{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T16:44:32Z","timestamp":1772988272019,"version":"3.50.1"},"reference-count":65,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["P17\u201001"],"award-info":[{"award-number":["P17\u201001"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2024,11]]},"abstract":"<jats:p>Imitation learning (IL)\u00a0facilitates intuitive robotic programming. However, ensuring the reliability of learned behaviors remains a challenge. In the context of reaching motions, a robot should consistently reach its goal, regardless of its initial conditions. To meet this requirement, IL methods often employ specialized function approximators that guarantee this property by construction. Although effective, these approaches come with some limitations: 1) they are typically restricted in the range of motions they can model, resulting in suboptimal IL capabilities, and 2) they require explicit extensions to account for the geometry of motions that consider orientations. To address these challenges, we introduce a novel stability loss function that does not constrain the function approximator's architecture and enables learning policies that yield accurate results. Furthermore, it is not restricted to a specific state space geometry; therefore, it can easily incorporate the geometry of the robot's state space. Proof of the stability properties induced by this loss is provided and the method is empirically validated in various settings. These settings include Euclidean and non\u2010Euclidean state spaces, as well as first\u2010order and second\u2010order motions, both in simulation and with real robots. More details about the experimental results can be found at https:\/\/youtu.be\/ZWKLGntCI6w.<\/jats:p>","DOI":"10.1002\/aisy.202400144","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T03:16:14Z","timestamp":1728875774000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["PUMA: Deep Metric Imitation Learning for Stable Motion Primitives"],"prefix":"10.1002","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9503-7783","authenticated-orcid":false,"given":"Rodrigo","family":"P\u00e9rez\u2010Dattari","sequence":"first","affiliation":[{"name":"Department of Cognitive Robotics Delft University of Technology  Mekelweg 2 2628 CD Delft The Netherlands"}]},{"given":"Cosimo","family":"Della Santina","sequence":"additional","affiliation":[{"name":"Department of Cognitive Robotics Delft University of Technology  Mekelweg 2 2628 CD Delft The Netherlands"}]},{"given":"Jens","family":"Kober","sequence":"additional","affiliation":[{"name":"Department of Cognitive Robotics Delft University of Technology  Mekelweg 2 2628 CD Delft The Netherlands"}]}],"member":"311","published-online":{"date-parts":[[2024,10,14]]},"reference":[{"key":"e_1_2_14_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2016.06.018"},{"key":"e_1_2_14_3_1","unstructured":"M. A.Rana A.Li D.Fox B.Boots F.Ramos N.Ratliff 2nd Annual Conf. on Learning for Dynamics and Control (L4DC) 2020."},{"key":"e_1_2_14_4_1","doi-asserted-by":"crossref","unstructured":"J.Urain M.Ginesi D.Tateo J.Peters 2020 IEEE\/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) IEEE Piscataway NJ2020 pp.5231\u20135237.","DOI":"10.1109\/IROS45743.2020.9341035"},{"key":"e_1_2_14_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"e_1_2_14_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.03.001"},{"key":"e_1_2_14_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.02.012"},{"key":"e_1_2_14_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211030952"},{"key":"e_1_2_14_9_1","doi-asserted-by":"crossref","unstructured":"A.Ude B.Nemec T.Petri\u0107 J.Morimoto 2014 IEEE International Conf. on Robotics and Automation (ICRA) IEEE Piscataway NJ2014 pp.2997\u20133004.","DOI":"10.1109\/ICRA.2014.6907291"},{"key":"e_1_2_14_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3289597"},{"key":"e_1_2_14_11_1","unstructured":"J.Zhang H. B.Mohammadi L.Rozo Conf. on Robot Learning PMLR2022."},{"key":"e_1_2_14_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3219019"},{"key":"e_1_2_14_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104510"},{"key":"e_1_2_14_14_1","doi-asserted-by":"crossref","unstructured":"F.Schroff D.Kalenichenko J.Philbin Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition IEEE Piscataway NJ2015 pp.815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_14_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym11091066"},{"key":"e_1_2_14_16_1","doi-asserted-by":"crossref","unstructured":"S.Calinon A.Pistillo D. G.Caldwell 2011 IEEE\/RSJ International Conf. on Intelligent Robots and Systems IEEE Piscataway NJ2011 pp.3413\u20133418.","DOI":"10.1109\/IROS.2011.6094418"},{"key":"e_1_2_14_17_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"e_1_2_14_18_1","unstructured":"A.Paraschos C.Daniel J. R.Peters G.Neumann inAdvances in Neural Information Processing Systems Curran Associates Inc.2013 26."},{"key":"e_1_2_14_19_1","volume":"10","author":"Seker M. Y.","year":"2019","journal-title":"Robotics: Science and Systems"},{"key":"e_1_2_14_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"e_1_2_14_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3248443"},{"key":"e_1_2_14_22_1","unstructured":"H. B.Amor G.Neumann S.Kamthe O.Kroemer J.Peters 2014 IEEE International Conf. on Robotics and Automation (ICRA) IEEE Piscataway NJ2014 pp.2831\u20132837."},{"key":"e_1_2_14_23_1","doi-asserted-by":"crossref","unstructured":"A.Pervez Y.Mao D.Lee 2017 IEEE\u2010RAS 17th International Conf. on Humanoid Robotics (Humanoids) IEEE Piscataway NJ2017 pp.191\u2013197.","DOI":"10.1109\/HUMANOIDS.2017.8246874"},{"key":"e_1_2_14_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.04.010"},{"key":"e_1_2_14_25_1","first-page":"5058","volume":"33","author":"Bahl S.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_2_14_26_1","unstructured":"N.Figueroa A.Billard Conf. on Robot Learning PMLR2018 pp.927\u2013946."},{"key":"e_1_2_14_27_1","unstructured":"H.Ravichandar I.Salehi A.Dani Conf. on Robot Learning PMLR2017 pp.369\u2013378."},{"key":"e_1_2_14_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.04.006"},{"key":"e_1_2_14_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2705279"},{"key":"e_1_2_14_30_1","unstructured":"H.Ravichandar A.Dani Dynamic Systems and Control Conf. Vol.57250 American Society of Mechanical Engineers New York NJ2015 p.V002T27A008."},{"key":"e_1_2_14_31_1","doi-asserted-by":"crossref","unstructured":"C.Blocher M.Saveriano D.Lee 2017 14th International Conf. on Ubiquitous Robots and Ambient Intelligence (URAI) IEEE Piscataway NJ2017 pp.124\u2013129.","DOI":"10.1109\/URAI.2017.7992901"},{"key":"e_1_2_14_32_1","unstructured":"W.Zhi T.Lai L.Ott F.Ramos inL4DC PMLR2022 pp.508\u2013519."},{"key":"e_1_2_14_33_1","unstructured":"P.Pastor L.Righetti M.Kalakrishnan S.Schaal 2011 IEEE\/RSJ International Conf. on Intelligent Robots and Systems IEEE Piscataway NJ2011 pp.365\u2013371."},{"key":"e_1_2_14_34_1","unstructured":"L.Koutras Z.Doulgeri Conf. on Robot Learning PMLR2020 pp.293\u2013302."},{"key":"e_1_2_14_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2677469"},{"key":"e_1_2_14_36_1","first-page":"1","author":"Arduengo M.","year":"2023","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"e_1_2_14_37_1","unstructured":"J.Silv\u00e9rio L.Rozo S.Calinon D. G.Caldwell 2015 IEEE\/RSJ international Conf. on Intelligent Robots and Systems (IROS) IEEE Piscataway NJ2015 pp.464\u2013470."},{"key":"e_1_2_14_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9745-2"},{"key":"e_1_2_14_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2657001"},{"key":"e_1_2_14_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.10.002"},{"key":"e_1_2_14_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3010633"},{"key":"e_1_2_14_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103761"},{"key":"e_1_2_14_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9758-x"},{"key":"e_1_2_14_44_1","volume-title":"Nonlinear Systems","author":"Khalil H. K.","year":"2002"},{"key":"e_1_2_14_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00498-014-0128-8"},{"key":"e_1_2_14_46_1","volume-title":"Visual Differential Geometry and Forms: A Mathematical Drama in Five Acts","author":"Needham T.","year":"2021"},{"key":"e_1_2_14_47_1","volume-title":"Deep Learning","author":"Goodfellow I.","year":"2016"},{"key":"e_1_2_14_48_1","volume-title":"Hands\u2010On Machine Learning with Scikit\u2010Learn, Keras, and TensorFlow","author":"G\u00e9ron A.","year":"2022"},{"key":"e_1_2_14_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00234-2"},{"key":"e_1_2_14_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-814725-2.00008-X"},{"key":"e_1_2_14_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"e_1_2_14_52_1","unstructured":"T.Eiter H.Mannila Computing Discrete Fr\u00e9chet Distance Technische Universitat Wien Tech. Rep. CD\u2010TR 94\/64 1994."},{"key":"e_1_2_14_53_1","unstructured":"P.Corke J.Haviland 2021 IEEE International Conf. on Robotics and Automation (ICRA) IEEE Piscataway NJ2021 pp.11 357\u201311 363."},{"key":"e_1_2_14_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143311"},{"key":"e_1_2_14_55_1","first-page":"97","volume-title":"Ordinary Differential Equations","author":"Arnold V. I.","year":"1992"},{"key":"e_1_2_14_56_1","first-page":"119","volume-title":"Topology","author":"Munkres J. R.","year":"2000"},{"key":"e_1_2_14_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-17771-7"},{"key":"e_1_2_14_58_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511625756.012"},{"key":"e_1_2_14_59_1","first-page":"53","volume-title":"Fundamentals of Differential Equations","author":"Nagle R. K.","year":"2018"},{"key":"e_1_2_14_60_1","volume-title":"Riemannian Manifolds: An Introduction to Curvature","author":"Lee J. M.","year":"2006"},{"key":"e_1_2_14_61_1","volume-title":"Complex Analysis","author":"Berg C.","year":"2008"},{"key":"e_1_2_14_62_1","doi-asserted-by":"publisher","DOI":"10.1214\/17-STS620"},{"key":"e_1_2_14_63_1","doi-asserted-by":"publisher","DOI":"10.1090\/chel\/370"},{"key":"e_1_2_14_64_1","doi-asserted-by":"publisher","DOI":"10.1090\/clrm\/059"},{"key":"e_1_2_14_65_1","unstructured":"J.Bergstra R.Bardenet Y.Bengio B.K\u00e9gl Advances in Neural Information Processing Systems Curran Associates Inc.2011 24."},{"key":"e_1_2_14_66_1","doi-asserted-by":"crossref","unstructured":"T.Akiba S.Sano T.Yanase T.Ohta M.Koyama Proc. of the 25th ACM SIGKDD International Conf. on Knowledge Discovery & Data Mining 2019 pp.2623\u20132631.","DOI":"10.1145\/3292500.3330701"}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202400144","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/aisy.202400144","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202400144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T11:23:58Z","timestamp":1772969038000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202400144"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":65,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10.1002\/aisy.202400144"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202400144","archive":["Portico"],"relation":{},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"value":"2640-4567","type":"print"},{"value":"2640-4567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,14]]},"assertion":[{"value":"2024-02-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2400144"}}