{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T04:57:54Z","timestamp":1790657874531,"version":"4.1.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Autonomous ecological monitoring requires robotic systems capable of efficiently exploring large natural environments while minimizing redundant traversal under limited communication and partial environmental knowledge. Although reinforcement learning provides adaptive decision making for multi-robot exploration, sparse rewards often result in inefficient exploration and slow policy convergence. This paper investigates whether locality-preserving geometric priors can improve decentralized reinforcement learning for ecological monitoring. We incorporate Hilbert space-filling curve information through state augmentation, exploration biasing, and potential-based reward shaping while preserving the underlying reinforcement learning algorithms. The framework is implemented using Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) and evaluated in simulated multi-robot ecological survey environments using teams of 4\u201316 robots. Performance is evaluated using coverage ratio, redundancy, cumulative reward, convergence speed, and ablation studies. Policies are further validated through outdoor experiments using two Boston Dynamics Spot robots operating in an environment containing natural vegetation and terrain obstacles. Results demonstrate consistent improvements in exploration efficiency, survey coverage, redundancy reduction, and learning performance relative to conventional DQN and PPO, demonstrating the effectiveness of geometric priors for reinforcement learning-based autonomous ecological monitoring.<\/jats:p>","DOI":"10.3389\/frobt.2026.1934273","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T04:33:20Z","timestamp":1790656400000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Geometric priors for reinforcement learning-based multi-robot ecological monitoring"],"prefix":"10.3389","volume":"13","author":[{"given":"Tamil Selvan","family":"Gurunathan","sequence":"first","affiliation":[{"name":"Department of Information Systems, University of Maryland Baltimore County","place":["Baltimore, MD, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aryya","family":"Gangopadhyay","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Maryland Baltimore County","place":["Baltimore, MD, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5986","DOI":"10.1109\/TRO.2025.3549186","article-title":"LPAC: learnable perception-action-communication loops with applications to coverage control","volume":"41","author":"Agarwal","year":"2025","journal-title":"IEEE Trans. Robotics"},{"key":"B2","volume-title":"Multi-Agent Reinforcement Learning: Foundations and Modern Approaches","author":"Albrecht","year":"2024"},{"key":"B3","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"key":"B4","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/t-c.1971.223258","article-title":"Alternative algorithm for Hilbert\u2019s space-filling curve","author":"Butz","year":"1971","journal-title":"IEEE Trans. Comput. C-20"},{"key":"B5","first-page":"11406","article-title":"Reinforcement learning driven multi-robot exploration via explicit communication and density-based frontier search","author":"Calzolari","year":"2025"},{"key":"B6","article-title":"Learning to explore using active neural SLAM","author":"Chaplot","year":"2020"},{"key":"B7","first-page":"11392","article-title":"MARVEL: multi-agent reinforcement learning for constrained Field-of-View multi-robot exploration in large-scale environments","author":"Chiun","year":"2025"},{"key":"B8","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","article-title":"First return then explore","volume":"590","author":"Ecoffet","year":"2021","journal-title":"Nature"},{"key":"B9","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2018"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1258","DOI":"10.1016\/j.robot.2013.09.004","article-title":"A survey on coverage path planning for robotics","volume":"61","author":"Galceran","year":"2013","journal-title":"Robotics Aut. Syst."},{"key":"B11","first-page":"66","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"Gupta","year":"2017"},{"key":"B12","first-page":"5302","article-title":"Meta-reinforcement learning of structured exploration strategies","volume":"31","author":"Gupta","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"B14","first-page":"873","article-title":"Optimal coverage of a grid using pairwise cooperative Mobile robots","volume":"17","author":"Huang","year":"2001","journal-title":"IEEE Trans. Robotics Automation"},{"key":"B15","doi-asserted-by":"publisher","first-page":"60158","DOI":"10.1109\/ACCESS.2025.3556446","article-title":"A comprehensive survey on coverage path planning for Mobile robots in dynamic environments","volume":"13","author":"Jayalakshmi","year":"2025","journal-title":"IEEE Access"},{"key":"B16","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/s10846-016-0461-x","article-title":"DARP: divide areas algorithm for optimal multi-robot coverage path planning","volume":"86","author":"Kapoutsis","year":"2017","journal-title":"J. Intelligent and Robotic Syst."},{"key":"B17","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.procs.2025.03.023","article-title":"Reward shaping for improved learning in attacker-defender game","volume":"257","author":"Kliem","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"B18","first-page":"1431","article-title":"Complete, decomposition-free coverage path planning","author":"Kusnur","year":"2022"},{"key":"B19","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"B20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"B21","first-page":"2778","article-title":"Curiosity-driven exploration by self-supervised prediction","author":"Pathak","year":"2017"},{"key":"B22","first-page":"4295","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2018"},{"key":"B23","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv Preprint arXiv:1707.06347"},{"key":"B24","article-title":"CAP: a connectivity-aware hierarchical coverage path planning algorithm for unknown environments using coverage guidance graph","author":"Shen","year":""},{"key":"B25","article-title":"Multi-CAP: a multi-robot connectivity-aware hierarchical coverage path planning algorithm for unknown environments","author":"Shen","year":"","journal-title":"arXiv Preprint arXiv:2509.14941"},{"key":"B26","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1146\/annurev-control-030323-022510","article-title":"Deep reinforcement learning for robotics: a survey of real-world successes","volume":"8","author":"Tang","year":"2025","journal-title":"Annu. Rev. Control, Robotics, Aut. Syst."},{"key":"B27","article-title":"Heterogeneous multi-agent reinforcement learning for unknown environment mapping","author":"Wakilpoor","year":"2020"},{"key":"B28","article-title":"Online obstacle evasion with space-filling curves","author":"Wakode","year":"2023","journal-title":"arXiv Preprint arXiv:2308.02200"},{"key":"B29","article-title":"Unsupervised predictive memory in a goal-directed agent","author":"Wayne","year":"2018","journal-title":"arXiv Preprint arXiv:1803.10760"},{"key":"B30","first-page":"146","article-title":"A frontier-based approach for autonomous exploration","volume-title":"Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA \u201997)","author":"Yamauchi","year":"1997"},{"key":"B13","first-page":"3715","article-title":"Mobile robot exploration and map-building with continuous localization","volume-title":"Proceedings of the 1998 IEEE International Conference on Robotics and Automation","author":"Yamauchi","year":"1998"},{"key":"B31","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","author":"Yu","year":"2021"},{"key":"B32","first-page":"1084","article-title":"Asynchronous multi-agent reinforcement learning for efficient real-time multi-robot cooperative exploration","author":"Yu","year":"2023"},{"key":"B33","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1934273\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T04:33:45Z","timestamp":1790656425000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1934273\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":33,"alternative-id":["10.3389\/frobt.2026.1934273"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2026.1934273","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"article-number":"1934273"}}