{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T14:26:46Z","timestamp":1772720806096,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636201","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"9057-9063","source":"Crossref","is-referenced-by-count":6,"title":["Risk Conditioned Neural Motion Planning"],"prefix":"10.1109","author":[{"given":"Xin","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashkan","family":"Jasour","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guy","family":"Rosman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Williams","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","author":"eysenbach","year":"2019","journal-title":"Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/moor.21.4.922"},{"key":"ref11","first-page":"1326","article-title":"Stationary deterministic policies for constrained mdps with multiple rewards, costs, and discount factors","author":"dolgov","year":"2005","journal-title":"IJCAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2514\/6.2010-8160"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619771"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1609\/icaps.v29i1.3479","article-title":"Online risk-bounded motion planning for autonomous vehicles in dynamic environments","volume":"29","author":"huang","year":"2019","journal-title":"Proceedings of the International Conference on Automated Planning and Scheduling"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561229"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/moor.25.1.130.15210"},{"key":"ref17","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref18","article-title":"Deep learning quadcopter control via risk-aware active learning","volume":"31","author":"andersson","year":"2017","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294259"},{"key":"ref4","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/2372560"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0237-4"},{"key":"ref27","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref6","article-title":"Rao*: An algorithm for chance-constrained pomdp’s","volume":"30","author":"santana","year":"2016","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI)"},{"key":"ref5","first-page":"1376","article-title":"An efficient motion planning algorithm for stochastic dynamic systems with constraints on probability of failure","author":"ono","year":"2008","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2011421"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref7","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref1","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017","journal-title":"Robotics Science and Systems"},{"key":"ref9","article-title":"Convergent policy optimization for safe reinforcement learning","author":"yu","year":"2019","journal-title":"Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","article-title":"Reachability-based trajectory safeguard (rts): A safe and fast reinforcement learning safety layer for continuous control","author":"shao","year":"2020"},{"key":"ref22","article-title":"Learning actionable representations with goal conditioned policies","author":"ghosh","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref21","article-title":"Learning multi-level hierarchies with hindsight","author":"levy","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref24","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":"ref23","article-title":"Planning with goal-conditioned policies","author":"nasiriany","year":"2019","journal-title":"Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.089"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.068"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636201.pdf?arnumber=9636201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:40:43Z","timestamp":1674081643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636201","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}