{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:23:38Z","timestamp":1767990218651,"version":"3.49.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0114600"],"award-info":[{"award-number":["2021ZD0114600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272170"],"award-info":[{"award-number":["62272170"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Trusted Industry Internet Software Collaborative Innovation Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tcad.2023.3260710","type":"journal-article","created":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T17:57:37Z","timestamp":1679507857000},"page":"3559-3570","source":"Crossref","is-referenced-by-count":8,"title":["Hierarchical Relational Graph Learning for Autonomous Multirobot Cooperative Navigation in Dynamic Environments"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7223-8849","authenticated-orcid":false,"given":"Ting","family":"Wang","sequence":"first","affiliation":[{"name":"MoE Engineering Research Center of Software\/Hardware Co-Design Technology and Application, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8479-6530","authenticated-orcid":false,"given":"Xiao","family":"Du","sequence":"additional","affiliation":[{"name":"MoE Engineering Research Center of Software\/Hardware Co-Design Technology and Application, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-0989","authenticated-orcid":false,"given":"Mingsong","family":"Chen","sequence":"additional","affiliation":[{"name":"MoE Engineering Research Center of Software\/Hardware Co-Design Technology and Application, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-4048","authenticated-orcid":false,"given":"Keqin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, State University of New York, New York, NY, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref35","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"ziebart","year":"2010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/M2VIP49856.2021.9665033"},{"key":"ref15","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Int Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref37","first-page":"1856","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"},{"key":"ref36","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref31","first-page":"671","article-title":"Learning decentralized controllers for robot swarms with graph neural networks","author":"tolstaya","year":"2019","journal-title":"Proc Annu Conf Robot Learn (CoRL)"},{"key":"ref30","first-page":"823","article-title":"Graph policy gradients for large scale robot control","author":"khan","year":"2020","journal-title":"Proc Annu Conf Robot Learn (CoRL)"},{"key":"ref11","first-page":"285","article-title":"Decentralized noncommunicating multiagent collision avoidance with deep reinforcement learning","author":"chen","year":"2017","journal-title":"Proc Int Conf Robot Autom (ICRA)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3072340"},{"key":"ref32","article-title":"Graph neural networks for decentralized multi-robot submodular action selection","author":"zhou","year":"2021","journal-title":"arXiv 2105 08601"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3089044"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857339"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197209"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682555"},{"key":"ref38","article-title":"Graph attention networks","author":"veli?kovi?","year":"2017","journal-title":"arXiv 1710 10903"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-016-9584-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref24","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref23","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","author":"jiang","year":"2018","journal-title":"Proc Int Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref25","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref41","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref22","first-page":"5567","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"scarselli","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972868"},{"key":"ref8","first-page":"3","article-title":"Reciprocal n-body collision avoidance","author":"van den berg","year":"2009","journal-title":"Proc Int Symp Robot Res (ISRR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2016.2633961"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2865229"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2017.7984200"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2329689"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/10288105\/10078380.pdf?arnumber=10078380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T19:00:47Z","timestamp":1699470047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10078380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":41,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2023.3260710","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}