{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T10:06:20Z","timestamp":1777716380909,"version":"3.51.4"},"reference-count":68,"publisher":"SAGE Publications","issue":"9-10","license":[{"start":{"date-parts":[[2013,6,28]],"date-time":"2013-06-28T00:00:00Z","timestamp":1372377600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2013,8]]},"abstract":"<jats:p>We address the problem of encoding and executing skills, i.e. motion tasks involving a combination of specifications regarding constraints and variability. We take an approach that is model-free in the sense that we do not assume an explicit and complete analytical specification of the task \u2013 which can be hard to obtain for many realistic robot systems. Instead, we learn an encoding of the skill from observations of an initial set of sample trajectories. This is achieved by encoding trajectories in a skill manifold which is learnt from data and generalizes in the sense that all trajectories on the manifold satisfy the constraints and allowable variability in the demonstrated samples. In new instances of the trajectory-generation problem, we restrict attention to geodesic trajectories on the learnt skill manifold, making computation more tractable. This procedure is also extended to accommodate dynamic obstacles and constraints, and to dynamically react against unexpected perturbations, enabling a form of model-free feedback control with respect to an incompletely modelled skill. We present experiments to validate this framework using various robotic systems \u2013 ranging from a three-link arm to a small humanoid robot \u2013 demonstrating significant computational improvements without loss of accuracy. Finally, we present a comparative evaluation of our framework against a state-of-the-art imitation-learning method.<\/jats:p>","DOI":"10.1177\/0278364913482016","type":"journal-article","created":{"date-parts":[[2013,6,29]],"date-time":"2013-06-29T05:19:28Z","timestamp":1372483168000},"page":"1120-1150","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":15,"title":["Motion planning and reactive control on learnt skill manifolds"],"prefix":"10.1177","volume":"32","author":[{"given":"Ioannis","family":"Havoutis","sequence":"first","affiliation":[{"name":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30, 16163 Genova, Italy"}]},{"given":"Subramanian","family":"Ramamoorthy","sequence":"additional","affiliation":[{"name":"Institute of Perception, Action and Behaviour, School of Informatics, University of Edinburgh, UK"}]}],"member":"179","published-online":{"date-parts":[[2013,6,28]]},"reference":[{"key":"bibr1-0278364913482016","doi-asserted-by":"crossref","unstructured":"Abbeel P, Ng AY (2004) Apprenticeship learning via inverse reinforcement learning. In: 21st International Conference on Machine Learning (ICML \u201804) Banff, Alberta, Canada, July 4\u20138. New York: ACM Press http:\/\/dl.acm.org\/citation.cfm?id=1015330.1015430.","DOI":"10.1145\/1015330.1015430"},{"key":"bibr2-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509694"},{"key":"bibr3-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152399"},{"key":"bibr4-0278364913482016","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop CM","year":"2007"},{"key":"bibr5-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69134-1_20"},{"key":"bibr6-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1999.772447"},{"key":"bibr7-0278364913482016","unstructured":"Brand M (2003) Charting a manifold. Advances in neural information processing systems (2003), pp. 961\u2013968. Cambridge: MIT Press."},{"key":"bibr8-0278364913482016","first-page":"1","volume-title":"Workshop on the Algorithmic Foundations of Robotics","author":"Bretl T","year":"2004"},{"key":"bibr9-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066385"},{"key":"bibr10-0278364913482016","first-page":"367","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS \u201808)","author":"Calinon S","year":"2008"},{"key":"bibr11-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1163\/016918609X12529294461843"},{"key":"bibr12-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642266"},{"key":"bibr13-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2008738"},{"key":"bibr14-0278364913482016","unstructured":"Conner DC (2008) Integrating planning and control for constrained dynamical systems. PhD Thesis, Robotics Institute, Carnegie Mellon University, USA."},{"key":"bibr15-0278364913482016","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2006.II.008"},{"key":"bibr16-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1249705"},{"key":"bibr17-0278364913482016","unstructured":"Costa J, Hero AO (2003) Manifold learning with geodesic minimal spanning trees. Computing Research Repository http:\/\/arxiv.org\/abs\/cs\/0307038."},{"key":"bibr18-0278364913482016","volume-title":"Introduction to Robotics","author":"Craig JJ","year":"1989"},{"key":"bibr19-0278364913482016","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-5143"},{"key":"bibr20-0278364913482016","doi-asserted-by":"publisher","DOI":"10.2514\/1.13400"},{"key":"bibr21-0278364913482016","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2008.IV.021"},{"key":"bibr22-0278364913482016","volume-title":"Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems","author":"Doll\u00e1r P","year":"2006"},{"key":"bibr23-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273527"},{"key":"bibr24-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/SSP.2012.6319815"},{"key":"bibr25-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1002\/047172288X.ch15"},{"key":"bibr26-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.852260"},{"key":"bibr27-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.202.23.3325"},{"key":"bibr28-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910376251"},{"key":"bibr29-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21606-5"},{"key":"bibr30-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5651957"},{"key":"bibr31-0278364913482016","first-page":"2946","volume-title":"IEEE International Conference on Robotics and Automation (ICRA \u201810)","author":"Havoutis I","year":"2010"},{"key":"bibr32-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102388"},{"key":"bibr33-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2006703"},{"key":"bibr34-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.976259"},{"key":"bibr35-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"bibr36-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1641880"},{"key":"bibr37-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015357"},{"key":"bibr38-0278364913482016","unstructured":"K\u00e9gl B (2003) Intrinsic dimension estimation using packing numbers. http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.20.3428."},{"key":"bibr39-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2139130"},{"key":"bibr40-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"bibr41-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013219111657"},{"key":"bibr42-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"bibr43-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"bibr44-0278364913482016","volume-title":"Advances in Neural Information Processing Systems 17 (NIPS 2004)","author":"Levina E","year":"2004"},{"key":"bibr45-0278364913482016","volume-title":"The Control Handbook","author":"Levine WS","year":"1996"},{"key":"bibr46-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574707003815"},{"key":"bibr47-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-40065-5_10"},{"key":"bibr48-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"bibr49-0278364913482016","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2006.II.012"},{"key":"bibr50-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543234"},{"key":"bibr51-0278364913482016","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen CE","year":"2006"},{"key":"bibr52-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1641823"},{"key":"bibr53-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"bibr54-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015754"},{"key":"bibr55-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2002.1258"},{"key":"bibr56-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5"},{"key":"bibr57-0278364913482016","volume-title":"Optimal Control and Estimation","author":"Stengel RF","year":"1995"},{"key":"bibr58-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399305"},{"key":"bibr59-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910369189"},{"key":"bibr60-0278364913482016","first-page":"841","volume-title":"Advances in Neural Information Processing Systems 15 (NIPS 2003)","author":"Teh YW","year":"2003"},{"key":"bibr61-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"key":"bibr62-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363556"},{"key":"bibr63-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469949"},{"key":"bibr64-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.166"},{"key":"bibr65-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1162\/089976605774320557"},{"key":"bibr66-0278364913482016","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1167"},{"key":"bibr67-0278364913482016","volume-title":"International Symposium on Robotics Research (ISRR)","author":"Ye G","year":"2011"},{"key":"bibr68-0278364913482016","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1109\/ROBOT.2009.5152665","volume-title":"International Conference on Robotics and Automation (ICRA \u201809)","author":"Zhang L","year":"2009"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364913482016","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364913482016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:18:12Z","timestamp":1777457892000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0278364913482016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,28]]},"references-count":68,"journal-issue":{"issue":"9-10","published-print":{"date-parts":[[2013,8]]}},"alternative-id":["10.1177\/0278364913482016"],"URL":"https:\/\/doi.org\/10.1177\/0278364913482016","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6,28]]}}}