{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:37:11Z","timestamp":1765546631562,"version":"3.28.0"},"reference-count":39,"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\/icra40945.2020.9196785","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"5299-5305","source":"Crossref","is-referenced-by-count":17,"title":["Learning Resilient Behaviors for Navigation Under Uncertainty"],"prefix":"10.1109","author":[{"given":"Tingxiang","family":"Fan","sequence":"first","affiliation":[]},{"given":"Pinxin","family":"Long","sequence":"additional","affiliation":[]},{"given":"Wenxi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Ruigang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref39"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"article-title":"Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning","year":"2018","author":"chen","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-008-0014-4"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"article-title":"Fully distributed multi-robot collision avoidance via deep reinforcement learning for safe and efficient navigation in complex scenarios","year":"2018","author":"fan","key":"ref34"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.17815\/CD.2016.1"},{"key":"ref12","article-title":"Uncertainty in deep learning","author":"gal","year":"2016","journal-title":"PhD diss Ph D thesis"},{"key":"ref13","first-page":"5574","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","author":"kendall","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917734298"},{"key":"ref15","article-title":"Learning to drive in a day","author":"kendall","year":"2018","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462978"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968307"},{"article-title":"A general frame-` work for uncertainty estimation in deep learning","year":"2019","author":"segu","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref28","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/100.580977","article-title":"The dynamic window approach to collision avoidance","volume":"4","author":"fox","year":"1997","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891491"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"article-title":"Uncertaintyaware reinforcement learning for collision avoidance","year":"2017","author":"kahn","key":"ref5"},{"key":"ref8","first-page":"1","article-title":"Sim-toreal transfer of robotic control with dynamics randomization","author":"peng","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"article-title":"End to end learning for self-driving cars","year":"2016","author":"bojarski","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1661412.1618468"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref20"},{"key":"ref22","volume":"118","author":"neal","year":"2012","journal-title":"Bayesian learning for neural networks"},{"key":"ref21","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref23","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","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\/09196785.pdf?arnumber=9196785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:23:24Z","timestamp":1656361404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196785","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}