{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:50:06Z","timestamp":1773726606578,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2021ZD0114500"],"award-info":[{"award-number":["2021ZD0114500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160889","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"9544-9550","source":"Crossref","is-referenced-by-count":3,"title":["Failure-aware Policy Learning for Self-assessable Robotics Tasks"],"prefix":"10.1109","author":[{"given":"Kechun","family":"Xu","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Runjian","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Shuqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Zizhang","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Hongxiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Ci","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Rong","family":"Xiong","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811547"},{"key":"ref35","article-title":"Decoupled exploration and exploitation policies for sample-efficient reinforcement learning","author":"whitney","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2955321"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5955"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.065"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref30","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3522579"},{"key":"ref33","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Robotic self-assessment of competence","author":"burghouts","year":"2020","journal-title":"ACM\/IEEE International Conference on Human-Robot Interaction (HRI)"},{"key":"ref32","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593420"},{"key":"ref1","article-title":"Why generalization in rl is difficult: Epistemic pomdps and implicit partial observability","volume":"34","author":"ghosh","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.074"},{"key":"ref39","article-title":"Navigating among people in crowded environment: Datasets for localization and human robot interaction","author":"ram\u00f3n-vigo","year":"2014","journal-title":"Proceedings of the Workshop on Robots in Clutter Perception and Interaction in Clutter IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref16","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"ebert","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061339"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092640"},{"key":"ref18","article-title":"Safari: Safe and active robot imitation learning with imagination","author":"di palo","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref23","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"kahn","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2007.III.041"},{"key":"ref25","first-page":"1367","article-title":"Error-aware imitation learning from teleoperation data for mobile manipulation","author":"wong","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref20","first-page":"126","article-title":"Learning 3d dynamic scene representations for robot manipulation","author":"xu","year":"2021","journal-title":"Conference on Robot Learning"},{"key":"ref42","author":"xu","year":"2021","journal-title":"Paper with appendix"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9156-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967706"},{"key":"ref44","author":"wightman","year":"2019","journal-title":"pytorch-image-models"},{"key":"ref21","author":"richter","year":"2017","journal-title":"Safe visual navigation via deep learning and novelty detection"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"ref29","article-title":"Vime: Variational information maximizing exploration","volume":"29","author":"houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","article-title":"Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic","author":"chen","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294259"},{"key":"ref3","article-title":"Learning to be safe: Deep rl with a safety critic","author":"srinivasan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref5","article-title":"Safe deep q-network for autonomous vehicles at unsignalized intersection","author":"mokhtari","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref40","first-page":"1","article-title":"Rawseeds: Robotics advancement through web-publishing of sensorial and elaborated extensive data sets","author":"bonarini","year":"2006","journal-title":"Workshop on Benchmarks in Robotics Research at IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2006)"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160889.pdf?arnumber=10160889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:32:49Z","timestamp":1690219969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160889\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160889","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}