{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T01:00:18Z","timestamp":1775523618365,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"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":[[2021,12,27]]},"DOI":"10.1109\/robio54168.2021.9739251","type":"proceedings-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T21:20:39Z","timestamp":1648502439000},"page":"1520-1525","source":"Crossref","is-referenced-by-count":5,"title":["A Deep Safe Reinforcement Learning Approach for Mapless Navigation"],"prefix":"10.1109","author":[{"given":"Shaohua","family":"Lv","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Department of Control Science and Engineering,Shenzhen,China"}]},{"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Department of Control Science and Engineering,Shenzhen,China"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Department of Control Science and Engineering,Shenzhen,China"}]},{"given":"Jianqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Department of Control Science and Engineering,Shenzhen,China"}]},{"given":"Xizheng","family":"Pang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Department of Control Science and Engineering,Shenzhen,China"}]},{"given":"Meiling","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Department of Control Science and Engineering,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref10","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401181"},{"key":"ref14","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104175"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.103261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11645","article-title":"Teaching a machine to read maps with deep reinforcement learning","volume":"32","author":"brunner","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref27","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref6","article-title":"Curiosity-driven exploration for mapless navigation with deep reinforcement learning","author":"zhelo","year":"2018"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"A survey of simultaneous localization and mapping","author":"huang","year":"2019"},{"key":"ref8","article-title":"Plugo: a vlc systematic perspective of large-scale indoor localization","author":"liang","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2014.6932662"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3062457"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-007-9157-6"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref20","article-title":"Semi-parametric topological memory for navigation","author":"savinov","year":"2018"},{"key":"ref22","article-title":"Concrete problems in ai safety","author":"amodei","year":"2016"},{"key":"ref21","article-title":"Learning hierarchical relationships for object-goal navigation","author":"qiu","year":"2020"},{"key":"ref24","first-page":"8020","article-title":"Learning human objectives by evaluating hypothetical behavior","author":"reddy","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref23","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"ray","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9217023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"}],"event":{"name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Sanya, China","start":{"date-parts":[[2021,12,27]]},"end":{"date-parts":[[2021,12,31]]}},"container-title":["2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9739207\/9739208\/09739251.pdf?arnumber=9739251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T14:10:20Z","timestamp":1675087820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9739251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,27]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/robio54168.2021.9739251","relation":{},"subject":[],"published":{"date-parts":[[2021,12,27]]}}}