\n \n \n
\n
\n\n \n \n Ghassemi, P.; and Chowdhury, S.\n\n\n \n \n \n \n \n Decentralized Informative Path Planning With Balanced Exploration-Exploitation for Swarm Robotic Search.\n \n \n \n \n\n\n \n\n\n\n In
Volume 1: 39th Computers and Information in Engineering Conference, pages V001T02A058, 8 2019. American Society of Mechanical Engineers\n
\n\n
\n\n
\n\n
\n\n \n \n Website\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{\n title = {Decentralized Informative Path Planning With Balanced Exploration-Exploitation for Swarm Robotic Search},\n type = {inproceedings},\n year = {2019},\n pages = {V001T02A058},\n websites = {https://doi.org/10.1115/DETC2019-97887,https://asmedigitalcollection.asme.org/IDETC-CIE/proceedings/IDETC-CIE2019/59179/Anaheim, California, USA/1069658},\n month = {8},\n publisher = {American Society of Mechanical Engineers},\n day = {18},\n city = {Anaheim, CA, USA},\n id = {595b1ccf-7204-3901-9fbc-ac4ca113a8d9},\n created = {2019-07-08T20:56:16.682Z},\n accessed = {2019-07-08},\n file_attached = {false},\n profile_id = {0bdc2b56-796f-3d8c-b59b-624a5fa689c3},\n last_modified = {2020-07-25T07:49:59.592Z},\n read = {true},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {ghassemi2019bswarm-detc},\n patent_owner = {Ghassemi, Payam},\n notes = {Identified as one of the strongest CIE 2019 papers; invited to submit to Journal of Computing and Information Science in Engineering.},\n private_publication = {false},\n abstract = {Swarm robotic search is concerned with searching targets in unknown environments (e.g., for search and rescue or hazard localization), using a large number of collaborating simple mobile robots. In such applications, decentralized swarm systems are touted for their task/coverage scalability, time efficiency, and fault tolerance. To guide the behavior of such swarm systems, two broad classes of approaches are available, namely nature-inspired swarm heuristics and multi-robotic search methods. However, simultaneously offering computationally-efficient scalability and fundamental insights into the exhibited behavior (instead of a black-box behavior model), remains challenging under either of these two class of approaches. In this paper, we develop an important extension of the batch Bayesian search method for application to embodied swarm systems, searching in a physical 2D space. Key contributions lie in: 1) designing an acquisition function that not only balances exploration and exploitation across the swarm, but also allows modeling knowledge extraction over trajectories; and 2) developing its distributed implementation to allow asynchronous task inference and path planning by the swarm robots. The resulting collective informative path planning approach is tested on target search case studies of varying complexity, where the target produces a spatially varying (measurable) signal. Significantly superior performance, in terms of mission completion efficiency, is observed compared to exhaustive search and random walk baselines, along with favorable performance scalability with increasing swarm size.},\n bibtype = {inproceedings},\n author = {Ghassemi, Payam and Chowdhury, Souma},\n doi = {10.1115/DETC2019-97887},\n booktitle = {Volume 1: 39th Computers and Information in Engineering Conference},\n keywords = {ADAMS,BSwarm,Swarm}\n}
\n
\n\n\n
\n Swarm robotic search is concerned with searching targets in unknown environments (e.g., for search and rescue or hazard localization), using a large number of collaborating simple mobile robots. In such applications, decentralized swarm systems are touted for their task/coverage scalability, time efficiency, and fault tolerance. To guide the behavior of such swarm systems, two broad classes of approaches are available, namely nature-inspired swarm heuristics and multi-robotic search methods. However, simultaneously offering computationally-efficient scalability and fundamental insights into the exhibited behavior (instead of a black-box behavior model), remains challenging under either of these two class of approaches. In this paper, we develop an important extension of the batch Bayesian search method for application to embodied swarm systems, searching in a physical 2D space. Key contributions lie in: 1) designing an acquisition function that not only balances exploration and exploitation across the swarm, but also allows modeling knowledge extraction over trajectories; and 2) developing its distributed implementation to allow asynchronous task inference and path planning by the swarm robots. The resulting collective informative path planning approach is tested on target search case studies of varying complexity, where the target produces a spatially varying (measurable) signal. Significantly superior performance, in terms of mission completion efficiency, is observed compared to exhaustive search and random walk baselines, along with favorable performance scalability with increasing swarm size.\n
\n\n\n
\n\n\n
\n
\n\n \n \n Ghassemi, P.; Lulekar, S., S.; and Chowdhury, S.\n\n\n \n \n \n \n \n Adaptive Model Refinement with Batch Bayesian Sampling for Optimization of Bio-inspired Flow Tailoring.\n \n \n \n \n\n\n \n\n\n\n In
AIAA Aviation 2019 Forum, 6 2019. American Institute of Aeronautics and Astronautics\n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n Website\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{\n title = {Adaptive Model Refinement with Batch Bayesian Sampling for Optimization of Bio-inspired Flow Tailoring},\n type = {inproceedings},\n year = {2019},\n websites = {https://arc.aiaa.org/doi/10.2514/6.2019-2983},\n month = {6},\n publisher = {American Institute of Aeronautics and Astronautics},\n day = {17},\n city = {Dallas, TX, USA},\n id = {f8e1829b-a456-33db-98eb-e0b2402024c0},\n created = {2019-07-08T20:56:27.362Z},\n accessed = {2019-07-08},\n file_attached = {true},\n profile_id = {0bdc2b56-796f-3d8c-b59b-624a5fa689c3},\n last_modified = {2020-07-10T06:28:06.192Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {ghassemi2019amrpbs},\n patent_owner = {Ghassemi, Payam},\n private_publication = {false},\n abstract = {This paper presents an advancement to an approach for model-independent surrogate-based optimization with adaptive batch sampling, known as Adaptive Model Refinement (AMR). While the original AMR method provides unique decisions with regards to "when" to sample and "how many" samples to add (to preserve the credibility of the optimization search process), it did not provide specific direction towards "where" to sample in the design variable space. This paper thus introduces the capability to identify optimum location to add new samples. The location of the infill points is decided by integrating a Gaussian Process-based criteria ("q-EI"), adopted from Bayesian optimization. The consideration of a penalization term to mitigate interaction among samples (in a batch) is crucial to effective integration of the q-EI criteria into AMR. The new AMR method, called AMR with Penalized Batch Bayesian Sampling (AMR-PBS) is tested on benchmark functions, demonstrating better performance compared to Bayesian EGO. In addition, it is successfully applied to design surface riblets for bio-inspired passive flow control (where high-fidelity samples are given by costly RANS CFD simulations), leading to a 10% drag reduction over the corresponding baseline (i.e., riblet-free aerodynamic surface).},\n bibtype = {inproceedings},\n author = {Ghassemi, Payam and Lulekar, Sumeet S. and Chowdhury, Souma},\n doi = {10.2514/6.2019-2983},\n booktitle = {AIAA Aviation 2019 Forum},\n keywords = {ADAMS,SBO}\n}
\n
\n\n\n
\n This paper presents an advancement to an approach for model-independent surrogate-based optimization with adaptive batch sampling, known as Adaptive Model Refinement (AMR). While the original AMR method provides unique decisions with regards to \"when\" to sample and \"how many\" samples to add (to preserve the credibility of the optimization search process), it did not provide specific direction towards \"where\" to sample in the design variable space. This paper thus introduces the capability to identify optimum location to add new samples. The location of the infill points is decided by integrating a Gaussian Process-based criteria (\"q-EI\"), adopted from Bayesian optimization. The consideration of a penalization term to mitigate interaction among samples (in a batch) is crucial to effective integration of the q-EI criteria into AMR. The new AMR method, called AMR with Penalized Batch Bayesian Sampling (AMR-PBS) is tested on benchmark functions, demonstrating better performance compared to Bayesian EGO. In addition, it is successfully applied to design surface riblets for bio-inspired passive flow control (where high-fidelity samples are given by costly RANS CFD simulations), leading to a 10% drag reduction over the corresponding baseline (i.e., riblet-free aerodynamic surface).\n
\n\n\n
\n\n\n
\n
\n\n \n \n Ghassemi, P.; and Chowdhury, S.\n\n\n \n \n \n \n \n Informative Path Planning with Local Penalization for Decentralized and Asynchronous Swarm Robotic Search.\n \n \n \n \n\n\n \n\n\n\n In
International Symposium on Multi-Robot and Multi-Agent Systems, MRS 2019, pages 188-194, 8 2019. Institute of Electrical and Electronics Engineers. (acceptance: 33%)\n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n Website\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{\n title = {Informative Path Planning with Local Penalization for Decentralized and Asynchronous Swarm Robotic Search},\n type = {inproceedings},\n year = {2019},\n keywords = {ADAMS,BSwarm,Conference,Swarm},\n pages = {188-194},\n websites = {http://arxiv.org/abs/1907.04396,https://ieeexplore.ieee.org/abstract/document/8901084/},\n month = {8},\n publisher = {Institute of Electrical and Electronics Engineers. (acceptance: 33%)},\n day = {22},\n city = {New Brunswick, NJ},\n id = {4d126477-38d4-3fc0-8451-18bd5bbcf53e},\n created = {2019-07-11T05:04:57.734Z},\n accessed = {2019-07-11},\n file_attached = {true},\n profile_id = {0bdc2b56-796f-3d8c-b59b-624a5fa689c3},\n last_modified = {2020-07-25T07:49:59.807Z},\n read = {true},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {ghassemi2019bswarm-mrs},\n patent_owner = {Ghassemi, Payam},\n notes = {(acceptance: 33%)},\n private_publication = {false},\n abstract = {Decentralized swarm robotic solutions to searching for targets that emit a spatially varying signal promise task parallelism, time efficiency, and fault tolerance. It is, however, challenging for swarm algorithms to offer scalability and efficiency, while preserving mathematical insights into the exhibited behavior. A new decentralized search method (called Bayes-Swarm), founded on batch Bayesian Optimization (BO) principles, is presented here to address these challenges. Unlike swarm heuristics approaches, Bayes-Swarm decouples the knowledge generation and task planning process, thus preserving insights into the emergent behavior. Key contributions lie in: 1) modeling knowledge extraction over trajectories, unlike in BO; 2) time-adaptively balancing exploration/exploitation and using an efficient local penalization approach to account for potential interactions among different robots' planned samples; and 3) presenting an asynchronous implementation of the algorithm. This algorithm is tested on case studies with bimodal and highly multimodal signal distributions. Up to 76 times better efficiency is demonstrated compared to an exhaustive search baseline. The benefits of exploitation/exploration balancing, asynchronous planning, and local penalization, and scalability with swarm size, are also demonstrated.},\n bibtype = {inproceedings},\n author = {Ghassemi, Payam and Chowdhury, Souma},\n doi = {10.1109/MRS.2019.8901084},\n booktitle = {International Symposium on Multi-Robot and Multi-Agent Systems, MRS 2019}\n}
\n
\n\n\n
\n Decentralized swarm robotic solutions to searching for targets that emit a spatially varying signal promise task parallelism, time efficiency, and fault tolerance. It is, however, challenging for swarm algorithms to offer scalability and efficiency, while preserving mathematical insights into the exhibited behavior. A new decentralized search method (called Bayes-Swarm), founded on batch Bayesian Optimization (BO) principles, is presented here to address these challenges. Unlike swarm heuristics approaches, Bayes-Swarm decouples the knowledge generation and task planning process, thus preserving insights into the emergent behavior. Key contributions lie in: 1) modeling knowledge extraction over trajectories, unlike in BO; 2) time-adaptively balancing exploration/exploitation and using an efficient local penalization approach to account for potential interactions among different robots' planned samples; and 3) presenting an asynchronous implementation of the algorithm. This algorithm is tested on case studies with bimodal and highly multimodal signal distributions. Up to 76 times better efficiency is demonstrated compared to an exhaustive search baseline. The benefits of exploitation/exploration balancing, asynchronous planning, and local penalization, and scalability with swarm size, are also demonstrated.\n
\n\n\n
\n\n\n
\n
\n\n \n \n Ghassemi, P.; DePauw, D.; and Chowdhury, S.\n\n\n \n \n \n \n \n Decentralized Dynamic Task Allocation in Swarm Robotic Systems for Disaster Response: Extended Abstract.\n \n \n \n \n\n\n \n\n\n\n In
2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), pages 83-85, 8 2019. IEEE\n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n Website\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{\n title = {Decentralized Dynamic Task Allocation in Swarm Robotic Systems for Disaster Response: Extended Abstract},\n type = {inproceedings},\n year = {2019},\n pages = {83-85},\n websites = {http://arxiv.org/abs/1907.04394,https://ieeexplore.ieee.org/document/8901062/},\n month = {8},\n publisher = {IEEE},\n day = {22},\n city = {New Brunswick, NJ},\n id = {3c46070e-f917-332e-adf0-6246955d7f09},\n created = {2019-07-11T05:04:57.748Z},\n accessed = {2019-07-11},\n file_attached = {true},\n profile_id = {0bdc2b56-796f-3d8c-b59b-624a5fa689c3},\n last_modified = {2020-07-25T07:49:59.774Z},\n read = {true},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {ghassemi2019decmrta},\n patent_owner = {Ghassemi, Payam},\n private_publication = {false},\n abstract = {Multiple robotic systems, working together, can provide important solutions to different real-world applications (e.g., disaster response), among which task allocation problems feature prominently. Very few existing decentralized multi-robotic task allocation (MRTA) methods simultaneously offer the following capabilities: consideration of task deadlines, consideration of robot range and task completion capacity limitations, and allowing asynchronous decision-making under dynamic task spaces. To provision these capabilities, this paper presents a computationally efficient algorithm that involves novel construction and matching of bipartite graphs. Its performance is tested on a multi-UAV flood response application.},\n bibtype = {inproceedings},\n author = {Ghassemi, Payam and DePauw, David and Chowdhury, Souma},\n doi = {10.1109/MRS.2019.8901062},\n booktitle = {2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS)},\n keywords = {ADAMS,Conference,MRTA,Swarm}\n}
\n
\n\n\n
\n Multiple robotic systems, working together, can provide important solutions to different real-world applications (e.g., disaster response), among which task allocation problems feature prominently. Very few existing decentralized multi-robotic task allocation (MRTA) methods simultaneously offer the following capabilities: consideration of task deadlines, consideration of robot range and task completion capacity limitations, and allowing asynchronous decision-making under dynamic task spaces. To provision these capabilities, this paper presents a computationally efficient algorithm that involves novel construction and matching of bipartite graphs. Its performance is tested on a multi-UAV flood response application.\n
\n\n\n
\n\n\n\n\n\n