eprintid: 10193055 rev_number: 15 eprint_status: archive userid: 699 dir: disk0/10/19/30/55 datestamp: 2024-06-05 09:49:24 lastmod: 2024-11-25 13:15:02 status_changed: 2024-06-05 09:49:24 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Champagnie, Kale creators_name: Chen, Boli creators_name: Arvin, Farshad creators_name: Hu, Junyan title: Online Multi-Robot Coverage Path Planning in Dynamic Environments Through Pheromone-Based Reinforcement Learning ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F46 keywords: Computer aided software engineering, Automation, Neural networks, Reinforcement learning, Path planning, Entropy note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Two promising approaches to coverage path planning are reward-based and pheromone-based methods. Rewardbased methods allow heuristics to be learned automatically, often yielding a superior performance over hand-crafted rules. On the other hand, pheromone-based methods consistently demonstrate superior generalization and adaptation abilities when placed in unfamiliar environments. To obtain the best of both worlds, we introduce Greedy Entropy Maximization (GEM), a hybrid approach that aims to maximize the entropy of a pheromone deposited by a swarm of homogeneous antlike agents. We begin by establishing a sharp upper-bound on achievable entropy and show that this corresponds to optimal dynamic coverage path planning. Next, we demonstrate that GEM closely approaches this upper-bound despite depriving agents of basic necessities such as memory and explicit communication. Finally, we show that GEM can be executed asynchronously in constant-time, enabling it to scale arbitrarily. date: 2024-10-23 date_type: published publisher: Institute of Electrical and Electronics Engineers (IEEE) official_url: https://doi.org/10.1109/CASE59546.2024.10711550 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2282465 doi: 10.1109/CASE59546.2024.10711550 isbn_13: 979-8-3503-5851-3 lyricists_name: Chen, Boli lyricists_id: BCHEB76 actors_name: Chen, Boli actors_id: BCHEB76 actors_role: owner full_text_status: public pres_type: paper series: IEEE International Conference on Automation Science and Engineering (CASE) publication: 2024 IEEE 20th International Conference on Automation Science and Engineering volume: 20 place_of_pub: Bari, Italy pagerange: 1000-1005 event_title: 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) event_location: Bari, Italy event_dates: 28th August - 1st September 2024 issn: 2161-8089 book_title: Proceedings of the 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) citation: Champagnie, Kale; Chen, Boli; Arvin, Farshad; Hu, Junyan; (2024) Online Multi-Robot Coverage Path Planning in Dynamic Environments Through Pheromone-Based Reinforcement Learning. In: Proceedings of the 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE). (pp. pp. 1000-1005). Institute of Electrical and Electronics Engineers (IEEE): Bari, Italy. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10193055/1/Kale_GEM.pdf