{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:44:50Z","timestamp":1775666690610,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8461096","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"5113-5120","source":"Crossref","is-referenced-by-count":234,"title":["PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-Based Planning"],"prefix":"10.1109","author":[{"given":"Aleksandra","family":"Faust","sequence":"first","affiliation":[]},{"given":"Kenneth","family":"Oslund","sequence":"additional","affiliation":[]},{"given":"Oscar","family":"Ramirez","sequence":"additional","affiliation":[]},{"given":"Anthony","family":"Francis","sequence":"additional","affiliation":[]},{"given":"Lydia","family":"Tapia","sequence":"additional","affiliation":[]},{"given":"Marek","family":"Fiser","sequence":"additional","affiliation":[]},{"given":"James","family":"Davidson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"53","DOI":"10.4310\/CIS.2010.v10.n1.a4","article-title":"A motion planning approach to studying molecular motions","volume":"10","author":"tapia","year":"2010","journal-title":"Communications in Information and Systems"},{"key":"ref32","first-page":"3309","article-title":"A framework for planning motion in environments with moving obstacles","author":"rodr\u00edguez","year":"2007","journal-title":"Proc IEEE Int Conf Intel Rob Syst (IROS)"},{"key":"ref31","first-page":"674","article-title":"Path planning for a robot manipulator based on probabilistic roadmap and reinforcement learning","author":"park","year":"2008","journal-title":"International Journal of Control Automation and Systems"},{"key":"ref30","year":"2017","journal-title":"Parasol Lab Department of Computer Science and Engineering Texas A&M University"},{"key":"ref34","article-title":"Collective robot reinforcement learning with distributed asynchronous guided policy search","author":"yahya","year":"2016","journal-title":"CoRR abs\/1610 00673"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2014.7004690"},{"key":"ref11","article-title":"Reinforcement learning for balancing a flying inverted pendulum","author":"figueroa","year":"2014","journal-title":"Proc World Congress on Intell Control Automat"},{"key":"ref12","author":"gr\u00fcne","year":"2011","journal-title":"Nonlinear Model Predictive Control Theory and Algorithms Communications and Control Engineering"},{"key":"ref13","first-page":"16","article-title":"Motion planning for a sixlegged lunar robot","author":"hauser","year":"2006","journal-title":"The Seventh International Workshop on the Algorithmic Foundations of Robotics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/027836402320556421"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref19","first-page":"293","article-title":"Rapidly-exploring random trees: Progress and prospects","author":"lavalle","year":"2000","journal-title":"Algorithmic and Computational Robotics New Directions"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/1059712311419378"},{"key":"ref4","first-page":"246","author":"alterovitz","year":"2007","journal-title":"The stochastic motion roadmap A sampling framework for planning with markov motion uncertainty"},{"key":"ref27","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2012.07.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205617"},{"key":"ref5","year":"2017","journal-title":"Computer Science Department University of New Mexico"},{"key":"ref8","first-page":"3555","article-title":"Preference-balancing motion planning under stochastic disturbances","author":"faust","year":"2015","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref7","article-title":"Pearl: Preference appraisal reinforcement learning for motion planning","author":"faust","year":"0","journal-title":"Under submission"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913501564"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.009"},{"key":"ref1","author":"abel","year":"2016","journal-title":"Exploratory gradient boosting for reinforcement learning in complex domains"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref22","article-title":"Efficient motion-based task learning for a serial link manipulator","volume":"3","author":"malone","year":"2014","journal-title":"Transactions on Control and Mechanical Systems"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR abs\/1509 02971"},{"key":"ref24","first-page":"862","article-title":"Implementation of an embodied general reinforcement learner on a serial link manipulator","author":"malone","year":"2012","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696512"},{"key":"ref26","year":"2013","journal-title":"Multi-Agent Robotics Hybrid and Embedded Systems Laboratory Department of Computer and Electrical Engineering University of New Mexico"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v21i1.13484","article-title":"Sample-based planning for continuous action markov decision processes","author":"mansley","year":"2011","journal-title":"The International Conference on Automated Planning & Scheduling"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08461096.pdf?arnumber=8461096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T16:43:45Z","timestamp":1720629825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8461096","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}