{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:02Z","timestamp":1757608682258,"version":"3.44.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127719","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"7263-7269","source":"Crossref","is-referenced-by-count":0,"title":["RM-Planner: Integrating Reinforcement Learning with Whole-Body Model Predictive Control for Mobile Manipulation"],"prefix":"10.1109","author":[{"given":"Zixuan","family":"Zhuang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanyue","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Mechanical Engineering,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renming","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Lu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Mechanical Engineering,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561315"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s23156952"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9427-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2015.7419012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340782"},{"key":"ref9","first-page":"138","article-title":"Deep whole-body control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning","author":"Fu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801928"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/1729881420921672"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref17","first-page":"603","article-title":"Hrl4in: Hierarchical reinforcement learning for interactive navigation with mobile manipulators","volume-title":"Conference on Robot Learning","author":"Li","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref22","first-page":"133","article-title":"Aggressive deep driving: Combining convolutional neural networks and model predictive control","volume-title":"Conference on Robot Learning","author":"Drews","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980409"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340823"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3141602"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref27","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610271"},{"key":"ref29","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Advances in neural information processing systems","volume":"31","author":"Nachum","year":"2018"},{"key":"ref30","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Advances in neural information processing systems","volume":"29","author":"Kulkarni","year":"2016"},{"key":"ref31","article-title":"Learning and transfer of modulated locomotor controllers","author":"Heess","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-018-0139-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812280"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968251"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2582040"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2927938"},{"key":"ref41","article-title":"igibson 2.0: Objectcentric simulation for robot learning of everyday household tasks","author":"Li","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Joint 2d-3d semantic data for indoor scene understanding","author":"Armeni","year":"2017","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127719.pdf?arnumber=11127719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:16:36Z","timestamp":1756880196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127719","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}