{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:20:21Z","timestamp":1774621221663,"version":"3.50.1"},"reference-count":50,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"48","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1734633"],"award-info":[{"award-number":["1734633"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2020,11,18]]},"abstract":"<jats:p>Warm-starting grasp-optimized motion planning with deep learning reduces computation time by two orders of magnitude.<\/jats:p>","DOI":"10.1126\/scirobotics.abd7710","type":"journal-article","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T00:14:30Z","timestamp":1605744870000},"source":"Crossref","is-referenced-by-count":64,"title":["Deep learning can accelerate grasp-optimized motion planning"],"prefix":"10.1126","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4874-9478","authenticated-orcid":true,"given":"Jeffrey","family":"Ichnowski","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, CA 94720, USA."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2062-5983","authenticated-orcid":true,"given":"Yahav","family":"Avigal","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, CA 94720, USA."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9544-6491","authenticated-orcid":true,"given":"Vishal","family":"Satish","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, CA 94720, USA."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-9499","authenticated-orcid":true,"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, CA 94720, USA."}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau4984"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"J. Ichnowski M. Danielczuk J. Xu V. Satish K. Goldberg \u201cGOMP: Grasp-optimized motion planning for bin picking \u201d in 2020 International Conference on Robotics and Automation (ICRA) (IEEE 2020).","DOI":"10.1109\/ICRA40945.2020.9197548"},{"key":"e_1_3_2_4_2","first-page":"1","article-title":"Finding locally optimal, collision-free trajectories with sequential convex optimization","volume":"9","author":"Schulman J.","year":"2013","unstructured":"J. Schulman, A. Lee, I. Awwal, H. Bradlow, P. Abbeel, Finding locally optimal, collision-free trajectories with sequential convex optimization. Robot. Sci. Syst. 9, 1\u201310 (2013).","journal-title":"Robot. Sci. Syst."},{"key":"e_1_3_2_5_2","unstructured":"Universal Robotics UR5 Collaborative Robot Arm https:\/\/web.archive.org\/web\/20190815054522\/https:\/\/www.universal-robots.com\/products\/ur5-robot\/ [accessed 15 August 2019]."},{"key":"e_1_3_2_6_2","unstructured":"Robotiq 2F-85 and 2F-140 Grippers https:\/\/web.archive.org\/web\/20190519030456\/https:\/\/robotiq.com\/products\/2f85-140-adaptive-robot-gripper [accessed 19 May 2019]."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-020-00179-2"},{"key":"e_1_3_2_8_2","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler M. D.","year":"2012","unstructured":"M. D. Zeiler, ADADELTA: An adaptive learning rate method. CoRR 1212.5701 , (2012).","journal-title":"CoRR"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"K. He X. Zhang S. Ren J. Sun Delving deep into rectifiers: Surpassing human-level performance on imagenet classification in Proceedings of the IEEE International Conference on Computer Vision (Santiago Chile 2015) pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"T. Kunz M. Stilman Time-optimal trajectory generation for path following with bounded acceleration and velocity in Proceedings of the 2012 Robotics: Science and Systems VIII (RSS) (2012).","DOI":"10.15607\/RSS.2012.VIII.027"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"W. Merkt V. Ivan S. Vijayakumar Leveraging precomputation with problem encoding for warm-starting trajectory optimization in complex environments in 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2018) pp. 5877\u20135884.","DOI":"10.1109\/IROS.2018.8593977"},{"key":"e_1_3_2_14_2","unstructured":"K. P. Hawkins Analytic inverse kinematics for the universal robots UR-5\/UR-10 arms Technical Report (Georgia Institute of Technology 2013)."},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"N. Ratliff M. Zucker J. A. Bagnell S. Srinivasa CHOMP: Gradient optimization techniques for efficient motion planning in 2009 IEEE International Conference on Robotics and Automation (IEEE 2009) pp. 489\u2013494.","DOI":"10.1109\/ROBOT.2009.5152817"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"M. Kalakrishnan S. Chitta E. Theodorou P. Pastor S. Schaal STOMP: Stochastic trajectory optimization for motion planning in 2011 IEEE International Conference on Robotics and Automation (IEEE 2011) pp. 4569\u20134574.","DOI":"10.1109\/ICRA.2011.5980280"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"C. Park J. Pan D. Manocha ITOMP: Incremental trajectory optimization for real-time replanning in dynamic environments in Twenty-Second International Conference on Automated Planning and Scheduling (AAAI Press 2012).","DOI":"10.1609\/icaps.v22i1.13513"},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"A. Kuntz C. Bowen R. Alterovitz Fast anytime motion planning in point clouds by interleaving sampling and interior point optimization in Robotics Research (Springer Cham 2020) pp. 929\u2013945.","DOI":"10.1007\/978-3-030-28619-4_63"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1168317"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"J. Mahler F. T. Pokorny B. Hou M. Roderick M. Laskey M. Aubry K. Kohlhoff T. Kr\u00f6ger J. Kuffner K. Goldberg Dex-Net 1.0: A cloud-based network of 3D objects for robust grasp planning using a multi-armed bandit model with correlated rewards in Proceedings of IEEE International Conference in Robotics and Automation (ICRA) (IEEE Stockholm Sweden 2016) pp. 1957\u20131964.","DOI":"10.1109\/ICRA.2016.7487342"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"e_1_3_2_22_2","unstructured":"J. Mahler K. Goldberg Learning deep policies for robot bin picking by simulating robust grasping sequences in Proceeding of the 1st Annual Conference on Robot Learning (CoRL) (2017) pp. 515\u2013524."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2895878"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"A. Mousavian C. Eppner D. Fox 6-DOF GraspNet: Variational grasp generation for object manipulation in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019) pp. 2901\u20132910.","DOI":"10.1109\/ICCV.2019.00299"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"A. Murali A. Mousavian C. Eppner C. Paxton D. Fox 6-DOF grasping for target-driven object manipulation in clutter (2019); arXiv:1912.03628 [cs.RO] (8 December 2019).","DOI":"10.1109\/ICRA40945.2020.9197318"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"X. Yan J. Hsu M. Khansari Y. Bai A. Pathak A. Gupta J. Davidson H. Lee Learning 6-DOF grasping interaction via deep geometry-aware 3D representations in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2018) pp. 1\u20139.","DOI":"10.1109\/ICRA.2018.8460609"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"M. Liu Z. Pan K. Xu K. Ganguly D. Manocha Generating grasp poses for a high-DOF gripper using neural networks in Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2019).","DOI":"10.1109\/IROS40897.2019.8968115"},{"key":"e_1_3_2_31_2","unstructured":"C. Eppner A. Mousavian D. Fox A billion ways to grasp: An evaluation of grasp sampling schemes on a dense physics-based grasp data set in International Symposium of Robotics Research (ISRR) (2019)."},{"key":"e_1_3_2_32_2","unstructured":"K. Goldberg MIT RoboSeminar - The New Wave in Robot Grasping (2019); https:\/\/youtu.be\/ATDrSWZXuwk."},{"key":"e_1_3_2_33_2","unstructured":"R. M. Murray Z. Li S. S. Sastry S. S. Sastry A Mathematical Introduction to Robotic Manipulation (CRC press 1994)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"D. Prattichizzo J. C. Trinkle Springer Handbook of Robotics (Springer 2016) pp. 955\u2013988.","DOI":"10.1007\/978-3-319-32552-1_38"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"E. Rimon J. Burdick The Mechanics of Robot Grasping (Cambridge University Press 2019).","DOI":"10.1017\/9781108552011"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"E. Johns S. Leutenegger A. J. Davison Deep learning a grasp function for grasping under gripper pose uncertainty. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2016) pp. 4461\u20134468.","DOI":"10.1109\/IROS.2016.7759657"},{"key":"e_1_3_2_37_2","unstructured":"U. Viereck A. ten Pas K. Saenko R. Platt Learning a visuomotor controller for real world robotic grasping using simulated depth images in Proceedings of the 1st Conference on Robot Learning (CoRL) (2017)."},{"key":"e_1_3_2_38_2","unstructured":"D. Kalashnikov A. Irpan P. Pastor J. Ibarz A. Herzog E. Jang D. Quillen E. Holly M. Kalakrishnan V. Vanhoucke S. Levine. Scalable deep reinforcement learning for vision-based robotic manipulation in Proceedings fo the 2nd Conference on Robot Learning (CoRL) (2018) pp. 651\u2013673."},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"L. Pinto A. Gupta Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2016) pp. 3406\u20133413.","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"S. Levine P. Pastor A. Krizhevsky D. Quillen Learning hand-eye coordination for robotic grasping with large-scale data collection in International Symposium on Experimental Robotics (ISER) (Springer 2016) pp. 173\u2013184.","DOI":"10.1007\/978-3-319-50115-4_16"},{"key":"e_1_3_2_41_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 InternationalConference on Robotics and Automation (ICRA) (IEEE 2018) pp. 4243\u20134250.","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"D. Kappler J. Bohg S. Schaal Leveraging big data for grasp planning in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2015) pp. 4304\u20134311.","DOI":"10.1109\/ICRA.2015.7139793"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972893"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2006.873005"},{"key":"e_1_3_2_45_2","unstructured":"M. Toussaint Logic-geometric programming: An optimization-based approach to combined task and motion planning in Proceedings of the 24th International Conference on Artificial Intelligence (IJCAI) (2015) pp. 1930\u20131936."},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"D. Hadfield-Menell C. Lin R. Chitnis S. Russell P. Abbeel Sequential quadratic programming for task plan optimization in 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2016) pp. 5040\u20135047.","DOI":"10.1109\/IROS.2016.7759740"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.3182\/20080706-5-KR-1001.01182"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"N. Mansard A. DelPrete M. Geisert S. Tonneau O. Stasse Using a memory of motion to efficiently warm-start a nonlinear predictive controller in 2018 Proceedings of theIEEE International Conference on Robotics and Automation (ICRA) (IEEE 2018) pp. 2986\u20132993.","DOI":"10.1109\/ICRA.2018.8463154"},{"key":"e_1_3_2_49_2","unstructured":"S. Ross G. Gordon D. Bagnell 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 (2011) pp. 627\u2013635."},{"key":"e_1_3_2_50_2","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N.","year":"2014","unstructured":"N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_51_2","doi-asserted-by":"crossref","unstructured":"S. J. Rennie V. Goel S. Thomas Annealed dropout training of deep networks in 2014 IEEE Spoken Language Technology Workshop (SLT) (IEEE 2014) pp. 159\u2013164.","DOI":"10.1109\/SLT.2014.7078567"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1126\/scirobotics.abd7710","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.abd7710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T12:30:13Z","timestamp":1705408213000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.abd7710"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,18]]},"references-count":50,"journal-issue":{"issue":"48","published-print":{"date-parts":[[2020,11,18]]}},"alternative-id":["10.1126\/scirobotics.abd7710"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.abd7710","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,18]]},"article-number":"eabd7710"}}