage) algorithm as a Coverage Path Planning (CPP) method. Based on the resulted flight campaign, UAV images were collected, and the incorporated image analysis processes finally extract vegetation knowledge. Also, geo referenced orthophotos and computer vision applications complete the generated oversight of the field. These supportive tools provide farmers with useful information (crop health indicators, weather predictions) letting them extrapolate knowledge and identify crop irregularities.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Over the last years, an intensified interest has been shown in many studies for precision agriculture. Unmanned Aircraft Systems (UASs) are capable of solving a plethora of surveying tasks due to their flexibility, independence and customization. The incorporation of UASs remote sensing in precision agriculture enhances the abilities of crop mapping, management and identification through vegetation indices. In addition to this, different image analysis and computer vision processes were adopted trying to facilitate field operations in cooperation with human intervention to enhance the overall performance. In this paper, we present a practically oriented application on vineyards towards an integrated low-cost system which utilizes Spiral-STC (Spanning Tree Coverage) algorithm as a Coverage Path Planning (CPP) method. Based on the resulted flight campaign, UAV images were collected, and the incorporated image analysis processes finally extract vegetation knowledge. Also, geo referenced orthophotos and computer vision applications complete the generated oversight of the field. These supportive tools provide farmers with useful information (crop health indicators, weather predictions) letting them extrapolate knowledge and identify crop irregularities.
11.
G. Orfanidis; S. Apostolidis; A. Ch. Kapoutsis; K. Ioannidis; E. B. Kosmatopoulos; S. Vrochidis; I. Kompatsiaris
Autonomous swarm of heterogeneous robots for surveillance operations Conference
12th International Conference on Computer Vision Systems (ICVS 2019), International Conference on Computer Vision Systems Springer, 2019, ISBN: 978-3-030-34995-0.
@conference{orfanidisautonomous,
title = {Autonomous swarm of heterogeneous robots for surveillance operations},
author = {G. Orfanidis and S. Apostolidis and A. Ch. Kapoutsis and K. Ioannidis and E. B. Kosmatopoulos and S. Vrochidis and I. Kompatsiaris},
url = {https://link.springer.com/chapter/10.1007%2F978-3-030-34995-0_72
https://kapoutsis.info/wp-content/uploads/2019/09/Workshop-3.8-Georgios_Orfanidis_et.al_.pdf
https://kapoutsis.info/wp-content/uploads/2019/09/Autonomous-swarm-of-heterogeneous-robots-for-surveillance-operations_presentation_v0.4.pptx},
doi = {https://doi.org/10.1007/978-3-030-34995-0_72},
isbn = {978-3-030-34995-0},
year = {2019},
date = {2019-11-23},
booktitle = {12th International Conference on Computer Vision Systems (ICVS 2019)},
pages = {787-796},
publisher = {Springer},
series = {International Conference on Computer Vision Systems},
abstract = {The introduction of Unmanned vehicles (UxVs) in the recent years has created a new security field that can use them as both a potential threat as well as new technological weapons against those threats. Dealing with these issues from the counter-threat perspective, the proposed architecture project focuses on designing and developing a complete system which utilizes the capabilities of multiple UxVs for surveillance objectives in different operational environments. Utilizing a combination of diverse UxVs equipped with various sensors, the developed architecture involves the detection and the characterization of threats based on both visual and thermal data. The identification of objects is enriched with additional information extracted from other sensors such as radars and RF sensors to secure the efficiency of the overall system. The current prototype displays diverse interoperability concerning the multiple visual sources that feed the system with the required optical data. Novel detection models identify the necessary threats while this information is enriched with higher-level semantic representations. Finally, the operator is informed properly according to the visual identification modules and the outcomes of the UxVs operations. The system can provide optimal surveillance capacities to the relevant authorities towards an increased situational awareness.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The introduction of Unmanned vehicles (UxVs) in the recent years has created a new security field that can use them as both a potential threat as well as new technological weapons against those threats. Dealing with these issues from the counter-threat perspective, the proposed architecture project focuses on designing and developing a complete system which utilizes the capabilities of multiple UxVs for surveillance objectives in different operational environments. Utilizing a combination of diverse UxVs equipped with various sensors, the developed architecture involves the detection and the characterization of threats based on both visual and thermal data. The identification of objects is enriched with additional information extracted from other sensors such as radars and RF sensors to secure the efficiency of the overall system. The current prototype displays diverse interoperability concerning the multiple visual sources that feed the system with the required optical data. Novel detection models identify the necessary threats while this information is enriched with higher-level semantic representations. Finally, the operator is informed properly according to the visual identification modules and the outcomes of the UxVs operations. The system can provide optimal surveillance capacities to the relevant authorities towards an increased situational awareness.
10.
G. Salavasidis; A. Ch. Kapoutsis; S. A. Chatzichristofis; P. Michailidis; E. B. Kosmatopoulos
Autonomous Trajectory Design System for Mapping of Unknown Sea-Floors Using a Team of AUVs Conference
2018 European Control Conference (ECC), IEEE, 2018, ISBN: 978-3-9524-2698-2.
@conference{salavasidis2018autonomous,
title = {Autonomous Trajectory Design System for Mapping of Unknown Sea-Floors Using a Team of AUVs},
author = {G. Salavasidis and A. Ch. Kapoutsis and S. A. Chatzichristofis and P. Michailidis and E. B. Kosmatopoulos},
url = {https://ieeexplore.ieee.org/document/8550174
https://kapoutsis.info/wp-content/uploads/2018/06/ECC18_0791_FI.pdf
https://kapoutsis.info/wp-content/uploads/2018/06/PresentationECC_v2.pptx
},
doi = {10.23919/ECC.2018.8550174},
isbn = {978-3-9524-2698-2},
year = {2018},
date = {2018-11-29},
booktitle = {2018 European Control Conference (ECC)},
publisher = {IEEE},
abstract = {This research develops a new on-line trajectory planning algorithm for a team of Autonomous Underwater Vehicles (AUVs). The goal of the AUVs is to cooperatively explore and map the ocean seafloor. As the morphology of the seabed is unknown and complex, standard non-convex algorithms perform insufficiently. To tackle this, a new simulation-based approach is proposed and numerically evaluated. This approach adapts the Parametrized Cognitive-based Adaptive Optimization (PCAO) algorithm. The algorithm transforms the exploration problem to a parametrized decision-making mechanism whose real-time implementation is feasible. Upon that transformation, this scheme calculates off-line a set of decision making mechanism’s parameters that approximate the – non-practically feasible – optimal solution. The advantages of the algorithm are significant computational simplicity, scalability, and the fact that it can straightforwardly embed any type of physical constraints and system limitations. In order to train the PCAO controller, two morphologically different seafloors are used. During this training, the algorithm outperforms an unrealistic optimal-one-step-ahead search algorithm. To demonstrate the universality of the controller, the most effective controller is used to map three new morphologically different seafloors. During the latter mapping experiment, the PCAO algorithm outperforms several gradient-descent-like approaches.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
This research develops a new on-line trajectory planning algorithm for a team of Autonomous Underwater Vehicles (AUVs). The goal of the AUVs is to cooperatively explore and map the ocean seafloor. As the morphology of the seabed is unknown and complex, standard non-convex algorithms perform insufficiently. To tackle this, a new simulation-based approach is proposed and numerically evaluated. This approach adapts the Parametrized Cognitive-based Adaptive Optimization (PCAO) algorithm. The algorithm transforms the exploration problem to a parametrized decision-making mechanism whose real-time implementation is feasible. Upon that transformation, this scheme calculates off-line a set of decision making mechanism’s parameters that approximate the – non-practically feasible – optimal solution. The advantages of the algorithm are significant computational simplicity, scalability, and the fact that it can straightforwardly embed any type of physical constraints and system limitations. In order to train the PCAO controller, two morphologically different seafloors are used. During this training, the algorithm outperforms an unrealistic optimal-one-step-ahead search algorithm. To demonstrate the universality of the controller, the most effective controller is used to map three new morphologically different seafloors. During the latter mapping experiment, the PCAO algorithm outperforms several gradient-descent-like approaches.
9.
A. Ch. Kapoutsis; Ch. M. Malliou; S. A. Chatzichristofis; E. B. Kosmatopoulos
Continuously Informed Heuristic A* – Optimal Path Retrieval Inside an Unknown Environment Conference
15th IEEE International Symposium on Safety, Security, and Rescue Robotics 2017 (SSRR 2017), IEEE, 2017, ISBN: 978-1-5386-3923-8.
@conference{kapoutsis2017Continuously,
title = {Continuously Informed Heuristic A* – Optimal Path Retrieval Inside an Unknown Environment},
author = {A. Ch. Kapoutsis and Ch. M. Malliou and S. A. Chatzichristofis and E. B. Kosmatopoulos},
url = {https://ieeexplore.ieee.org/document/8088166
https://kapoutsis.info/wp-content/uploads/2017/10/ssrr2017Final.pdf
https://www.youtube.com/watch?v=ct_mnyqIjUU
https://kapoutsis.info/wp-content/uploads/2017/10/ssrr2017_nc_nv.pptx
https://github.com/athakapo/Continuously-Informed-Heuristic-A---Optimal-path-retrieval-inside-an-unknown-environment},
doi = {10.1109/SSRR.2017.8088166},
isbn = {978-1-5386-3923-8},
year = {2017},
date = {2017-10-30},
booktitle = {15th IEEE International Symposium on Safety, Security, and Rescue Robotics 2017 (SSRR 2017)},
publisher = {IEEE},
abstract = {This paper deals with the problem of retrieving the optimal path between two points inside an unknown environment, utilizing a robot-scouter. The vast majority of the path planning frameworks for an unknown environment focuses on the problem of navigating a robot, as soon as possible, towards a pre-specified location. As a result, the final followed path between the start and end location is not necessarily the optimal one, as the objective of the robot at each timestamp is to minimize its current distance to the desirable location. However, there are several real-life applications, like the one formulated in this paper, where the robot-scouter has to find the minimum path between two positions in an unknown environment, which is going to be used in a future phase. In principle, the optimal path can be guaranteed by a searching agent that adopts an A*-like decision mechanism. In this paper, we propose a specifically-tailored variation (CIA*) of the A* algorithm to the problem in hand. CIA* inherits the A* optimality and efficiency guarantees, while at the same time exploits the learnt formation of the obstacles, to on-line revise the heuristic evaluation of the candidate states. As reported in the simulation results, CIA* achieves an enhancement in the range of 20-50%, over the typical A*, on the cells that have to be visited to guarantee the optimal path construction. An open-source implementation of the proposed algorithm along with a Matlab GUI are available.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
This paper deals with the problem of retrieving the optimal path between two points inside an unknown environment, utilizing a robot-scouter. The vast majority of the path planning frameworks for an unknown environment focuses on the problem of navigating a robot, as soon as possible, towards a pre-specified location. As a result, the final followed path between the start and end location is not necessarily the optimal one, as the objective of the robot at each timestamp is to minimize its current distance to the desirable location. However, there are several real-life applications, like the one formulated in this paper, where the robot-scouter has to find the minimum path between two positions in an unknown environment, which is going to be used in a future phase. In principle, the optimal path can be guaranteed by a searching agent that adopts an A*-like decision mechanism. In this paper, we propose a specifically-tailored variation (CIA*) of the A* algorithm to the problem in hand. CIA* inherits the A* optimality and efficiency guarantees, while at the same time exploits the learnt formation of the obstacles, to on-line revise the heuristic evaluation of the candidate states. As reported in the simulation results, CIA* achieves an enhancement in the range of 20-50%, over the typical A*, on the cells that have to be visited to guarantee the optimal path construction. An open-source implementation of the proposed algorithm along with a Matlab GUI are available.
- https://ieeexplore.ieee.org/document/8088166
- https://kapoutsis.info/wp-content/uploads/2017/10/ssrr2017Final.pdf
- https://www.youtube.com/watch?v=ct_mnyqIjUU
- https://kapoutsis.info/wp-content/uploads/2017/10/ssrr2017_nc_nv.pptx
- https://github.com/athakapo/Continuously-Informed-Heuristic-A---Optimal-path-ret[...]
- doi:10.1109/SSRR.2017.8088166
8.
A. Ch. Kapoutsis; G. Salavasidis; S. A. Chatzichristofis; J. Braga; J. Pinto; J. B. Sousa; E. B. Kosmatopoulos
IFAC Workshop on Navigation, Guidance and Control of Underwater Vehicles (NGCUV’2015), vol. 48, no. 2, IFAC-PapersOnLine ELSEVIER, 2015, ISSN: 2405-8963.
@conference{kapoutsis2015noptilus,
title = {The NOPTILUS Project Overview: A Fully-Autonomous Navigation System of Teams of AUVs for Static/Dynamic Underwater Map Construction},
author = {A. Ch. Kapoutsis and G. Salavasidis and S. A. Chatzichristofis and J. Braga and J. Pinto and J. B. Sousa and E. B. Kosmatopoulos},
url = {https://www.sciencedirect.com/science/article/pii/S2405896315002773
http://chatzichristofis.info/files/papers/C37.pdf
https://kapoutsis.info/wp-content/uploads/2020/12/presentationNGCUV.pptx},
doi = {https://doi.org/10.1016/j.ifacol.2015.06.038},
issn = {2405-8963},
year = {2015},
date = {2015-09-02},
booktitle = {IFAC Workshop on Navigation, Guidance and Control of Underwater Vehicles (NGCUV’2015)},
volume = {48},
number = {2},
pages = {231-237},
publisher = {ELSEVIER},
series = {IFAC-PapersOnLine},
abstract = {Within the project NOPTILUS, a fully functional system/methodology had been developed that allows the cooperative, fully-autonomous navigation of teams of AUVs when deployed in Static or Dynamic Underwater Map Construction (SDUMC) or Dynamic Underwater Phenomena Tracking (DUPT) missions. The key ingredient of this fully functional system/methodology (called the NOPTILUS Planning, Assignment and Navigation Module - NOPTILUS PAN) is an optimal control algorithm - called Parametrized Cognitive Adaptive Optmization - (PCAO) - developed by one of the NOPTILUS partners (CERTH). PCAO is firstly tailored and modified so as to be applicable to the problem of autonomous navigation of teams of AUVs when deployed in SDUMC or DUPT missions. For this purpose, a nonlinear model is developed so as to capture the dynamics of the AUVs, their sensors and the underwater environment. More precisely, the original PCAO-based approach is revised so as to be able to efficiently handle information coming from the localization module, the underwater acoustic communication module, the situation understanding module as well as instructions from the operator. The information coming from these modules is handled by the NOPTILUS PAN module without the need to enter in tedious re-design tasks. Two real-life experiments (involving teams of AUVs deployed in static mapping or simultaneous static mapping and dynamic target taking) demonstrate the efficiency and practicability of the NOPTILUS PAN module.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Within the project NOPTILUS, a fully functional system/methodology had been developed that allows the cooperative, fully-autonomous navigation of teams of AUVs when deployed in Static or Dynamic Underwater Map Construction (SDUMC) or Dynamic Underwater Phenomena Tracking (DUPT) missions. The key ingredient of this fully functional system/methodology (called the NOPTILUS Planning, Assignment and Navigation Module - NOPTILUS PAN) is an optimal control algorithm - called Parametrized Cognitive Adaptive Optmization - (PCAO) - developed by one of the NOPTILUS partners (CERTH). PCAO is firstly tailored and modified so as to be applicable to the problem of autonomous navigation of teams of AUVs when deployed in SDUMC or DUPT missions. For this purpose, a nonlinear model is developed so as to capture the dynamics of the AUVs, their sensors and the underwater environment. More precisely, the original PCAO-based approach is revised so as to be able to efficiently handle information coming from the localization module, the underwater acoustic communication module, the situation understanding module as well as instructions from the operator. The information coming from these modules is handled by the NOPTILUS PAN module without the need to enter in tedious re-design tasks. Two real-life experiments (involving teams of AUVs deployed in static mapping or simultaneous static mapping and dynamic target taking) demonstrate the efficiency and practicability of the NOPTILUS PAN module.
7.
C. Iakovidou; N. Anagnostopoulos; A. Ch. Kapoutsis; Y. Boutalis; S. A. Chatzichristofis
12th International Workshop on Content-Based Multimedia Indexing (CBMI), IEEE, 2014, ISBN: 978-1-4799-3990-9.
@conference{iakovidou2014searching,
title = {Searching Images with Mpeg-7 (& Mpeg-7 Like) Powered Localized Descriptors: The Simple Answer to Effective Content Based Image Retrieval},
author = {C. Iakovidou and N. Anagnostopoulos and A. Ch. Kapoutsis and Y. Boutalis and S. A. Chatzichristofis},
url = {https://ieeexplore.ieee.org/abstract/document/6849821/
http://chatzichristofis.info/files/papers/C33.pdf
https://kapoutsis.info/wp-content/uploads/2021/06/presentation2-140620172353-phpapp02.pdf},
doi = {10.1109/CBMI.2014.6849821},
isbn = {978-1-4799-3990-9},
year = {2014},
date = {2014-07-10},
booktitle = {12th International Workshop on Content-Based Multimedia Indexing (CBMI)},
publisher = {IEEE},
abstract = {In this paper we propose and evaluate a new technique that localizes the description ability of the well established MPEG-7 and MPEG-7-like global descriptors. We employ the SURF detector to define salient image patches of blob-like textures and use the MPEG-7 Scalable Color (SC), Color Layout (CL) and Edge Histogram (EH) descriptors and the global MPEG-7-like Color and Edge Directivity Descriptor (CEDD), to produce the final local features' vectors. In order to test the new descriptors in the most straightforward fashion, we use the Bag-Of-Visual-Words framework for indexing and retrieval. The experimental results conducted on two different benchmark databases with varying codebook sizes, revealed an astonishing boost in the retrieval performance of the proposed descriptors compared both to their own performance (in their original form) and to other state-of-the-art methods of local and global descriptors. Open-source implementation of the proposed descriptors is available in c#, Java and MATLAB.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In this paper we propose and evaluate a new technique that localizes the description ability of the well established MPEG-7 and MPEG-7-like global descriptors. We employ the SURF detector to define salient image patches of blob-like textures and use the MPEG-7 Scalable Color (SC), Color Layout (CL) and Edge Histogram (EH) descriptors and the global MPEG-7-like Color and Edge Directivity Descriptor (CEDD), to produce the final local features' vectors. In order to test the new descriptors in the most straightforward fashion, we use the Bag-Of-Visual-Words framework for indexing and retrieval. The experimental results conducted on two different benchmark databases with varying codebook sizes, revealed an astonishing boost in the retrieval performance of the proposed descriptors compared both to their own performance (in their original form) and to other state-of-the-art methods of local and global descriptors. Open-source implementation of the proposed descriptors is available in c#, Java and MATLAB.
6.
A. Ch. Kapoutsis; S. A. Chatzichristofis; L. Doitsidis; J. Borges de Sousa; E. B. Kosmatopoulos
21st Mediterranean Conference on Control and Automation, IEEE, 2013, ISBN: 978-1-4799-0997-1.
@conference{kapoutsis2013autonomous,
title = {Autonomous Navigation of Teams of Unmanned Aerial or Underwater Vehicles for Exploration of Unknown Static & Dynamic Environments},
author = {A. Ch. Kapoutsis and S. A. Chatzichristofis and L. Doitsidis and J. Borges de Sousa and E. B. Kosmatopoulos},
url = {https://ieeexplore.ieee.org/document/6608870/
https://kapoutsis.info/wp-content/uploads/2016/01/med_2013.pdf},
doi = {10.1109/MED.2013.6608870},
isbn = {978-1-4799-0997-1},
year = {2013},
date = {2013-09-26},
booktitle = {21st Mediterranean Conference on Control and Automation},
publisher = {IEEE},
abstract = {In this paper, we present a new approach that is able to efficiently and fully-autonomously navigate a team of Unmanned Aerial or Underwater Vehicles (UAUV's) when deployed in exploration of unknown static and dynamic environments towards providing accurate static/dynamic maps of the environment. Additionally to achieving to efficiently and fully-autonomously navigate the UAUV team, the proposed approach possesses certain advantages such as its extremely computational simplicity and scalability, and the fact that it can very straightforwardly embed and type of physical or other constraints and limitations (e.g., obstacle avoidance, nonlinear sensor noise models, localization fading environments, etc).},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In this paper, we present a new approach that is able to efficiently and fully-autonomously navigate a team of Unmanned Aerial or Underwater Vehicles (UAUV's) when deployed in exploration of unknown static and dynamic environments towards providing accurate static/dynamic maps of the environment. Additionally to achieving to efficiently and fully-autonomously navigate the UAUV team, the proposed approach possesses certain advantages such as its extremely computational simplicity and scalability, and the fact that it can very straightforwardly embed and type of physical or other constraints and limitations (e.g., obstacle avoidance, nonlinear sensor noise models, localization fading environments, etc).
5.
S. A. Chatzichristofis; A. Ch. Kapoutsis; E. B. Kosmatopoulos; L. Doitsidis; D. Rovas; Joao Borges de Sousa
The NOPTILUS Project: Autonomous Multi-AUV Navigation for Exploration of Unknown Environments Conference
FAC Workshop on Navigation, Guidance and Control of Underwater Vehicles (NGCUV’2012), vol. 45, no. 5, Springer, 2012, ISBN: 978-3-902823-19-9.
@conference{chatzicristofis2012noptilus,
title = {The NOPTILUS Project: Autonomous Multi-AUV Navigation for Exploration of Unknown Environments},
author = {S. A. Chatzichristofis and A. Ch. Kapoutsis and E. B. Kosmatopoulos and L. Doitsidis and D. Rovas and Joao Borges de Sousa},
url = {https://www.sciencedirect.com/science/article/pii/S1474667016306310
https://kapoutsis.info/wp-content/uploads/2016/04/NGCUV2012.pdf},
doi = {https://doi.org/10.3182/20120410-3-PT-4028.00062},
isbn = {978-3-902823-19-9},
year = {2012},
date = {2012-04-10},
booktitle = {FAC Workshop on Navigation, Guidance and Control of Underwater Vehicles (NGCUV’2012)},
volume = {45},
number = {5},
pages = {373-380},
publisher = {Springer},
abstract = {Current multi-AUV systems are far from being capable of fully autonomously taking over real-life complex situation-awareness operations. As such operations require advanced reasoning and decision-making abilities, current designs have to heavily rely on human operators. The involvement of humans, however, is by no means a guarantee of performance; humans can easily be over-whelmed by the information overload, fatigue can act detrimentally to their performance, properly coordinating vehicles actions is hard, and continuous operation is all but impossible. Within the European funded project NOPTILUS we take the view that an effective fully-autonomous multi-AUV concept/system, is capable of overcoming these shortcomings, by replacing human-operated operations by a fully autonomous one. In this paper, we present a new approach that is able to efficiently and fully-autonomously navigate a team of AUVs when deployed in exploration of unknown static and dynamic environments towards providing accurate static/dynamic maps of the environment. Additionally to achieving to efficiently and fully-autonomously navigate the AUV team, the proposed approach possesses certain advantages such as its extremely computational simplicity and scalability, and the fact that it can very straightforwardly embed and type of physical or other constraints and limitations (e.g., obstacle avoidance, nonlinear sensor noise models, localization fading environments, etc).},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Current multi-AUV systems are far from being capable of fully autonomously taking over real-life complex situation-awareness operations. As such operations require advanced reasoning and decision-making abilities, current designs have to heavily rely on human operators. The involvement of humans, however, is by no means a guarantee of performance; humans can easily be over-whelmed by the information overload, fatigue can act detrimentally to their performance, properly coordinating vehicles actions is hard, and continuous operation is all but impossible. Within the European funded project NOPTILUS we take the view that an effective fully-autonomous multi-AUV concept/system, is capable of overcoming these shortcomings, by replacing human-operated operations by a fully autonomous one. In this paper, we present a new approach that is able to efficiently and fully-autonomously navigate a team of AUVs when deployed in exploration of unknown static and dynamic environments towards providing accurate static/dynamic maps of the environment. Additionally to achieving to efficiently and fully-autonomously navigate the AUV team, the proposed approach possesses certain advantages such as its extremely computational simplicity and scalability, and the fact that it can very straightforwardly embed and type of physical or other constraints and limitations (e.g., obstacle avoidance, nonlinear sensor noise models, localization fading environments, etc).
4.
L. T. Tsochatzidis; A. Ch. Kapoutsis; N. I. Dourvas; S. A. Chatzichristofis; Y. S. Boutalis; K. Zagoris
The Fifth International Conference on Advances in Computer-Human Interactions (ACHI 2012), 2012, ISBN: 978-1-61208-177-9.
@conference{tsokado2012,
title = {TSOKADO: An Image Search Engine Performing Recursive Query Recommendation Based on Visual Information},
author = {L. T. Tsochatzidis and A. Ch. Kapoutsis and N. I. Dourvas and S. A. Chatzichristofis and Y. S. Boutalis and K. Zagoris},
url = {http://www.thinkmind.org/index.php?view=article&articleid=achi_2012_4_50_20255
http://chatzichristofis.info/files/papers/C26.pdf},
isbn = {978-1-61208-177-9},
year = {2012},
date = {2012-01-30},
booktitle = {The Fifth International Conference on Advances in Computer-Human Interactions (ACHI 2012)},
journal = {The Fifth International Conference on Advances in Computer Human Interactions (ACHI 2012)},
abstract = {This paper tackles the problem of the user’s incapability to describe exactly the image that he seeks by introducing an innovative image search engine called TsoKaDo. Until now the traditional web image search was based only on the comparison between metadata of the webpage and the user’s textual description. In the method proposed, images from various search engines are classified based on visual content and new tags are proposed to the user. Recursively, the results get closer to the user’s desire. The aim of this paper is to present a new way of searching, especially in case with less query generality, giving greater weight in visual content rather than in metadata.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
This paper tackles the problem of the user’s incapability to describe exactly the image that he seeks by introducing an innovative image search engine called TsoKaDo. Until now the traditional web image search was based only on the comparison between metadata of the webpage and the user’s textual description. In the method proposed, images from various search engines are classified based on visual content and new tags are proposed to the user. Recursively, the results get closer to the user’s desire. The aim of this paper is to present a new way of searching, especially in case with less query generality, giving greater weight in visual content rather than in metadata.
Book Chapters
3.
G. Orfanidis; S. Apostolidis; G. Prountzos; M. Riga; A. Ch. Kapoutsis; K. Ioannidis; E. B. Kosmatopoulos; S. Vrochidis; I. Kompatsiaris
Border Surveillance Using Computer Vision-Enabled Robotic Swarms for Semantically Enriched Situational Awareness Book Chapter
In: Technology Development for Security Practitioners, pp. 243-258, Springer, 2021, ISBN: 978-3-030-69460-9.
@inbook{Orfanidis2021,
title = {Border Surveillance Using Computer Vision-Enabled Robotic Swarms for Semantically Enriched Situational Awareness},
author = {G. Orfanidis and S. Apostolidis and G. Prountzos and M. Riga and A. Ch. Kapoutsis and K. Ioannidis and E. B. Kosmatopoulos and S. Vrochidis and I. Kompatsiaris},
url = {https://link.springer.com/chapter/10.1007/978-3-030-69460-9_15
https://zenodo.org/record/3961453#.YNXZVHUzbJU},
doi = {10.1007/978-3-030-69460-9_15},
isbn = {978-3-030-69460-9},
year = {2021},
date = {2021-06-25},
urldate = {2021-06-25},
booktitle = {Technology Development for Security Practitioners},
pages = {243-258},
publisher = {Springer},
abstract = {Cross-border crime utilizes recent advanced systems to perform their illegal activities. Innovative sensory systems and specialized equipment are examples that were used for trafficking of human and of various illicit materials. The increasing challenges that border personnel must resolve require the usage of recent technological advances as well. Thus, the utilization of pioneer technologies seems imperative to precede technologically organized crime. Towards this objective, the introduction of unmanned vehicles (UxV) and the advances of relevant sub-systems have created a new solution to fight cross-border crime. Utilizing a combination of UxVs enriched with enhanced detection capabilities comprises an effective solution. The chapter will introduce and present the capability of an autonomous navigation system by exploiting swarm intelligence principles towards simplifying the overall operation. Computer vision advances and semantic enrichment of the acquired information are incorporated to deliver cutting-edge technologies. The described architecture and services can provide a complete solution for optimal border surveillance and increased situation awareness.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Cross-border crime utilizes recent advanced systems to perform their illegal activities. Innovative sensory systems and specialized equipment are examples that were used for trafficking of human and of various illicit materials. The increasing challenges that border personnel must resolve require the usage of recent technological advances as well. Thus, the utilization of pioneer technologies seems imperative to precede technologically organized crime. Towards this objective, the introduction of unmanned vehicles (UxV) and the advances of relevant sub-systems have created a new solution to fight cross-border crime. Utilizing a combination of UxVs enriched with enhanced detection capabilities comprises an effective solution. The chapter will introduce and present the capability of an autonomous navigation system by exploiting swarm intelligence principles towards simplifying the overall operation. Computer vision advances and semantic enrichment of the acquired information are incorporated to deliver cutting-edge technologies. The described architecture and services can provide a complete solution for optimal border surveillance and increased situation awareness.
2.
A. Ch. Kapoutsis; S. A. Chatzichristofis; G. Ch. Sirakoulis; L. Doitsidis; E. B. Kosmatopoulos
Employing Cellular Automata for Shaping Accurate Morphology Maps Using Scattered Data from Robotics’ Missions Book Chapter
In: Sirakoulis, G.; Aadamatzky, A. (Ed.): vol. 13, Chapter 10, pp. 229-246, Springer-Verlag, Robots and Lattice Automata, 2014, ISBN: 978-3-319-10924-4.
@inbook{kapoutsis2015employing,
title = {Employing Cellular Automata for Shaping Accurate Morphology Maps Using Scattered Data from Robotics’ Missions},
author = {A. Ch. Kapoutsis and S. A. Chatzichristofis and G. Ch. Sirakoulis and L. Doitsidis and E. B. Kosmatopoulos},
editor = {G. Sirakoulis and A. Aadamatzky},
url = {https://link.springer.com/chapter/10.1007%2F978-3-319-10924-4_10
https://kapoutsis.info/wp-content/uploads/2016/01/Final_Employing-Cellular-Automata-for-Shaping-Accurate-Morphology-Maps.pdf},
doi = {https://doi.org/10.1007/978-3-319-10924-4},
isbn = {978-3-319-10924-4},
year = {2014},
date = {2014-10-12},
volume = {13},
pages = {229-246},
publisher = {Springer-Verlag},
edition = {Robots and Lattice Automata},
chapter = {10},
series = {Emergence, Complexity and Computation},
abstract = {Accurate maps are essential in the case of robot teams, so that they can operate autonomously and accomplish their tasks efficiently. In this work we present an approach which allows the generation of detailed maps, suitable for robot navigation, from a mesh of sparse points using Cellular Automata and simple evolutions rules. The entire map area can be considered as a 2D Cellular Automaton (CA) where the value at each CA cell represents the height of the ground in the corresponding coordinates. The set of measurements form the original state of the CA. The CA rules are responsible for generating the intermediate heights among the real measurements. The proposed method can automatically adjust its rules, so as to encapture local morphological attributes, using a pre-processing procedure in the set of measurements. The main advantage of the proposed approach is the ability to maintain an accurately reconstruction even in cases where the number of measurements are significant reduced. Experiments have been conducted employing data collected from two totally different real-word environments. In the first case the proposed approach is applied, so as to build a detailed map of a large unknown underwater area in Oporto, Portugal. The second case concerns data collected by a team of aerial robots in real experiments in an area near Zurich, Switzerland and is also used for the evaluation of the approach. The data collected, in the two aforementioned cases, are extracted using different kind of sensors and robots, thus demonstrating the applicability of our approach in different kind of devices. The proposed method outperforms the performance of other well-known methods in literature thus enabling its application for real robot navigation.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Accurate maps are essential in the case of robot teams, so that they can operate autonomously and accomplish their tasks efficiently. In this work we present an approach which allows the generation of detailed maps, suitable for robot navigation, from a mesh of sparse points using Cellular Automata and simple evolutions rules. The entire map area can be considered as a 2D Cellular Automaton (CA) where the value at each CA cell represents the height of the ground in the corresponding coordinates. The set of measurements form the original state of the CA. The CA rules are responsible for generating the intermediate heights among the real measurements. The proposed method can automatically adjust its rules, so as to encapture local morphological attributes, using a pre-processing procedure in the set of measurements. The main advantage of the proposed approach is the ability to maintain an accurately reconstruction even in cases where the number of measurements are significant reduced. Experiments have been conducted employing data collected from two totally different real-word environments. In the first case the proposed approach is applied, so as to build a detailed map of a large unknown underwater area in Oporto, Portugal. The second case concerns data collected by a team of aerial robots in real experiments in an area near Zurich, Switzerland and is also used for the evaluation of the approach. The data collected, in the two aforementioned cases, are extracted using different kind of sensors and robots, thus demonstrating the applicability of our approach in different kind of devices. The proposed method outperforms the performance of other well-known methods in literature thus enabling its application for real robot navigation.
PhD Theses
1.
A. Ch. Kapoutsis
Democritus University of Thrace department of Electrical and Computer Engineering , 2017.
@phdthesis{kapoutsis2017towards,
title = {Towards a fully autonomous and cooperative deployment of multi-robot teams for exploration and coverage in unknown or partially known environments},
author = {A. Ch. Kapoutsis},
editor = {E. B. Kosmatopoulos and G. A. Rovithakis and S. I. Roumeliotis and A. Gasteratos and S. A. Chatzichristofis and M. G. Lagoudakis},
url = {https://www.didaktorika.gr/eadd/handle/10442/42416?locale=en
https://kapoutsis.info/wp-content/uploads/2019/03/PhD_main.pdf
https://kapoutsis.info/wp-content/uploads/2020/12/PhdPresentationFinal_ReducedSize.pptx
},
year = {2017},
date = {2017-12-17},
address = {Building A', Xanthi-Kimeria Campus, 67100, Xanthi},
school = {Democritus University of Thrace department of Electrical and Computer Engineering },
abstract = {In this thesis we deal with the problem of navigating a team of robots in both known and unknown environments, so as the mission’s objectives to be fulfilled. The structure of this thesis is divided into two main pillars. In the first pillar we deal with the problem of determining an optimal path involving all points of a given area of interest (offline), while avoiding sub-areas with specific characteristics (e.g. obstacles, no-fly zones, etc.). This problem, which is usually referred as multi-robot coverage path planning (mCPP), has been proven to be NP-hard. Currently, existing approaches produce polynomial algorithms that are able to only approximate the minimum covering time. In chapter 3, a novel methodology is proposed, capable of producing such optimal paths in approximately polynomial time. In the heart of the proposed approach lies the DARP algorithm, which divides the terrain into a number of equal areas each corresponding to a specific robot, in such a way to guarantee: complete coverage, non-backtracking solution, minimum coverage path, while at the same time does not need any preparatory stage. In the second pillar of this thesis, we design algorithms capable of navigating team of robots without any prior knowledge. More specifically, we deal with problems where the objectives of the multi-robot system can be transformed to the optimization of a specifically defined cost-function. Due to the unknown environment, unknown robots’ dynamics, sensor nonlinearities, etc., the analytic form of the cost-function is not available a priori. Therefore, standard gradient descent-like algorithms are not applicable to these problems. In chapter 4, we first show that optimal one-step-ahead exploration schemes that are based on a transformed optimization criterion can lead to highly efficient solutions to the multi-robot exploration. As, however, optimal one-step-ahead solutions to the transformed optimization criterion cannot be practically obtained using conventional optimization schemes, the second step in our approach is to combine the use of the transformed optimization criterion with the Cognitive Adaptive Optimization (CAO): CAO is a practicably feasible computational methodology which adaptively provides an accurate approximation of the optimal one-step-ahead solutions. This combination results in a multi-robot exploration scheme which is both practically implementable and provides with quite efficient solutions as it is shown both by theoretical analysis and, most importantly, by extensive simulation experiments and real-life underwater sea-floor mapping experiments in the Leixoes port, Portugal. Finally, in chapter 5, we propose a distributed algorithm applicable to a quite large class of practical multi-robot applications. In such multi-robot applications, the user-defined objectives of the mission can be casted as a general optimization problem, without explicit guidelines of the sub-tasks per different robot. A novel distributed methodology is proposed, based on the CAO algorithm (as proposed on the previous chapter) that carefully designs a cost-function for each operational robot, where the joined optimization of which can accomplish the overall team objectives. The latter can be achieved by online learning (on each robot), only the problem-specific characteristics that affect the accomplishment of the overall mission objectives. The overall, low-complexity algorithm, can straightforwardly incorporate any kind of operational constraint, is fault tolerant and can appropriately tackle time-varying cost-functions. A cornerstone of this approach is that it shares the same convergence characteristics as those of block coordinate descent algorithms. The proposed algorithm is evaluated in four heterogeneous simulation set-ups under multiple scenarios, against both general purpose (centralized) and specifically-tailored to the problem in hand, algorithms.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
In this thesis we deal with the problem of navigating a team of robots in both known and unknown environments, so as the mission’s objectives to be fulfilled. The structure of this thesis is divided into two main pillars. In the first pillar we deal with the problem of determining an optimal path involving all points of a given area of interest (offline), while avoiding sub-areas with specific characteristics (e.g. obstacles, no-fly zones, etc.). This problem, which is usually referred as multi-robot coverage path planning (mCPP), has been proven to be NP-hard. Currently, existing approaches produce polynomial algorithms that are able to only approximate the minimum covering time. In chapter 3, a novel methodology is proposed, capable of producing such optimal paths in approximately polynomial time. In the heart of the proposed approach lies the DARP algorithm, which divides the terrain into a number of equal areas each corresponding to a specific robot, in such a way to guarantee: complete coverage, non-backtracking solution, minimum coverage path, while at the same time does not need any preparatory stage. In the second pillar of this thesis, we design algorithms capable of navigating team of robots without any prior knowledge. More specifically, we deal with problems where the objectives of the multi-robot system can be transformed to the optimization of a specifically defined cost-function. Due to the unknown environment, unknown robots’ dynamics, sensor nonlinearities, etc., the analytic form of the cost-function is not available a priori. Therefore, standard gradient descent-like algorithms are not applicable to these problems. In chapter 4, we first show that optimal one-step-ahead exploration schemes that are based on a transformed optimization criterion can lead to highly efficient solutions to the multi-robot exploration. As, however, optimal one-step-ahead solutions to the transformed optimization criterion cannot be practically obtained using conventional optimization schemes, the second step in our approach is to combine the use of the transformed optimization criterion with the Cognitive Adaptive Optimization (CAO): CAO is a practicably feasible computational methodology which adaptively provides an accurate approximation of the optimal one-step-ahead solutions. This combination results in a multi-robot exploration scheme which is both practically implementable and provides with quite efficient solutions as it is shown both by theoretical analysis and, most importantly, by extensive simulation experiments and real-life underwater sea-floor mapping experiments in the Leixoes port, Portugal. Finally, in chapter 5, we propose a distributed algorithm applicable to a quite large class of practical multi-robot applications. In such multi-robot applications, the user-defined objectives of the mission can be casted as a general optimization problem, without explicit guidelines of the sub-tasks per different robot. A novel distributed methodology is proposed, based on the CAO algorithm (as proposed on the previous chapter) that carefully designs a cost-function for each operational robot, where the joined optimization of which can accomplish the overall team objectives. The latter can be achieved by online learning (on each robot), only the problem-specific characteristics that affect the accomplishment of the overall mission objectives. The overall, low-complexity algorithm, can straightforwardly incorporate any kind of operational constraint, is fault tolerant and can appropriately tackle time-varying cost-functions. A cornerstone of this approach is that it shares the same convergence characteristics as those of block coordinate descent algorithms. The proposed algorithm is evaluated in four heterogeneous simulation set-ups under multiple scenarios, against both general purpose (centralized) and specifically-tailored to the problem in hand, algorithms.
Notice for downloading material: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.