{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:29:46Z","timestamp":1784644186427,"version":"3.55.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197209","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"448-454","source":"Crossref","is-referenced-by-count":57,"title":["Cooperative Multi-Robot Navigation in Dynamic Environment with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ruihua","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengduo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2010.06.019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2019.8816208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref16","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"christiano","year":"2016"},{"key":"ref17","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2016"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682555"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2013.6629610"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.876927"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915576234"},{"key":"ref5","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":"ref8","article-title":"Deep reinforcement learning for multi-agent systems: A review of challenges, solutions and applications","author":"nguyen","year":"2018"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10131","article-title":"Implicit coordination in crowded multi-agent navigation","author":"godoy","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2017.7984200"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"},{"key":"ref20","first-page":"1","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","author":"peng","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref22","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref24","article-title":"Extending the openai gym for robotics: a toolkit for reinforcement learning using ros and gazebo","author":"zamora","year":"2016"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197209.pdf?arnumber=9197209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T13:58:22Z","timestamp":1668779902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197209","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}