{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:31:52Z","timestamp":1777735912723,"version":"3.51.4"},"reference-count":61,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.sagepub.com\/licence-information-for-chorus"}],"funder":[{"name":"FAIR - Future Artificial Intelligence Research, European Union Next-GenerationEU","award":["PIANO NAZIONALE DI RIPRESA E RESILIENZA (PNRR) \u00e2\u20ac\u201c"],"award-info":[{"award-number":["PIANO NAZIONALE DI RIPRESA E RESILIENZA (PNRR) \u00e2\u20ac\u201c"]}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["National Center of Competence in Research (NCCR)"],"award-info":[{"award-number":["National Center of Competence in Research (NCCR)"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["H2020-MSCA-RISE project NoMADS - DLV-777826"],"award-info":[{"award-number":["H2020-MSCA-RISE project NoMADS - DLV-777826"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["Research and Innovation Programme, grant #731540"],"award-info":[{"award-number":["Research and Innovation Programme, grant #731540"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["SLING grant #819789"],"award-info":[{"award-number":["SLING grant #819789"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CBMM, STC award CCF-1231216"],"award-info":[{"award-number":["CBMM, STC award CCF-1231216"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"NVIDIA Corporation","doi-asserted-by":"crossref","award":["Donation of a Titan Xp GPUs and a Tesla k40 GPU"],"award-info":[{"award-number":["Donation of a Titan Xp GPUs and a Tesla k40 GPU"]}],"id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["BAA-AFRL-AFOSR-2016-0007"],"award-info":[{"award-number":["BAA-AFRL-AFOSR-2016-0007"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-17-1-0390"],"award-info":[{"award-number":["FA9550-17-1-0390"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-18-1-7009"],"award-info":[{"award-number":["FA9550-18-1-7009"]}],"id":[{"id":"10.13039\/100000181","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":[[2024,2]]},"abstract":"<jats:p>We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised learning that enables learning models to operate on output spaces with complex structures. Through the lens of structured prediction, we show how robots can learn to imitate trajectories belonging to not only Euclidean spaces but also Riemannian manifolds. Exploiting ideas from information theory, we propose a class of loss functions based on the f-divergence to measure the information loss between the demonstrated and reproduced probabilistic trajectories. Different types of f-divergence will result in different policies, which we call imitation modes. Furthermore, our approach enables the incorporation of spatial and temporal trajectory modulation, which is necessary for robots to be adaptive to the change in working conditions. We benchmark our algorithm against state-of-the-art methods in terms of trajectory reproduction and adaptation. The quantitative evaluation shows that our approach outperforms other algorithms regarding both accuracy and efficiency. We also report real-world experimental results on learning manifold trajectories in a polishing task with a KUKA LWR robot arm, illustrating the effectiveness of our algorithmic framework.<\/jats:p>","DOI":"10.1177\/02783649231204656","type":"journal-article","created":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T02:36:30Z","timestamp":1698892590000},"page":"113-133","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":15,"title":["A structured prediction approach for robot imitation learning"],"prefix":"10.1177","volume":"43","author":[{"given":"Anqing","family":"Duan","sequence":"first","affiliation":[{"name":"Robotics and Machine Intelligence Laboratory, The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"given":"Iason","family":"Batzianoulis","sequence":"additional","affiliation":[{"name":"Learning Algorithms and Systems Laboratory, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8890-2732","authenticated-orcid":false,"given":"Raffaello","family":"Camoriano","sequence":"additional","affiliation":[{"name":"Visual And Multimodal Applied Learning Laboratory (VANDAL), Politecnico di Torino, Turin, Italy"}]},{"given":"Lorenzo","family":"Rosasco","sequence":"additional","affiliation":[{"name":"DIBRIS, Universit\u00e0 degli Studi di Genova, Genoa, Italy"},{"name":"Laboratory for Computational and Statistical Learning (IIT@MIT), Istituto Italiano di Tecnologia and Massachusetts Institute of Technology, Cambridge, MA, USA"},{"name":"Machine Learning Genoa (MaLGa) Center, Universit\u00e0 di Genova, Genoa, Italy"}]},{"given":"Daniele","family":"Pucci","sequence":"additional","affiliation":[{"name":"Artificial and Mechanical Intelligence research line (AMI), Istituto Italiano di Tecnologia, Genoa, Italy"}]},{"given":"Aude","family":"Billard","sequence":"additional","affiliation":[{"name":"Learning Algorithms and Systems Laboratory, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"}]}],"member":"179","published-online":{"date-parts":[[2023,11,1]]},"reference":[{"key":"bibr1-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"bibr2-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"bibr3-02783649231204656","volume-title":"Optimization Algorithms on Matrix Manifolds","author":"Absil PA","year":"2009"},{"key":"bibr4-02783649231204656","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00132"},{"key":"bibr5-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917744035"},{"key":"bibr6-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1561\/2200000036"},{"key":"bibr7-02783649231204656","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.021"},{"key":"bibr8-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056367"},{"key":"bibr9-02783649231204656","first-page":"5058","volume":"33","author":"Bahl S","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bibr10-02783649231204656","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.082"},{"key":"bibr11-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"bibr12-02783649231204656","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.078"},{"key":"bibr13-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2020.2980548"},{"key":"bibr14-02783649231204656","first-page":"2192","volume-title":"Uncertainty in Artificial Intelligence","author":"Cheng CA","year":"2018"},{"key":"bibr15-02783649231204656","first-page":"4412","volume-title":"Advances in Neural Information Processing Systems 29","author":"Ciliberto C","year":"2016"},{"issue":"98","key":"bibr16-02783649231204656","first-page":"1","volume":"21","author":"Ciliberto C","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"bibr17-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3236952"},{"key":"bibr18-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624934"},{"key":"bibr19-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968496"},{"key":"bibr20-02783649231204656","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00060"},{"key":"bibr21-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3186504"},{"key":"bibr22-02783649231204656","unstructured":"Figueroa N, Billard A (2018) A physically-consistent bayesian non-parametric mixture model for dynamical system learning. In:2nd Annual Conference on Robot Learning, CoRL 2018, Z\u00fcrich, Switzerland, 29\u201331 October 2018, Proceedings, volume 87."},{"key":"bibr23-02783649231204656","first-page":"158","volume-title":"Conference on Robot Learning","author":"Florence P","year":"2022"},{"key":"bibr24-02783649231204656","first-page":"1259","volume-title":"Conference on Robot Learning","author":"Ghasemipour SKS","year":"2020"},{"key":"bibr25-02783649231204656","first-page":"4565","volume-title":"Advances in Neural Information Processing Systems","author":"Ho J","year":"2016"},{"key":"bibr26-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919846363"},{"key":"bibr27-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"bibr28-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"bibr29-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"bibr30-02783649231204656","volume-title":"2019 International Conference on Robotics and Automation (ICRA)","author":"Khoramshahi M","year":"2020"},{"key":"bibr31-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919868530"},{"key":"bibr32-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03194-1_4"},{"key":"bibr33-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509025"},{"key":"bibr34-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2163863"},{"key":"bibr35-02783649231204656","first-page":"2789","volume-title":"Advances in Neural Information Processing Systems","author":"Mroueh Y","year":"2012"},{"key":"bibr36-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"bibr37-02783649231204656","first-page":"2616","volume-title":"Advances in Neural Information Processing Systems","author":"Paraschos A","year":"2013"},{"key":"bibr38-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1201\/9781420034813"},{"key":"bibr39-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"bibr40-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"bibr41-02783649231204656","first-page":"305","volume-title":"Advances in Neural Information Processing Systems","author":"Pomerleau DA","year":"1989"},{"key":"bibr42-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9121-3"},{"key":"bibr43-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"bibr44-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943190"},{"key":"bibr45-02783649231204656","unstructured":"Ross S, Gordon G, Bagnell D (2011) 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, pp. 627\u2013635."},{"key":"bibr46-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3187818"},{"key":"bibr47-02783649231204656","first-page":"1657","volume":"28","author":"Rudi A","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bibr48-02783649231204656","first-page":"5610","volume-title":"Advances in Neural Information Processing Systems","author":"Rudi A","year":"2018"},{"key":"bibr49-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"bibr50-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650949"},{"key":"bibr51-02783649231204656","first-page":"1889","volume-title":"International Conference on Machine Learning","author":"Schulman J","year":"2015"},{"key":"bibr52-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0941-2"},{"key":"bibr53-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.05.005"},{"key":"bibr54-02783649231204656","first-page":"10022","volume-title":"International Conference on Machine Learning","author":"Swamy G","year":"2021"},{"key":"bibr55-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759801"},{"key":"bibr56-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2018.2817589"},{"key":"bibr57-02783649231204656","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.826410"},{"key":"bibr58-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202140"},{"key":"bibr59-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2657001"},{"key":"bibr60-02783649231204656","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206153"},{"key":"bibr61-02783649231204656","unstructured":"Ziebart BD, Maas A, Bagnell JA, et al. (2008) Maximum entropy inverse reinforcement learning. In: Proceedings of the 23rd National Conference on Artificial Intelligence - Volume 3, AAAI\u201908. AAAI Press. ISBN 9781577353683, p. 1433\u20131438."}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231204656","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649231204656","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231204656","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231204656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:17:12Z","timestamp":1777457832000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649231204656"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":61,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["10.1177\/02783649231204656"],"URL":"https:\/\/doi.org\/10.1177\/02783649231204656","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,1]]}}}