{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:38:42Z","timestamp":1780357122119,"version":"3.54.1"},"reference-count":33,"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\/icra55743.2025.11127975","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"4761-4767","source":"Crossref","is-referenced-by-count":13,"title":["Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V"],"prefix":"10.1109","author":[{"given":"Peiyuan","family":"Zhi","sequence":"first","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muzhi","family":"Han","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhitian","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyuan","family":"Jiao","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoxiong","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812057"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10133-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196681"},{"key":"ref9","article-title":"Doremi: Grounding language model by detecting and recovering from plan-execution misalignment","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.034"},{"key":"ref11","article-title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636554"},{"key":"ref14","article-title":"Open-vla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref16","article-title":"Ok-robot: What really matters in integrating open-knowledge models for robotics","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"3468","article-title":"Reflect: Summarizing robot experiences for failure explanation and correction","volume-title":"Conference on Robot Learning (CoRL)","author":"Liu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3471457"},{"key":"ref19","volume-title":"Gpt-4v(ision) system card","year":"2023"},{"key":"ref20","article-title":"Open-vocabulary mobile manipulation in unseen dynamic environments with 3d semantic maps","author":"Qiu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref22","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable task planning","author":"Rana","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref25","article-title":"Replan: Robotic replanning with perception and language models","author":"Skreta","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3477090"},{"key":"ref27","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Describe, explain, plan and select: interactive planning with llms enables open-world multi-task agents","author":"Wang","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v20i1.13436"},{"key":"ref30","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yao","year":"2022"},{"key":"ref31","article-title":"Homerobot: Open-vocabulary mobile manipulation","author":"Yenamandra","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"ref33","article-title":"Large language models for robotics: A survey","author":"Zeng","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11127975.pdf?arnumber=11127975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:06:32Z","timestamp":1756879592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127975","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}