{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:19:34Z","timestamp":1773926374304,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/lra.2022.3186635","type":"journal-article","created":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:29:36Z","timestamp":1656361776000},"page":"8299-8306","source":"Crossref","is-referenced-by-count":15,"title":["Generalizable Task Planning Through Representation Pretraining"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9453-8933","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"first","affiliation":[{"name":"Stanford Vision and Learning Lab., Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danfei","family":"Xu","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[{"name":"Stanford Vision and Learning Lab., Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"477","article-title":"Behavior: Benchmark for everyday household activities in virtual, interactive, and ecological environments","volume-title":"Proc. Conf. Robot Learn.","author":"Srivastava","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943079"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref5","first-page":"1930","article-title":"Logic-geometric programming: An optimization-based approach to combined task and motion planning","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Toussaint","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.044"},{"key":"ref7","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","author":"Mao","year":"2019"},{"key":"ref8","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":"ref9","first-page":"148","article-title":"SORNet: Spatial object-centric representations for sequential manipulation","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Yuan","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989109"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211004615"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811575"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref16","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner","year":"2019"},{"key":"ref17","article-title":"Model-based visual planning with self-supervised functional distances","author":"Tian","year":"2020"},{"key":"ref18","article-title":"Example-driven model-based reinforcement learning for solving long-horizon visuomotor tasks","author":"Wu","year":"2021"},{"key":"ref19","first-page":"6120","article-title":"Value prediction network","volume-title":"in Proc. Adv. Neural Inf. Process. Syst.","author":"Oh","year":"2017"},{"key":"ref20","article-title":"Learning to act by predicting the future","author":"Dosovitskiy","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560841"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560934"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref24","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. Conf. Robot Learn.","author":"Jang","year":"2022"},{"key":"ref25","first-page":"2021","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Proc. 5th Conf. Robot Learn. (CoRL)","author":"Shridhar"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.076"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196597"},{"key":"ref30","article-title":"Regression planning networks","author":"Xu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636037"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.072"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594313"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812057"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981440"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref37","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Zeng","year":"2020"},{"key":"ref38","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref39","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9750005\/09808141.pdf?arnumber=9808141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:13:22Z","timestamp":1706760802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9808141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3186635","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}