{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T09:27:06Z","timestamp":1759742826245,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20220818102415033,JSGG20201103093802006,KJZD20230923114222045"],"award-info":[{"award-number":["JCYJ20220818102415033,JSGG20201103093802006,KJZD20230923114222045"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61977019,U1813206"],"award-info":[{"award-number":["61977019,U1813206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128867","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8849-8855","source":"Crossref","is-referenced-by-count":1,"title":["Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation"],"prefix":"10.1109","author":[{"given":"Jianqi","family":"Gao","sequence":"first","affiliation":[{"name":"School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055"}]},{"given":"Xizheng","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University,Faculty of Robot Science and Engineering,Shenyang,China,110819"}]},{"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Inteligence Science and Engineering, Harbin Institute of Technology,Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics,Department of Guangdong,Shenzhen,China,518055"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2023.101343"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/JSEE.2023.000051"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-1323-3_27"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/CCC58697.2023.10240555"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12030081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3269533"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3118407"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22216-0_37"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR58858.2023.10406349"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3312237"},{"key":"ref12","article-title":"The pitfall of more powerful autoencoders in lidar-based navigation","author":"Gebauer","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CAC57257.2022.10055983"},{"key":"ref16","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Intell. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref18","first-page":"5055","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref19","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref21","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128867.pdf?arnumber=11128867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:32:05Z","timestamp":1756881125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128867","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}