{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T03:19:40Z","timestamp":1792552780010,"version":"4.5.0"},"reference-count":56,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"84","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2023,11,22]]},"abstract":"<jats:p>In-hand object reorientation is necessary for performing many dexterous manipulation tasks, such as tool use in less structured environments, which remain beyond the reach of current robots. Prior works built reorientation systems assuming one or many of the following conditions: reorienting only specific objects with simple shapes, limited range of reorientation, slow or quasi-static manipulation, simulation-only results, the need for specialized and costly sensor suites, and other constraints that make the system infeasible for real-world deployment. We present a general object reorientation controller that does not make these assumptions. It uses readings from a single commodity depth camera to dynamically reorient complex and new object shapes by any rotation in real time, with the median reorientation time being close to 7 seconds. The controller was trained using reinforcement learning in simulation and evaluated in the real world on new object shapes not used for training, including the most challenging scenario of reorienting objects held in the air by a downward-facing hand that must counteract gravity during reorientation. Our hardware platform only used open-source components that cost less than 5000 dollars. Although we demonstrate the ability to overcome assumptions in prior work, there is ample scope for improving absolute performance. For instance, the challenging duck-shaped object not used for training was dropped in 56% of the trials. When it was not dropped, our controller reoriented the object within 0.4 radians (23\u00b0) 75% of the time.<\/jats:p>","DOI":"10.1126\/scirobotics.adc9244","type":"journal-article","created":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T18:58:25Z","timestamp":1700679505000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":102,"title":["Visual dexterity: In-hand reorientation of novel and complex object shapes"],"prefix":"10.1126","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0190-3853","authenticated-orcid":true,"given":"Tao","family":"Chen","sequence":"first","affiliation":[{"name":"Improbable AI Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA."},{"name":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology, Cambridge, MA 02139, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Megha","family":"Tippur","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology, Cambridge, MA 02139, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1757-8197","authenticated-orcid":true,"given":"Siyang","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing 100084, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8479-7237","authenticated-orcid":true,"given":"Vikash","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta AI, Pittsburgh, PA 15213, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edward","family":"Adelson","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology, Cambridge, MA 02139, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8463-9917","authenticated-orcid":true,"given":"Pulkit","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Improbable AI Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA."},{"name":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology, Cambridge, MA 02139, USA."},{"name":"Institute of Artificial Intelligence and Advanced Interactions (IAIFI), Massachusetts Institute of Technology, Cambridge, MA 02139, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"M.\u00a0T.\u00a0Mason J.\u00a0K.\u00a0Salisbury J.\u00a0K.\u00a0Parker Robot Hands and the Mechanics of Manipulation (MIT Press 1989).","DOI":"10.1115\/1.3153010"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1177\/027836498200100102"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066268"},{"key":"e_1_3_2_5_2","unstructured":"I. Mordatch Z.\u00a0Popovi\u0107 E.\u00a0Todorov Contact-invariant optimization for hand manipulation in Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation (ACM 2012) pp.\u00a0137\u2013144."},{"key":"e_1_3_2_6_2","first-page":"1560","article-title":"Dexterous manipulation using both palm and fingers","volume":"39","author":"Bai Y.","year":"2014","unstructured":"Y.\u00a0Bai, C. K.\u00a0Liu, Dexterous manipulation using both palm and fingers. IEEE Int. Conf. Robot. 39, 1560\u20131565 (2014).","journal-title":"IEEE Int. Conf. Robot."},{"key":"e_1_3_2_7_2","first-page":"6808","article-title":"Real-time behaviour synthesis for dynamic hand-manipulation","author":"Kumar V.","year":"2014","unstructured":"V.\u00a0Kumar, Y.\u00a0Tassa, T.\u00a0Erez, E.\u00a0Todorov, Real-time behaviour synthesis for dynamic hand-manipulation. IEEE Int. Conf. Robot., 6808\u20136815 (2014).","journal-title":"IEEE Int. Conf. Robot."},{"key":"e_1_3_2_8_2","first-page":"297","article-title":"A system for general in-hand object reorientation","volume":"164","author":"Chen T.","year":"2022","unstructured":"T.\u00a0Chen, J.\u00a0Xu, P.\u00a0Agrawal, A system for general in-hand object reorientation. Conf. Robot Learning 164, 297\u2013307 (2022).","journal-title":"Conf. Robot Learning"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"e_1_3_2_10_2","unstructured":"Open AI I.\u00a0Akkaya M.\u00a0Andrychowicz M.\u00a0Chociej M.\u00a0Litwin B.\u00a0M.\u00a0Grew A.\u00a0Petron A.\u00a0Paino M.\u00a0Plappert G.\u00a0Powell R.\u00a0Ribas J.\u00a0Schneider N.\u00a0Tezak J.\u00a0Tworek P.\u00a0Welinder L.\u00a0Weng Q.\u00a0Yuan W.\u00a0Zaremba L.\u00a0Zhang Solving rubik\u2019s cube with a robot hand. arXiv:1910.07113 [cs.LG] (16 October 2019)."},{"key":"e_1_3_2_11_2","unstructured":"A. Nagabandi K.\u00a0Konolige S.\u00a0Levine V.\u00a0Kumar Deep dynamics models for learning dexterous manipulation in Conference on Robot Learning (ML Research Press 2020) pp.\u00a01101\u20131112."},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"N. Furukawa A.\u00a0Namiki S.\u00a0Taku M.\u00a0Ishikawa Dynamic regrasping using a high-speed multifingered hand and a high-speed vision system in Proceedings 2006 IEEE International Conference on Robotics and Automation (IEEE 2006) pp.\u00a0181\u2013187.","DOI":"10.1109\/ROBOT.2006.1641181"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"T. Ishihara A.\u00a0Namiki M.\u00a0Ishikawa M.\u00a0Shimojo Dynamic pen spinning using a high-speed multifingered hand with high-speed tactile sensor in 6th IEEE-RAS International Conference on Humanoid Robots (IEEE 2006) pp.\u00a0258\u2013263.","DOI":"10.1109\/ICHR.2006.321394"},{"key":"e_1_3_2_14_2","unstructured":"V. Kumar A.\u00a0Gupta E.\u00a0Todorov and S.\u00a0Levine Learning dexterous manipulation policies from experience and imitation. arXiv:1611.05095 [cs.LG] (15 November 2016)."},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"B. Calli A.\u00a0M.\u00a0Dollar Vision-based model predictive control for within-hand precision manipulation with underactuated grippers in 2017 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2017) pp.\u00a02839\u20132845.","DOI":"10.1109\/ICRA.2017.7989331"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9772-z"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"H. Van Hoof T.\u00a0Hermans G.\u00a0Neumann J.\u00a0Peters Learning robot in-hand manipulation with tactile features in 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) (IEEE 2015) pp.\u00a0121\u2013127.","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007411"},{"key":"e_1_3_2_19_2","article-title":"Surprisingly robust in-hand manipulation: An empirical study","author":"Bhatt A.","year":"2021","unstructured":"A.\u00a0Bhatt, A.\u00a0Sieler, S.\u00a0Puhlmann, O.\u00a0Brock, Surprisingly robust in-hand manipulation: An empirical study. Robot. Sci. Syst., (2021).","journal-title":"Robot. Sci. Syst."},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"B. Calli A.\u00a0Kimmel K.\u00a0Hang K.\u00a0Bekris A.\u00a0Dollar Path planning for within-hand manipulation over learned representations of safe states in International Symposium on Experimental Robotics (Springer 2020) pp.\u00a0437\u2013447.","DOI":"10.1007\/978-3-030-33950-0_38"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"H. Zhu A.\u00a0Gupta A.\u00a0Rajeswaran S.\u00a0Levine V.\u00a0Kumar Dexterous manipulation with deep reinforcement learning: Efficient general and low-cost in 2019 International Conference on Robotics and Automation (ICRA) (IEEE 2019) pp.\u00a03651\u20133657.","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"A. Rajeswaran V.\u00a0Kumar A.\u00a0Gupta G.\u00a0Vezzani J.\u00a0Schulman E.\u00a0Todorov S.\u00a0Levine Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. arXiv:1709.10087 [cs.LG] (18 September 2017).","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"G. Khandate M.\u00a0Haas-Heger M.\u00a0Ciocarlie On the feasibility of learning finger-gaiting in-hand manipulation with intrinsic sensing in 2022 International Conference on Robotics and Automation (ICRA ) (IEEE 2022) pp.\u00a02752\u20132758.","DOI":"10.1109\/ICRA46639.2022.9812212"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145961"},{"key":"e_1_3_2_25_2","unstructured":"R. Jeong J.\u00a0T.\u00a0Springenberg J.\u00a0Kay D.\u00a0Zheng Y.\u00a0Zhou A.\u00a0Galashov N.\u00a0Heess F.\u00a0Nori Learning dexterous manipulation from suboptimal experts in Conference on Robot Learning (ML Research Press 2020) pp.\u00a0915\u2013934."},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"L. Sievers J.\u00a0Pitz B.\u00a0B\u00e4uml Learning purely tactile in-hand manipulation with a torque-controlled hand in 2022 International Conference on Robotics and Automation (ICRA) (IEEE 2022) pp.\u00a02745\u20132751.","DOI":"10.1109\/ICRA46639.2022.9812093"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"A. Allshire M.\u00a0MittaI V.\u00a0Lodaya V.\u00a0Makoviychuk D.\u00a0Makoviichuk F.\u00a0Widmaier M.\u00a0W\u00fcthrich S.\u00a0Bauer A.\u00a0Handa A.\u00a0Garg Transferring dexterous manipulation from gpu simulation to a remote real-world trifinger in 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2022) pp.\u00a011 802\u201311 809.","DOI":"10.1109\/IROS47612.2022.9981458"},{"key":"e_1_3_2_28_2","unstructured":"D. Chen B.\u00a0Zhou V.\u00a0Koltun and P.\u00a0Kr\u00e4henb\u00fchl Learning by cheating in Conference on Robot Learning (ML Research Press 2020) pp.\u00a066\u201375."},{"key":"e_1_3_2_29_2","unstructured":"G.\u00a0B.\u00a0Margolis T.\u00a0Chen K.\u00a0Paigwar X.\u00a0Fu D.\u00a0Kim S.\u00a0Kim and P.\u00a0Agrawal Learning to jump from pixels in Conference on Robot Learning (ML Research Press 2022) pp.\u00a01025\u20131034."},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"A. Kumar Z.\u00a0Fu D.\u00a0Pathak J.\u00a0Malik RMA: Rapid motor adaptation for legged robots. arXiv:2107.04034. [cs.LG] (8 July 2021).","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3070102"},{"key":"e_1_3_2_33_2","doi-asserted-by":"crossref","unstructured":"J. Tobin R.\u00a0Fong A.\u00a0Ray J.\u00a0Schneider W.\u00a0Zaremba P.\u00a0Abbeel Domain randomization for transferring deep neural networks from simulation to the real world in 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (IEEE 2017) pp.\u00a023\u201330.","DOI":"10.1109\/IROS.2017.8202133"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"N.\u00a0C.\u00a0Dafle A.\u00a0Rodriguez R.\u00a0Paolini B.\u00a0Tang S.\u00a0S.\u00a0Srinivasa M.\u00a0Erdmann M.\u00a0T.\u00a0Mason I.\u00a0Lundberg H.\u00a0Staab T.\u00a0Fuhlbrigge Extrinsic dexterity: In-hand manipulation with external forces in 2014 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2014) pp.\u00a01578\u20131585.","DOI":"10.1109\/ICRA.2014.6907062"},{"key":"e_1_3_2_35_2","unstructured":"M. Ahn H.\u00a0Zhu K.\u00a0Hartikainen H.\u00a0Ponte A.\u00a0Gupta S.\u00a0Levine V.\u00a0Kumar Robel: Robotics benchmarks for learning with low-cost robots in Conference on Robot Learning (PMLR 2020) pp.\u00a01300\u20131313."},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1080\/00031305.1998.10480559","article-title":"Violin plots: A box plot-density trace synergism","volume":"52","author":"Hintze J. L.","year":"1998","unstructured":"J. L.\u00a0Hintze, R. D.\u00a0Nelson, Violin plots: A box plot-density trace synergism. Am. Stat. 52, 181\u2013184 (1998).","journal-title":"Am. Stat."},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"A. Handa A.\u00a0Allshire V.\u00a0Makoviychuk A.\u00a0Petrenko R.\u00a0Singh J.\u00a0Liu D.\u00a0Makoviichuk K.\u00a0Van Wyk A.\u00a0Zhurkevich B.\u00a0Sundaralingam Y.\u00a0S.\u00a0Narang Dextreme: Transfer of agile in-hand manipulation from simulation to reality in 2023 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2023) pp.\u00a05977\u20135984.","DOI":"10.1109\/ICRA48891.2023.10160216"},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","unstructured":"C. Chen P.\u00a0Culbertson M.\u00a0Lepert M.\u00a0Schwager J.\u00a0Bohg Trajectotree: Trajectory optimization meets tree search for planning multi-contact dexterous manipulation in 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2021) pp.\u00a08262\u20138268.","DOI":"10.1109\/IROS51168.2021.9636346"},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"T. Pang H.\u00a0Suh L.\u00a0Yang R.\u00a0Tedrake Global planning for contact-rich manipulation via local smoothing of quasi-dynamic contact models. arXiv:2206.10787 [cs.RO] (22 June 2022).","DOI":"10.1109\/TRO.2023.3300230"},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"J. Xu T.\u00a0Chen L.\u00a0Zlokapa M.\u00a0Foshey W.\u00a0Matusik S.\u00a0Sueda P.\u00a0Agrawal An end-to-end differentiable framework for contact-aware robot design. arXiv:2107.07501 [cs.RO] (15 June 2021).","DOI":"10.15607\/RSS.2021.XVII.008"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"S. Brahmbhatt C.\u00a0Ham C.\u00a0C.\u00a0Kemp J.\u00a0Hays ContactDB: Analyzing and predicting grasp contact via thermal imaging in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2019).","DOI":"10.1109\/CVPR.2019.00891"},{"key":"e_1_3_2_42_2","unstructured":"V. Makoviychuk L.\u00a0Wawrzyniak Y.\u00a0Guo M.\u00a0Lu K.\u00a0Storey M.\u00a0Macklin D.\u00a0Hoeller N.\u00a0Rudin A.\u00a0Allshire A.\u00a0Handa G.\u00a0State Isaac gym: High performance GPU based physics simulation for robot learning in Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS 2021)."},{"key":"e_1_3_2_43_2","unstructured":"S. Ross G.\u00a0Gordon D.\u00a0Bagnell A reduction of imitation learning and structured prediction to no-regret online learning in Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (ML Research Press 2011) pp.\u00a0627\u2013635."},{"key":"e_1_3_2_44_2","unstructured":"J. Schulman F.\u00a0Wolski P.\u00a0Dhariwal A.\u00a0Radford O.\u00a0Klimov Proximal policy optimization algorithms. arXiv:1707.06347 [cs.LG] (20 July 2017)."},{"key":"e_1_3_2_45_2","unstructured":"A.\u00a0Y.\u00a0Ng D.\u00a0Harada S.\u00a0Russell Policy invariance under reward transformations: Theory and application to reward shaping in Proceedings of the Sixteenth International Conference on Machine Learning vol. 99 (ICML 1999) pp.\u00a0278\u2013287."},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"C. Choy J.\u00a0Gwak S.\u00a0Savarese 4D spatio-temporal convnets: Minkowski convolutional neural networks in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE 2019) pp.\u00a03075\u20133084.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"K. Cho B.\u00a0van Merri\u00ebnboer C.\u00a0Gulcehre D.\u00a0Bahdanau F.\u00a0Bougares H.\u00a0Schwenk Y.\u00a0Bengio Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing ( EMNLP ) (Association for Computational Linguistics 2014) pp.\u00a01724\u20131734.","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"J. Tan T.\u00a0Zhang E.\u00a0Coumans A.\u00a0Iscen Y.\u00a0Bai D.\u00a0Hafner S.\u00a0Bohez V.\u00a0Vanhoucke Sim-to-real: Learning agile locomotion for quadruped robots. arXiv:1804.10332v2 [cs.RO] (27 April 2018).","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"e_1_3_2_50_2","doi-asserted-by":"crossref","unstructured":"L. Downs A.\u00a0Francis N.\u00a0Koenig B.\u00a0Kinman R.\u00a0Hickman K.\u00a0Reymann T.\u00a0B.\u00a0McHugh V.\u00a0Vanhoucke Google scanned objects: A high-quality dataset of 3D scanned household items in 2022 International Conference on Robotics and Automation (ICRA) (IEEE 2022) pp.\u00a02553\u20132560.","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"e_1_3_2_51_2","unstructured":"K. Mamou E.\u00a0Lengyel A.\u00a0Peters Volumetric hierarchical approximate convex decomposition in Game Engine Gems 3 (AK Peters 2016) pp.\u00a0141\u2013158."},{"key":"e_1_3_2_52_2","unstructured":"D.-A. Clevert T.\u00a0Unterthiner S.\u00a0Hochreiter Fast and accurate deep network learning by exponential linear units (elus) in 4th International Conference on Learning Representations ( ICLR 2016)."},{"key":"e_1_3_2_53_2","unstructured":"D.\u00a0P.\u00a0Kingma J.\u00a0Ba Adam: A method for stochastic optimization in 3rd International Conference on Learning Representations (ICLR 2015)."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066213"},{"key":"e_1_3_2_55_2","unstructured":"M. Quigley K.\u00a0Conley B.\u00a0Gerkey J.\u00a0Faust T.\u00a0Foote J.\u00a0Leibs R.\u00a0Wheeler A.\u00a0Y.\u00a0Ng ROS: An open-source robot operating system in ICRA Workshop on Open Source Software (IEEE 2009) vol. 3 p.\u00a05."},{"key":"e_1_3_2_56_2","unstructured":"P. Florence C.\u00a0Lynch A.\u00a0Zeng O.\u00a0A.\u00a0Ramirez A.\u00a0Wahid L.\u00a0Downs A.\u00a0Wong J.\u00a0Lee I.\u00a0Mordatch J.\u00a0Tompson Implicit behavioral cloning in Conference on Robot Learning (ML Research Press 2022) pp.\u00a0158\u2013168."},{"key":"e_1_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Y. Zhou C.\u00a0Barnes J.\u00a0Lu J.\u00a0Yang H.\u00a0Li On the continuity of rotation representations in neural networks in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2019) pp.\u00a05745\u20135753.","DOI":"10.1109\/CVPR.2019.00589"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adc9244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:27:53Z","timestamp":1730575673000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.adc9244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,22]]},"references-count":56,"journal-issue":{"issue":"84","published-print":{"date-parts":[[2023,11,22]]}},"alternative-id":["10.1126\/scirobotics.adc9244"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.adc9244","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,22]]},"assertion":[{"value":"2022-11-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-26","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadc9244"}}