{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T09:50:06Z","timestamp":1782294606377,"version":"3.54.5"},"reference-count":33,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T00:00:00Z","timestamp":1694044800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100000145","name":"Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-2132519"],"award-info":[{"award-number":["IIS-2132519"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000147","name":"Division of Civil, Mechanical and Manufacturing Innovation","doi-asserted-by":"publisher","award":["CMMI-2037101"],"award-info":[{"award-number":["CMMI-2037101"]}],"id":[{"id":"10.13039\/100000147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:p>This paper tackles the task of goal-conditioned dynamic manipulation of deformable objects. This task is highly challenging due to its complex dynamics (introduced by object deformation and high-speed action) and strict task requirements (defined by a precise goal specification). To address these challenges, we present Iterative Residual Policy (IRP), a general learning framework applicable to repeatable tasks with complex dynamics. IRP learns an implicit policy via delta dynamics\u2014instead of modeling the entire dynamical system and inferring actions from that model, IRP learns delta dynamics that predict the effects of delta action on the previously observed trajectory. When combined with adaptive action sampling, the system can quickly optimize its actions online to reach a specified goal. We demonstrate the effectiveness of IRP on two tasks: whipping a rope to hit a target point and swinging a cloth to reach a target pose. Despite being trained only in simulation on a fixed robot setup, IRP is able to efficiently generalize to noisy real-world dynamics, new objects with unseen physical properties, and even different robot hardware embodiments, demonstrating its excellent generalization capability relative to alternative approaches.<\/jats:p>","DOI":"10.1177\/02783649231201201","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T14:03:52Z","timestamp":1694095432000},"page":"389-404","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":16,"title":["Iterative residual policy: For goal-conditioned dynamic manipulation of deformable objects"],"prefix":"10.1177","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0319-0228","authenticated-orcid":false,"given":"Cheng","family":"Chi","sequence":"first","affiliation":[{"name":"Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7332-6712","authenticated-orcid":false,"given":"Benjamin","family":"Burchfiel","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5056-8046","authenticated-orcid":false,"given":"Eric","family":"Cousineau","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Feng","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuran","family":"Song","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2023,9,7]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6697007"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1636313"},{"key":"e_1_3_4_4_1","volume-title":"Model Predictive Control","author":"Camacho EF","year":"2013","unstructured":"Camacho EF, Alba CB (2013) Model Predictive Control. Springer science and business media. Available at: https:\/\/link.springer.com\/book\/10.1007\/978-1-4471-3398-8"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1080\/10671188.1960.10613109"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2808924"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139990"},{"key":"e_1_3_4_9_1","volume-title":"Conference on Robotic Learning","author":"Ha H","year":"2021","unstructured":"Ha H, Song S (2021) The unreasonable effectiveness of dynamic manipulation for cloth unfolding. Conference on Robotic Learning (CoRL)."},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","unstructured":"Hietala J Blanco-Mulero D Alcan G et al. (2021) Learning Visual Feedback Control for Dynamic Cloth Folding. In 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) pp.1455\u20131462. DOI: 10.1109\/IROS47612.2022.9981376","DOI":"10.1109\/IROS47612.2022.9981376"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.034"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196659"},{"key":"e_1_3_4_13_1","first-page":"10002","volume-title":"Trajectory optimization for manipulation of deformable objects: Assembly of belt drive units","author":"Jin S","year":"2021","unstructured":"Jin S, Romeres D, Ragunathan A, et al. (2021) Trajectory optimization for manipulation of deformable objects: Assembly of belt drive units. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 10002\u201310008: IEEE."},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793513"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354231"},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","unstructured":"Lim V Huang H Chen LY et al. (2021) Real2Sim2Real: Self-supervised learning of physical single-step dynamic actions for planar robot casting. In 2022 International Conference on Robotics and Automation (ICRA) pp. 8282\u20138289. DOI: 10.1109\/ICRA46639.2022.9811651","DOI":"10.1109\/ICRA46639.2022.9811651"},{"key":"e_1_3_4_17_1","volume-title":"ICLR","author":"Loshchilov I","year":"2019","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: ICLR."},{"key":"e_1_3_4_18_1","first-page":"152","article-title":"Dynamic manipulation","volume":"1","author":"Mason MT","year":"1993","unstructured":"Mason MT, Lynch K (1993) Dynamic manipulation. Proceedings of (IROS) IEEE\/RSJ International Conference on Intelligent Robots and Systems 1: 152\u2013159.","journal-title":"Proceedings of (IROS) IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920918299"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-1912-8"},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/BioRob49111.2020.9224399"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801939"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28872-7_20"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561391"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197121"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635837"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"e_1_3_4_30_1","article-title":"Learning 3D Dynamic Scene Representations for Robot Manipulation","author":"Xu Z","year":"2020","unstructured":"Xu Z, He Z, Wu J, et al. (2020) Learning 3D Dynamic Scene Representations for Robot Manipulation. Conference on Robot Learning (CoRL).","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979606"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ARSO.2015.7428219"},{"key":"e_1_3_4_33_1","doi-asserted-by":"crossref","unstructured":"Zeng A Song S Lee J et al. (2019) Tossingbot: learning to throw arbitrary objects with residual physics.","DOI":"10.15607\/RSS.2019.XV.004"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561630"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231201201","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649231201201","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231201201","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231201201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T09:40:59Z","timestamp":1782294059000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649231201201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,7]]},"references-count":33,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["10.1177\/02783649231201201"],"URL":"https:\/\/doi.org\/10.1177\/02783649231201201","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,7]]}}}