{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:12:23Z","timestamp":1771611143834,"version":"3.50.1"},"reference-count":43,"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":"am","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":[{"name":"NSF","award":["2214177"],"award-info":[{"award-number":["2214177"]}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-22-1-0249"],"award-info":[{"award-number":["FA9550-22-1-0249"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ONR MURI","award":["N00014-22-1-2740"],"award-info":[{"award-number":["N00014-22-1-2740"]}]},{"name":"ONR MURI","award":["N00014-24-1-2603"],"award-info":[{"award-number":["N00014-24-1-2603"]}]},{"name":"ONR MURI","award":["W911NF-23-1-0034"],"award-info":[{"award-number":["W911NF-23-1-0034"]}]},{"DOI":"10.13039\/100019800","name":"Quest for Intelligence, Massachusetts Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019800","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Boston Dynamics Artificial Intelligence Institute"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3656799","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:03:37Z","timestamp":1769115817000},"page":"3366-3373","source":"Crossref","is-referenced-by-count":1,"title":["Open-World Task and Motion Planning via Vision-Language Model Generated Constraints"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9291-3728","authenticated-orcid":false,"given":"Nishanth","family":"Kumar","sequence":"first","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0227-1071","authenticated-orcid":false,"given":"William","family":"Shen","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2996-2188","authenticated-orcid":false,"given":"Fabio","family":"Ramos","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8657-2450","authenticated-orcid":false,"given":"Tom\u00e1s","family":"Lozano-P\u00e9rez","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6054-7145","authenticated-orcid":false,"given":"Leslie Pack","family":"Kaelbling","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6474-1276","authenticated-orcid":false,"given":"Caelan Reed","family":"Garrett","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4573","article-title":"ReKep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2024"},{"key":"ref2","first-page":"1362","article-title":"Trust the PRoC3S: Solving long-horizon robotics problems with LLMs and constraint satisfaction","volume-title":"Proc. Conf. Robot Learn.","author":"Curtis","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref4","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref5","article-title":"Look before you leap: Unveiling the power of GPT-4V in robotic vision-language planning","author":"Hu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref7","first-page":"639","article-title":"Combined task and motion planning through an extensible planner-independent interface layer","volume-title":"Proc. IEEE Int. Conf. Robot. Automat.","author":"Srivastava","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128705"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref11","article-title":"Bilevel planning for robots: An illustrated introduction","author":"Kumar","year":"2023"},{"key":"ref12","article-title":"Translating natural language to planning goals with large-language models","author":"Xie","year":"2023"},{"key":"ref13","first-page":"215","article-title":"From skills to symbols: Learning symbolic representations for abstract high-level planning","volume-title":"J. Artif. Intell. Res.","volume":"61","author":"Konidaris","year":"2018"},{"key":"ref14","first-page":"12120","article-title":"Predicate invention for bilevel planning","volume-title":"Proc. AAAI Conf. Artif. Intell","author":"Silver","year":"2023"},{"key":"ref15","article-title":"VisualPredicator: Learning abstract world models with neuro-symbolic predicates for robot planning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang","year":"2024"},{"key":"ref16","article-title":"Predicate invention from pixels via pretrained vision-language models","author":"Athalye"},{"key":"ref17","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref19","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2024"},{"key":"ref20","article-title":"GR00T N1: An open foundation model for generalist humanoid robots","year":"2025"},{"key":"ref21","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Ichter","year":"2023"},{"key":"ref22","article-title":"Grounded decoding: Guiding text generation with grounded models for embodied agents","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"36","author":"Huang","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref24","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802284"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160220"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801328"},{"key":"ref28","first-page":"4005","article-title":"RoboPoint: A vision-language model for spatial affordance prediction in robotics","volume-title":"Proc. Conf. Robot Learn.","author":"Yuan","year":"2024"},{"key":"ref29","first-page":"5326","article-title":"Manipulate-anything: Automating real-world robots using vision-language models","volume-title":"Proc. Conf. Robot Learn.","author":"Duan","year":"2024"},{"key":"ref30","article-title":"RePLan: Robotic replanning with perception and language models","author":"Skreta","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15125"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127555"},{"key":"ref35","article-title":"PDDL: The planning domain definition language","author":"McDermott","year":"1998"},{"key":"ref36","first-page":"5","article-title":"Planning as heuristic search: New results","volume-title":"Proc. Euro. Conf. Plan.","author":"Bonet","year":"1999"},{"key":"ref37","first-page":"253","article-title":"The FF planning system: Fast plan generation through heuristic search","volume-title":"J. Artif. Intell. Res.","volume":"14","author":"Hoffmann","year":"2001"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/10720246_11","article-title":"Exhibiting knowledge in planning problems to minimize state encoding length","volume-title":"Proc. Recent Adv. AI Plan.: 5th Eur. Conf. Plann.","author":"Edelkamp","year":"2000"},{"key":"ref39","article-title":"Sampling-based robot task and motion planning in the real world","author":"Garrett","year":"2021"},{"key":"ref40","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng","year":"2020"},{"key":"ref41","article-title":"LLM+P: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023"},{"key":"ref42","first-page":"2070","article-title":"Learning efficient abstract planning models that choose what to predict","volume-title":"Prod. Conf. Robot Learn.","author":"Kumar","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812057"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/11359420\/11361071-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11361071.pdf?arnumber=11361071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:56:34Z","timestamp":1770152194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11361071\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3656799","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}