{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:06:50Z","timestamp":1777129610064,"version":"3.51.4"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YFB1714700"],"award-info":[{"award-number":["2021YFB1714700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/lra.2025.3629984","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:54:49Z","timestamp":1762455289000},"page":"65-72","source":"Crossref","is-referenced-by-count":2,"title":["A Hierarchical Vision-Language and Reinforcement Learning Framework for Robotic Task and Motion Planning in Collaborative Manipulation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1042-5421","authenticated-orcid":false,"given":"Junnan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1055-9513","authenticated-orcid":false,"given":"Chaoxu","family":"Mu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6346-6930","authenticated-orcid":false,"given":"Lei","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref2","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn.","author":"Kim","year":"2024"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref4","first-page":"26311","article-title":"Do embodied agents dream of pixelated sheep: Embodied decision making using language guided world modelling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nottingham","year":"2023"},{"key":"ref5","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"key":"ref6","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref8","first-page":"6892","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. IEEE Int. Conf. Robot. Automat.","author":"ONeill","year":"2024"},{"key":"ref9","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2022"},{"key":"ref10","first-page":"1","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1129"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1705"},{"key":"ref14","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2022"},{"key":"ref15","first-page":"8469","article-title":"Palm-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref16","article-title":"Socratic models: Composing zeroshot multimodal reasoning with language","author":"Zeng","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-082619-100135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919890396"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3283497"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3262461"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3247160"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2023.3323798"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3228578"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295991"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611277"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300840"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11250609\/11230518.pdf?arnumber=11230518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T06:15:58Z","timestamp":1763446558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":28,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3629984","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}