{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T21:39:36Z","timestamp":1774647576006,"version":"3.50.1"},"reference-count":52,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"54","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1750489"],"award-info":[{"award-number":["IIS-1750489"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141712050"],"award-info":[{"award-number":["N000141712050"]}],"id":[{"id":"10.13039\/100000006","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":[],"crossmark-restriction":false},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2021,5,12]]},"abstract":"<jats:p>We plan for rope manipulation with an unreliable model by learning where to trust the model and how to recover when stuck.<\/jats:p>","DOI":"10.1126\/scirobotics.abd8170","type":"journal-article","created":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T19:11:03Z","timestamp":1621451463000},"source":"Crossref","is-referenced-by-count":49,"title":["Learning where to trust unreliable models in an unstructured world for deformable object manipulation"],"prefix":"10.1126","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8701-9809","authenticated-orcid":true,"given":"P.","family":"Mitrano","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2615-3473","authenticated-orcid":true,"given":"D.","family":"MConachie","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA."},{"name":"Toyota Research Institute, Cambridge, MA, USA."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9712-109X","authenticated-orcid":true,"given":"D.","family":"Berenson","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA."}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"A. Wang T. Kurutach K. Liu P. Abbeel A. Tamar Learning robotic manipulation through visual planning and acting in Robotics Science and Systems Freiburg im Breisgau Germany (2019).","DOI":"10.15607\/RSS.2019.XV.074"},{"key":"e_1_3_2_3_2","unstructured":"K. Chua R. Calandra R. McAllister S. Levine Deep reinforcement learning in a handful of trials using probabilistic dynamics models in Proceedings of the 32nd International Conference on Neural Information Processing Systems (2018)."},{"key":"e_1_3_2_4_2","unstructured":"B. Lakshminarayanan A. Pritzel C. Blundell Simple and scalable predictive uncertainty estimation using deep ensembles in Proceedings of the 31st International Conference on Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_5_2","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","volume":"84","author":"Kamthe S.","year":"2018","unstructured":"S. Kamthe, M. Deisenroth, Data-efficient reinforcement learning with probabilistic model predictive control. Int. Conf. Artif. Intell. Stat. 84, 1701\u20131710 (2018).","journal-title":"Int. Conf. Artif. Intell. Stat."},{"key":"e_1_3_2_6_2","unstructured":"Y. Wang S. Chaudhuri L. E. Kavraki Bounded policy synthesis for POMDPs with safe-reachability objectives in Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems Stockholm Sweden (2018)."},{"key":"e_1_3_2_7_2","first-page":"266","article-title":"Firm: Sampling-based feedback motion planning under motion uncertainty and imperfect measurements","volume":"33","author":"Agha-mohammadi A.-a.","year":"2013","unstructured":"A.-a. Agha-mohammadi, S. Chakravorty, N. M. Amato, Firm: Sampling-based feedback motion planning under motion uncertainty and imperfect measurements. Int. J. Robot. Res. 33, 266\u2013304 (2013).","journal-title":"Int. J. Robot. Res."},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"J. V. D. Berg P. Abbeel K. Goldberg Lqg-mp: Optimized path planning for robots with motion uncertainty and imperfect state information in Robotics Science and Systems June 2010.","DOI":"10.15607\/RSS.2010.VI.017"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"C. Finn S. Levine Deep visual foresight for planning robot motion in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA ) 29 May to 3 June 2017.","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"T. Koller F. Berkenkamp M. Turchetta J. Boedecker A. Krause Learning-based model predictive control for safe exploration and reinforcement learning in Robotics Science and Systems Workshop on Safe Autonomy (2019).","DOI":"10.1109\/CDC.2018.8619572"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"A. Nagabandi G. Kahn R. S. Fearing S. Levine Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning in International Conference on Robotics and Automation (2018).","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067354"},{"key":"e_1_3_2_13_2","unstructured":"J. Matas S. James A. J. Davison Sim-to-real reinforcement learning for deformable object manipulation in Conference on Robot Learning Z\u00fcrich Switzerland (2018)."},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"P. Sundaresan J. Grannen B. Thananjeyan A. Balakrishna M. Laskey K. Stone J. E. Gonzalez K. Goldberg Learning rope manipulation policies using dense object descriptors trained on synthetic depth data in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 31 May to 31 August 2020.","DOI":"10.1109\/ICRA40945.2020.9197121"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Y. Wu W. Yan T. Kurutach L. Pinto P. Abbeel Learning to manipulate deformable objects without demonstrations in Robotics Science and Systems (Robotics Science and Systems) (2020).","DOI":"10.15607\/RSS.2020.XVI.065"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"A. Nair D. Chen P. Agrawal P. Isola P. Abbeel J. Malik S. Levine Combining self-supervised learning and imitation for vision-based rope manipulation in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA ) 29 May to 3 June 2017 pp. 2146\u20132153.","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"e_1_3_2_17_2","unstructured":"M. Zhang S. Vikram L. Smith P. Abbeel M. J. Johnson S. Levine SOLAR: Deep structured representations for model-based reinforcement learning in International Conference on Machine Learning (2019)."},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"G. A. Bekey K. Y. Goldberg Neural Networks in Robotics (Springer 1993).","DOI":"10.1007\/978-1-4615-3180-7"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2901898"},{"key":"e_1_3_2_20_2","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume":"97","author":"Hafner D.","year":"2019","unstructured":"D. Hafner, T. Lillicrap, I. Fischer, R. Villegas, H. David, L. Honglak, D. James, Learning latent dynamics for planning from pixels. Int. Conf. Mach. Learn. 97, 2555\u20132565 (2019).","journal-title":"Int. Conf. Mach. Learn."},{"key":"e_1_3_2_21_2","first-page":"4732","article-title":"Universal planning networks","volume":"80","author":"Srinivas A.","year":"2018","unstructured":"A. Srinivas, A. Jabri, P. Abbeel, S. Levine, C. Finn, Universal planning networks. Int. Conf. Mach. Learn. 80, 4732\u20134741 (2018).","journal-title":"Int. Conf. Mach. Learn."},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"A. Vemula Y. Oza A. J.Bagnell M. Likhachev Planning and execution using inaccurate models with provable guarantees in Robotics Science and Systems (2020).","DOI":"10.15607\/RSS.2020.XVI.001"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"D. Navarro-Alarcon Y. Liu J.G. Romero P. Li Visually servoed deformation control by robot manipulators in Proceedings of IEEE International Conference on Robotics and Automation 6 to 10 May 2013.","DOI":"10.1109\/ICRA.2013.6631329"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"B. Jia Z. Hu J. Pan D. Manocha Manipulating highly deformable materials using a visual feedback dictionary in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 21 to 25 May 2018.","DOI":"10.1109\/ICRA.2018.8461264"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920918299"},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"J. Fu S. Levine P. Abbeel One-shot learning of manipulation skills with online dynamics adaptation and neural network priors in Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) 9 to 14 October 2016.","DOI":"10.1109\/IROS.2016.7759592"},{"key":"e_1_3_2_27_2","unstructured":"I. Clavera J. Rothfuss J. Schulman Y. Fujita T. Asfour P. Abbeel Model-based reinforcement learning via meta-policy optimization in Conference on Robot Learning (2018)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"K. Bousmalis A. Irpan P. Wohlhart Y. Bai M. Kelcey M. Kalakrishnan L. Downs J. Ibarz P. Pastor K. Konolige S. Levine V. Vanhoucke Using simulation and domain adaptation to improve efficiency of deep robotic grasping in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 21 to 25 May 2018.","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"X. B. Peng M. Andrychowicz W. Zaremba P. Abbeel Sim-to-real transfer of robotic control with dynamics randomization in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 21 to 25 May 2018.","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_2_31_2","unstructured":"OpenAI I. Akkaya M. Andrychowicz M. Chociej M. Litwin B. McGrew A. Petron A. Paino M. Plappert G. Powell R. Ribas J. Schneider N. Tezak J. Tworek P. Welinder L. Weng Q. Yuan W. Zaremba L. Zhang Solving rubik\u2019s cube with a robot hand. arXiv:1910.07113 (2019)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"e_1_3_2_33_2","unstructured":"J. G. Schneider Exploiting model uncertainty estimates for safe dynamic control learning in Proceedings of the 9th International Conference on Neural Information Processing Systems (MIT Press Cambridge MA 1996)."},{"key":"e_1_3_2_34_2","first-page":"162","article-title":"Curious ilqr: Resolving uncertainty in model-based RL","volume":"100","author":"Bechtle S.","year":"2019","unstructured":"S. Bechtle, Y. Lin, A. Rai, L. Righetti, F. Meier, Curious ilqr: Resolving uncertainty in model-based RL. Proc. Conf. Robot Learn. 100, 162\u2013171 (2019).","journal-title":"Proc. Conf. Robot Learn."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0951-8320(96)00077-4"},{"key":"e_1_3_2_37_2","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","volume":"48","author":"Gal Y.","year":"2016","unstructured":"Y. Gal, Z. Ghahramani, Dropout as a bayesian approximation: Representing model uncertainty in deep learning. Int. Conf. Mach. Learn. 48, 1050\u20131059 (2016).","journal-title":"Int. Conf. Mach. Learn."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972849"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972858"},{"key":"e_1_3_2_40_2","unstructured":"K. Zhou J. C. Doyle Essentials of Robust Control (Prentice Hall 1998) vol. 104."},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Y. Li J. Wu J. Zhu J. B. Tenenbaum A. Torralba R. Tedrake Propagation networks for model-based control under partial observation in Proceedings of the International Conference on Robotics and Automation 20 to 24 May 2019 pp. 1205\u20131211.","DOI":"10.1109\/ICRA.2019.8793509"},{"key":"e_1_3_2_42_2","first-page":"855","article-title":"Cross-entropy randomized motion planning","volume":"31","author":"Kobilarov M.","year":"2011","unstructured":"M. Kobilarov, Cross-entropy randomized motion planning. Rotob. Sci. Syst. 31, 855\u2013871 (2011).","journal-title":"Rotob. Sci. Syst."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","unstructured":"N. D. Ratliff A. J. Bagnell M. A. Zinkevich Maximum margin planning in Proceedings of the 23rd International Conference on Machine Learning Pittsburgh PA USA (2006).","DOI":"10.1145\/1143844.1143936"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205651"},{"key":"e_1_3_2_46_2","unstructured":"F. Berkenkamp M. Turchetta A. P. Schoellig A. Krause Safe model-based reinforcement learning with stability guarantees in Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS) 4 to 9 December 2017."},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"T. Koller F. Berkenkamp M. Turchetta A. Krause Learning-based model predictive control for safe exploration in Proceedings of the 2018 IEEE Conference on Decision and Control Miami FL USA (2018) pp. 6059\u20136066.","DOI":"10.1109\/CDC.2018.8619572"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","unstructured":"A. Nagabandi G. Yang T. Asmar R. Pandya G. Kahn S. Levine R. S. Fearing Learning image-conditioned dynamics models for control of under-actuated legged millirobots in Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems Madrid Spain (2017).","DOI":"10.1109\/IROS.2018.8594193"},{"key":"e_1_3_2_50_2","unstructured":"D. Mrowca C. Zhuang E. Wang N. Haber L. Fei-Fei J. B. Tenenbaum D. L. K. Yamins Flexible neural representation for physics prediction in Proceedings of the 32nd International Conference on Neural Information Processing Systems Montr\u00e9al Canada (2018)."},{"key":"e_1_3_2_51_2","unstructured":"N. Koenig A. Howard Design and use paradigms for gazebo an open-source multi-robot simulator in Proceedings of the 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems Sendai Japan (2004)."},{"key":"e_1_3_2_52_2","unstructured":"R. Smith Open Dynamics Engine (2005); www.ode.org\/."},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969931"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1126\/scirobotics.abd8170","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.abd8170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T11:54:38Z","timestamp":1705406078000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.abd8170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,12]]},"references-count":52,"journal-issue":{"issue":"54","published-print":{"date-parts":[[2021,5,12]]}},"alternative-id":["10.1126\/scirobotics.abd8170"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.abd8170","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,12]]},"article-number":"eabd8170"}}