{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:03:55Z","timestamp":1756771435512,"version":"3.44.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968483","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"7558-7565","source":"Crossref","is-referenced-by-count":18,"title":["Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints"],"prefix":"10.1109","author":[{"given":"Arbaaz","family":"Khan","sequence":"first","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayue","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brent","family":"Schlotfeldt","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah Y.","family":"Tang","sequence":"additional","affiliation":[{"name":"Nuro,Palo Alto,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osbert","family":"Bastani","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijay","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,GRASP Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017","journal-title":"arXiv preprint arXiv 1705 08926"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref13","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref14","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref15","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700706"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-19457-3_1","article-title":"Reciprocal n-body collision avoidance","author":"van den berg","year":"2011","journal-title":"Robotics Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_15"},{"key":"ref4","first-page":"1","article-title":"Efficient multi-robot motion planning for unlabeled discs in simple polygons","author":"adler","year":"2015","journal-title":"Algorithmic Foundations of Robotics XI"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2793890"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487740"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426233"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9424","article-title":"Scram: Scalable collision-avoiding role assignment with minimal-makespan for formational positioning","author":"macalpine","year":"2015","journal-title":"Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36279-8_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913515307"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"4634","DOI":"10.1109\/IROS.2015.7354037","article-title":"Multi-robot navigation in formation via sequential convex programming","author":"alonso-mora","year":"2015","journal-title":"Intelligent Robots and Systems (IROS) 2015 IEEE\/RSJ International Conference on"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9412-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/70.976023"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref22","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv preprint arXiv 1609 02907"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref24","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"arXiv preprint arXiv 1802 01561"},{"key":"ref23","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"arXiv preprint arXiv 1803 00933"},{"key":"ref26","article-title":"Scalable centralized deep multi-agent reinforcement learning via policy gradients","author":"khan","year":"2018","journal-title":"arXiv preprint arXiv 1805 08776"},{"key":"ref25","article-title":"RLlib: Abstractions for distributed reinforcement learning","author":"liang","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968483.pdf?arnumber=8968483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:22:13Z","timestamp":1756754533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968483","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}