{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:34:53Z","timestamp":1730255693142,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8463209","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:28:03Z","timestamp":1537554483000},"page":"7541-7547","source":"Crossref","is-referenced-by-count":4,"title":["Improving Model-Based Balance Controllers Using Reinforcement Learning and Adaptive Sampling"],"prefix":"10.1109","author":[{"given":"Visak C.V.","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Sehoon","family":"Ha","sequence":"additional","affiliation":[]},{"given":"Katsu","family":"Yamane","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2012.6651514"},{"key":"ref11","first-page":"4145","article-title":"Compliant attitude control and stepping strategy for balance recovery with the humanoid COMAN","author":"perrin","year":"2013","journal-title":"IEEE International Conference on Intelligent Robots and Systems"},{"key":"ref12","first-page":"1989","article-title":"A feedback controller for biped humanoids that can counteract large perturbations during gait","volume":"2005","author":"komura","year":"2005","journal-title":"Proceedings - IEEE International Conference on Robotics and Automation"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1177\/0278364912452762","article-title":"Capturability-based analysis and control of legged locomotion, Part 2: Application to M2V2, a lower-body humanoid","volume":"31","author":"pratt","year":"2012","journal-title":"The International Journal of Robotics Research"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref14"},{"key":"ref15","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)"},{"journal-title":"LQR-Trees Feedback Motion Planning on Sparse Randomized Trees","year":"2009","author":"tedrake","key":"ref16"},{"key":"ref17","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"konidaris","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3009907"},{"key":"ref19","first-page":"2051","article-title":"A surrogate modeling and adaptive sampling toolbox for computer based design","volume":"11","author":"gorissen","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref28","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/3072959.3073602","article-title":"Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"peng","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref27","first-page":"1889","author":"schulman","year":"2015","journal-title":"Trust region policy optimization"},{"key":"ref3","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":"ref6","first-page":"3943","article-title":"Momentum-based reactive stepping controller on level and non-level ground for humanoid robot push recovery","author":"yun","year":"2011","journal-title":"IEEE International Conference on Intelligent Robots and Systems"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1145\/2897824.2925881","article-title":"Terrain-adaptive locomotion skills using deep reinforcement learning","volume":"35","author":"peng","year":"2016","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref8","first-page":"1549","article-title":"Integration of multi-level postural balancing on humanoid robots","author":"hyon","year":"2009","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"journal-title":"Push Recovery Control for Force-Controlled Humanoid Robots","year":"2011","author":"stephens","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321385"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1145\/1531326.1531386","article-title":"Momentum control for balance","volume":"28","author":"macchietto","year":"2009","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref1","article-title":"Integral control of humanoid balance","author":"stephens","year":"2007","journal-title":"IEEE International Conference on Intelligent Robots and Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"ref22","article-title":"An efficient spline-based rrt path planner for non-holonomic robots in cluttered environments","author":"yang","year":"2013","journal-title":"International Conference on Unmanned Aircraft Systems (ICUAS) IEEE"},{"key":"ref21","first-page":"3692","article-title":"Adaptive sampling for environmental field estimation using robotic sensors","author":"rahimi","year":"2005","journal-title":"Intelligent Robots and Systems 2005 (IROS 2005) 2005 IEEE\/RSJ International Conference On IEEE"},{"key":"ref24","article-title":"Active learning of inverse models with intrinsically motivated goal exploration in rodots","volume":"abs 1301 4862","author":"baranes","year":"2013","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778810"},{"journal-title":"A Python Binding of Dynamic Animation and Robotics Toolkit","year":"0","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630645"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2018,5,21]]},"location":"Brisbane, QLD","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\/08463209.pdf?arnumber=8463209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:28:43Z","timestamp":1598210923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8463209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8463209","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}