{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:50:05Z","timestamp":1772301005729,"version":"3.50.1"},"reference-count":77,"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\/icra55743.2025.11128407","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13875-13882","source":"Crossref","is-referenced-by-count":3,"title":["Local Policies Enable Zero-Shot Long-Horizon Manipulation"],"prefix":"10.1109","author":[{"given":"Murtaza","family":"Dalal","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Min","family":"Liu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Walter","family":"Talbott","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Deepak","family":"Pathak","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Ruslan","family":"Salakhutdinov","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2303","author":"OpenAI","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","author":"Collaboration","year":"2023","journal-title":"Open x-embodiment: Robotic learning datasets and rt-x models"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref5","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref7","author":"Fu","year":"2024","journal-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref10","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Conference on Robot Learning","author":"Agarwal","year":"2023"},{"key":"ref11","author":"Zhuang","year":"2023","journal-title":"Robot parkour learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610200"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.039"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.064"},{"key":"ref16","author":"Jiang","year":"2024","journal-title":"Transic: Sim-to-real policy transfer by learning from online correction"},{"key":"ref17","author":"Akkaya","year":"2019","journal-title":"Solving rubik\u2019s cube with a robot hand"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160216"},{"key":"ref19","author":"Lum","year":"2024","journal-title":"Dextrah-g: Pixels-to-action dexterous arm-hand grasping with geometric fabrics"},{"key":"ref20","author":"Chen","year":"2022","journal-title":"Visual dexterity: In-hand dexterous manipulation from depth"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref23","article-title":"Factory: Fast contact for robotic assembly","volume-title":"Robotics: Science and Systems XVIII","author":"Narang","year":"2022"},{"key":"ref24","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref25","author":"Dalal","year":"2024","journal-title":"Neural mp: A generalist neural motion planner"},{"key":"ref26","author":"Center","year":"1984","journal-title":"Shakey the robot"},{"key":"ref27","volume-title":"Robot manipulators: mathematics, programming, and control: the computer control of robot manipulators","author":"Paul","year":"1981"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1115\/1.3426611"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81854-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795645"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1108\/ir.2001.28.3.266.1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196681"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4527.001.0001"},{"issue":"2","key":"ref34","volume-title":"Mechanical assemblies: their design, manufacture, and role in product development","volume":"1","author":"Whitney","year":"2004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913484072"},{"key":"ref36","author":"Ahn","year":"2022","journal-title":"Do as i can, not as i say: Grounding language in robotic affordances"},{"key":"ref37","author":"Huang","year":"2022","journal-title":"Inner monologue: Embodied reasoning through planning with language models"},{"key":"ref38","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning. PMLR","author":"Huang","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref41","author":"Huang","year":"2023","journal-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models"},{"key":"ref42","article-title":"Bootstrap your own skills: Learning to solve new tasks with large language model guidance","volume-title":"Conference on Robot Learning","author":"Zhang","year":"2023"},{"key":"ref43","author":"Liu","year":"2023","journal-title":"Llm+ p: Empowering large language models with optimal planning proficiency"},{"key":"ref44","article-title":"Plan-seq-learn: Language model guided rl for solving long horizon robotics tasks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dalal","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3410155"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref47","article-title":"Dexterous functional grasping","volume-title":"7th Annual Conference on Robot Learning","author":"Agarwal","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460528"},{"issue":"1","key":"ref49","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning","volume":"112","author":"Sutton","year":"1999","journal-title":"Artificial Intelligence"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01717"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00459"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref54","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross","year":"2011"},{"key":"ref55","author":"Hsu","year":"2022","journal-title":"Vision-based manipulators need to also see from their hands"},{"key":"ref56","author":"Dalal","year":"2023","journal-title":"Imitating task and motion planning with visuomotor transformers"},{"key":"ref57","author":"Mandlekar","year":"2021","journal-title":"What matters in learning from offline human demonstrations for robot manipulation"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.10"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref61","author":"Makoviychuk","year":"2021","journal-title":"Isaac gym: High performance gpu-based physics simulation for robot learning"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref65","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref67","author":"Zhu","year":"2020","journal-title":"robosuite: A modular simulation framework and benchmark for robot learning"},{"key":"ref68","author":"Yarats","year":"2021","journal-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning"},{"key":"ref69","first-page":"21847","article-title":"Accelerating robotic reinforcement learning via parameterized action primitives","volume":"34","author":"Dalal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref71","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.041","article-title":"Furniturebench: Reproducible real-world benchmark for long-horizon complex manipulation","volume-title":"Robotics: Science and Systems XIX","author":"Heo","year":"2023"},{"key":"ref72","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Advances in Neural Information Processing Systems","volume":"1","author":"Pomerleau","year":"1988"},{"key":"ref73","author":"Mandlekar","year":"2021","journal-title":"What matters in learning from offline human demonstrations for robot manipulation"},{"key":"ref74","author":"Kostrikov","year":"2021","journal-title":"Offline reinforcement learning with implicit q-learning"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8793698"},{"key":"ref76","author":"Mandlekar","year":"2020","journal-title":"Human-in-the-loop imitation learning using remote tele-operation"},{"key":"ref77","author":"Kim","year":"2024","journal-title":"Open-vla: An open-source vision-language-action model"}],"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\/11128407.pdf?arnumber=11128407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:11:54Z","timestamp":1756879914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128407","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}