{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T18:35:00Z","timestamp":1791830100464,"version":"4.3.4"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology Major","award":["2022ZD0116401"],"award-info":[{"award-number":["2022ZD0116401"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306023"],"award-info":[{"award-number":["62306023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484490"],"award-info":[{"award-number":["20240484490"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/lra.2024.3487491","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T17:35:34Z","timestamp":1730223334000},"page":"11138-11145","source":"Crossref","is-referenced-by-count":22,"title":["Safe and Efficient Multi-Agent Collision Avoidance With Physics-Informed Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6219-1741","authenticated-orcid":false,"given":"Pu","family":"Feng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4298-9358","authenticated-orcid":false,"given":"Rongye","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Size","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0350-9573","authenticated-orcid":false,"given":"Junkang","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7947-6743","authenticated-orcid":false,"given":"Simin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2998-8828","authenticated-orcid":false,"given":"Wenjun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajem.2017.09.025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08422-0_66"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2014.12.098"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITNG.2010.53"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2012.6283526"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_15"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341464"},{"key":"ref8","first-page":"2373","article-title":"Neural graph control barrier functions guided distributed collision-avoidance multi-agent control","volume-title":"Proc. Conf. Robot Learn.","author":"Zhang","year":"2023"},{"key":"ref9","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":"ref10","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref11","article-title":"Physics-informed multi-agent reinforcement learning for distributed multi-robot problems","author":"Sebastian","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981353"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3241337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011211"},{"key":"ref17","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"key":"ref18","first-page":"1008","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref19","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812259"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10409-021-01148-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3106259"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-022-01939-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111731"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref26","article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","author":"Terry","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(95)00026-S"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5772\/5618"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812221"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10726578\/10737374.pdf?arnumber=10737374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:38:59Z","timestamp":1734982739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10737374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":29,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3487491","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}