{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T14:03:20Z","timestamp":1769090600485,"version":"3.49.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573159"],"award-info":[{"award-number":["62573159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics","award":["2023B1212010005"],"award-info":[{"award-number":["2023B1212010005"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20240903100802004"],"award-info":[{"award-number":["KJZD20240903100802004"]}]},{"name":"Shenzhen Science and Technology Program","award":["GXWD20231130153844002"],"award-info":[{"award-number":["GXWD20231130153844002"]}]},{"name":"Shenzhen Science and Technology Program","award":["SYSPG20241211173609005"],"award-info":[{"award-number":["SYSPG20241211173609005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3653406","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:51:39Z","timestamp":1768510299000},"page":"2538-2545","source":"Crossref","is-referenced-by-count":0,"title":["Gentle Manipulation of Long-Horizon Tasks Without Human Demonstrations"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3308-2911","authenticated-orcid":false,"given":"Jiayu","family":"Zhou","sequence":"first","affiliation":[{"name":"Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments, Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligent Science and Engineering, College of Artificial Intelligence, Harbin Institute of Technology Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8630-3331","authenticated-orcid":false,"given":"Qiwei","family":"Wu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments, Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligent Science and Engineering, College of Artificial Intelligence, Harbin Institute of Technology Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6668-1945","authenticated-orcid":false,"given":"Xuanbao","family":"Qin","sequence":"additional","affiliation":[{"name":"Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments, Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligent Science and Engineering, College of Artificial Intelligence, Harbin Institute of Technology Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8203-7795","authenticated-orcid":false,"given":"Yunjiang","family":"Lou","sequence":"additional","affiliation":[{"name":"Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments, Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligent Science and Engineering, College of Artificial Intelligence, Harbin Institute of Technology Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6469-5281","authenticated-orcid":false,"given":"Xiaogang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments, Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, School of Intelligent Science and Engineering, College of Artificial Intelligence, Harbin Institute of Technology Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0792-8974","authenticated-orcid":false,"given":"Renjing","family":"Xu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2025.3642671"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adl0628"},{"key":"ref3","first-page":"1","article-title":"3D-ViTac: Learning fine-grained manipulation with visuo-tactile sensing","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2024"},{"key":"ref4","first-page":"1596","article-title":"Visuotactile affordances for cloth manipulation with local control","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Sunil","year":"2023"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref6","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295236"},{"key":"ref8","first-page":"1645","article-title":"Tactile sim-to-real policy transfer via real-to-sim image translation","volume-title":"Proc. Conf. Robot Learn.","author":"Church","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref10","article-title":"On bringing robots home","author":"Shafiullah","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref12","first-page":"4066","article-title":"Mobile ALOHA: Learning bimanual mobile manipulation using low-cost whole-body teleoperation","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Fu","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref14","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ross","year":"2010"},{"key":"ref15","first-page":"1","article-title":"Plan-SEQ-learn: Language model guided RL for solving long horizon robotics tasks","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Dalal","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1115\/1.4035373"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2006.340202"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/70.258051"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202149"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CASE56687.2023.10260563"},{"key":"ref21","first-page":"1910","article-title":"Aloha unleashed: A simple recipe for robot dexterity","volume-title":"Proc. Conf. Robot Learn.","author":"Zhao","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.157"},{"key":"ref25","article-title":"SkillMimicGen: Automated demonstration generation for efficient skill learning and deployment","volume-title":"Proc. Conf. Robot Learn.","author":"Garrett","year":"2024"},{"key":"ref26","first-page":"1820","article-title":"MimicGen: A data generation system for scalable robot learning using human demonstrations","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Mandlekar","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127809"},{"key":"ref28","article-title":"Gentle manipulation policy learning via demonstrations from VLM planned atomic skills","author":"Zhou","year":"2025"},{"key":"ref29","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref30","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Representation Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref31","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146945"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3547267"},{"key":"ref34","article-title":"RobotWin 2.0: A scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation","author":"Chen","year":"2025"},{"key":"ref35","first-page":"44776","article-title":"Libero: Benchmarking knowledge transfer for lifelong robot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref36","first-page":"22955","article-title":"Behavior transformers: Cloning k modes with one stone","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Shafiullah","year":"2022"},{"key":"ref37","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Mandlekar","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11352805.pdf?arnumber=11352805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:12:04Z","timestamp":1769029924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11352805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":38,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3653406","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}