{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:55:30Z","timestamp":1730292930457,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"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":[[2022,12,5]]},"DOI":"10.1109\/robio55434.2022.10011798","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:51:38Z","timestamp":1674067898000},"page":"2003-2008","source":"Crossref","is-referenced-by-count":1,"title":["A Motion Planning and Control Method of Quadruped Robot Based on Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Weilong","family":"Liu","sequence":"first","affiliation":[{"name":"Qilu University of Technology (Shandong Academy of Sciences),School of Mathematics and Statistics,Jinan,Shandong,China,250353"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Qilu University of Technology (Shandong Academy of Sciences),School of Mathematics and Statistics,Jinan,Shandong,China,250353"}]},{"given":"Landong","family":"Hou","sequence":"additional","affiliation":[{"name":"Qilu University of Technology (Shan-dong Academy of Sciences),School of Electrical Engineering and Automation,Jinan,Shandong,China,250353"}]},{"given":"Shuhui","family":"Yang","sequence":"additional","affiliation":[{"name":"Qilu University of Technology (Shandong Academy of Sciences),School of Mathematics and Statistics,Jinan,Shandong,China,250353"}]},{"given":"Yiming","family":"Xu","sequence":"additional","affiliation":[{"name":"Qilu University of Technology (Shan-dong Academy of Sciences),School of Electrical Engineering and Automation,Jinan,Shandong,China,250353"}]},{"given":"Lixia","family":"Liu","sequence":"additional","affiliation":[{"name":"Qilu University of Technology (Shandong Academy of Sciences),School of Mathematics and Statistics,Jinan,Shandong,China,250353"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593885"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"journal-title":"Highly dynamic quadruped locomotion via whole-body impulse control and model predictive control","year":"2019","author":"Kim","key":"ref4"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref7","first-page":"10","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"80","author":"Fujimoto","year":"2018"},{"key":"ref8","first-page":"20","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proceedings of The 33rd International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"48","author":"Duan","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979660"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"journal-title":"Robust recovery controller for a quadrupedal robot using deep reinforcement learning","year":"2019","author":"Lee","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iros47612.2022.9982132"},{"journal-title":"Robust quadruped jumping via deep reinforcement learning","year":"2020","author":"Bellegarda","key":"ref18"},{"journal-title":"Efficient learning of control poli-cies for robust quadruped bounding using pretrained neural networks","year":"2020","author":"Li","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145495"},{"key":"ref21","first-page":"07","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"37","author":"Schulman"}],"event":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2022,12,5]]},"location":"Jinghong, China","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10011626\/10011636\/10011798.pdf?arnumber=10011798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T08:20:30Z","timestamp":1707466830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/robio55434.2022.10011798","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]}}}