{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:16:49Z","timestamp":1775326609100,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Germany's Excellence Strategy","award":["GS01EXC-2070"],"award-info":[{"award-number":["GS01EXC-2070"]}]},{"name":"Germany's Excellence Strategy","award":["390732324"],"award-info":[{"award-number":["390732324"]}]},{"name":"5351:KI-FOR Automation and Artificial Intelligence for Monitoring and Decision Making in Horticultural Crops, AID4Cropsunder","award":["BE 4420\/4-1"],"award-info":[{"award-number":["BE 4420\/4-1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/lra.2025.3560830","type":"journal-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T17:41:23Z","timestamp":1744652483000},"page":"6256-6263","source":"Crossref","is-referenced-by-count":6,"title":["Safe Multi-Agent Reinforcement Learning for Behavior-Based Cooperative Navigation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8402-3530","authenticated-orcid":false,"given":"Murad","family":"Dawood","sequence":"first","affiliation":[{"name":"Humanoid Robots Lab, University of Bonn, Bonn, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1994-4266","authenticated-orcid":false,"given":"Sicong","family":"Pan","sequence":"additional","affiliation":[{"name":"Humanoid Robots Lab, University of Bonn, Bonn, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0109-5724","authenticated-orcid":false,"given":"Nils","family":"Dengler","sequence":"additional","affiliation":[{"name":"Humanoid Robots Lab, University of Bonn, Bonn, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7240-546X","authenticated-orcid":false,"given":"Siqi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munchen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4012-4668","authenticated-orcid":false,"given":"Angela P.","family":"Schoellig","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, Technical University of Munich, Munchen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4343-3028","authenticated-orcid":false,"given":"Maren","family":"Bennewitz","sequence":"additional","affiliation":[{"name":"Humanoid Robots Lab, University of Bonn, Bonn, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2932570"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160914"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2794879"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/205759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3301295"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812263"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"ref9","first-page":"823","article-title":"Graph policy gradients for large scale robot control","volume-title":"Proc. Conf. Robot Learn.","author":"Khan","year":"2019"},{"key":"ref10","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Rudin","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161216"},{"key":"ref13","article-title":"Safe deep reinforcement learning for multi-agent systems with continuous action spaces","author":"Sheebaelhamd","year":"2021"},{"key":"ref14","first-page":"483","article-title":"Safe multi-agent reinforcement learning via shielding","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Aly","year":"2021"},{"key":"ref15","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3171096"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3329232"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3324593"},{"key":"ref19","first-page":"576","article-title":"Decentralized control of quadrotor swarms with end-to-end deep reinforcement learning","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Batra","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610428"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812050"},{"key":"ref22","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app11020546"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2953326"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172168"},{"key":"ref26","article-title":"Safe multi-agent reinforcement learning through decentralized multiple control barrier functions","author":"Cai","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref28","article-title":"MAMPS: Safe multi-agent reinforcement learning via model predictive shielding","author":"Zhang","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811604"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068662"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812259"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref34","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref35","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Foerster","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049335"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383734"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161492"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-021-00208-8"},{"key":"ref41","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10969146\/10964685.pdf?arnumber=10964685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T06:52:18Z","timestamp":1747119138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10964685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":41,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3560830","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}