{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T14:38:40Z","timestamp":1771943920256,"version":"3.50.1"},"reference-count":54,"publisher":"Cambridge University Press (CUP)","issue":"7","license":[{"start":{"date-parts":[[2020,12,18]],"date-time":"2020-12-18T00:00:00Z","timestamp":1608249600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotica"],"published-print":{"date-parts":[[2021,7]]},"abstract":"<jats:title>SUMMARY<\/jats:title><jats:p>Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.<\/jats:p>","DOI":"10.1017\/s0263574720001186","type":"journal-article","created":{"date-parts":[[2020,12,18]],"date-time":"2020-12-18T12:53:41Z","timestamp":1608296021000},"page":"1299-1315","source":"Crossref","is-referenced-by-count":13,"title":["Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters"],"prefix":"10.1017","volume":"39","author":[{"given":"Yosef","family":"Cohen","sequence":"first","affiliation":[]},{"given":"Or","family":"Bar-Shira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7717-7259","authenticated-orcid":false,"given":"Sigal","family":"Berman","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2020,12,18]]},"reference":[{"key":"S0263574720001186_ref39","volume-title":"Mathematical Physics","author":"Schultz","year":"1999"},{"key":"S0263574720001186_ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.004"},{"key":"S0263574720001186_ref43","unstructured":"[43] Ruder, S. , \u201cAn overview of gradient descent optimization algorithms\u201d, arXiv preprint arXiv:1609.04747 (2016)."},{"key":"S0263574720001186_ref53","unstructured":"[53] Schaal, S. , Kotosaka, S. and Sternad, D. , \u201cNonlinear Dynamical Systems as Movement Primitives,\u201d IEEE International Conference Humanoid Robotics, Santa Monica, USA (2000)."},{"key":"S0263574720001186_ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"S0263574720001186_ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.03.011"},{"key":"S0263574720001186_ref47","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"S0263574720001186_ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.071"},{"key":"S0263574720001186_ref51","doi-asserted-by":"crossref","unstructured":"[51] Peters, J. and Schaal, S. , \u201cPolicy Gradient Methods for Robotics\u201d, IEEE\/RSJ International Conference Intelligent Robots and Systems, Beijing, China (2006) pp. 2219\u20132225.","DOI":"10.1109\/IROS.2006.282564"},{"key":"S0263574720001186_ref52","doi-asserted-by":"crossref","unstructured":"[52] Schaal, S. , Mohajerian, P. and Ijspeert, A. , \u201cDynamics Systems vs. Optimal Control \u2014 A Unifying View,\u201d In: Progress in Brain Research ( Cisek, P. , Drew, T. and Kalaska, J. F. eds.), vol. 165 (2007) pp. 425\u2013445.","DOI":"10.1016\/S0079-6123(06)65027-9"},{"key":"S0263574720001186_ref37","unstructured":"[37] Liu, K. , Weissenfeld, A. and Ostermann, J. , \u201cParameterization of mouth images by LLE and PCA for image-based facial animation,\u201d IEEE International Conference on Acoustics, Speech, and Signal Processing, Toulouse, France (2006) pp. 461\u2013464."},{"key":"S0263574720001186_ref13","doi-asserted-by":"crossref","unstructured":"[13] Stulp, F. , Raiola, G. , Hoarau, A. 1, Ivaldi, S. and Sigaud, O. , \u201cLearning Compact Parameterized Skills with a Single Regression\u201d, IEEE-RAS International Conference on Humanoid Robots (Humanoids), Atlanta, USA (2013) pp. 417\u2013422.","DOI":"10.1109\/HUMANOIDS.2013.7030008"},{"key":"S0263574720001186_ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-1904-8"},{"key":"S0263574720001186_ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9457(00)00029-4"},{"key":"S0263574720001186_ref38","doi-asserted-by":"crossref","unstructured":"[38] Cohen, Y. and Berman, S. , \u201cTight Dynamic Movement Primitives for Complex Trajectory Generation,\u201d IEEE International Conference on Systems, Man, and Cybernetics, Manchester, UK (2013) pp. 2402\u20132407.","DOI":"10.1109\/SMC.2013.410"},{"key":"S0263574720001186_ref42","doi-asserted-by":"crossref","unstructured":"[42] Sze, V. , Chen, Y. H. , Yang, T. J. and Emer, J. S. , \u201cEfficient processing of deep neural networks: A tutorial and survey,\u201d Proceedings of the IEEE, 105(12), 2295\u20132329 (2017).","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"S0263574720001186_ref28","doi-asserted-by":"crossref","unstructured":"[28] Rueckert, E. , Mundo, J. , Paraschos, A. , Peters, J. and Neumann, G. , \u201cExtracting Low-Dimensional Control Variables for Movement Primitives,\u201d IEEE International Conference on Robotics and Automation, Seattle, USA (2015) pp. 1511\u20131518.","DOI":"10.1109\/ICRA.2015.7139390"},{"key":"S0263574720001186_ref20","doi-asserted-by":"publisher","DOI":"10.1017\/S026357471900078X"},{"key":"S0263574720001186_ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"S0263574720001186_ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20144-8"},{"key":"S0263574720001186_ref16","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"S0263574720001186_ref44","first-page":"315","volume-title":"International Conference on Artificial Intelligence and Statistics, Ft","author":"Glorot","year":"2011"},{"key":"S0263574720001186_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907421"},{"key":"S0263574720001186_ref45","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"S0263574720001186_ref17","doi-asserted-by":"crossref","unstructured":"[17] Hoffmann, H. , Pastor, P. , Park, D. H. and Schaal, S. , \u201cBiologically-Inspired Dynamical Systems for Movement Generation: Automatic Real-Time Goal Adaptation and Obstacle Avoidance,\u201d IEEE International Conference on Robotics and Automation, vol. 2, Kobe, Japan (2009), pp. 1\u20137.","DOI":"10.1109\/ROBOT.2009.5152423"},{"key":"S0263574720001186_ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10827-009-0180-4"},{"key":"S0263574720001186_ref14","unstructured":"[14] Ijspeert, A. J. , Nakanishi, J. and Schaal, S. , \u201cMovement Imitation with Nonlinear Dynamical Systems in Humanoid Robots,\u201d IEEE International Conference on Robotics and Automation, vol. 2, Washington, DC, USA (2002) pp. 1398\u20131403."},{"key":"S0263574720001186_ref21","doi-asserted-by":"crossref","unstructured":"[21] Girgin, H. and Ugur, E. , \u201cAssociative Skill Memory Models,\u201d IEEE\/RSJ International Conference on Intelligent Robots and Systems, Madrid, Spain (2018) pp. 6043\u20136048.","DOI":"10.1109\/IROS.2018.8593450"},{"key":"S0263574720001186_ref31","doi-asserted-by":"publisher","DOI":"10.11648\/j.ajtas.20160504.13"},{"key":"S0263574720001186_ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"S0263574720001186_ref49","unstructured":"[49] Kormushev, P. , Calinon, S. and Caldwell, D. G. , \u201cApproaches for Learning Human-Like Motor Skills which Require Variable Stiffness During Execution\u201d, IEEE International Conference on Humanoid Robots, Santa Monica, USA (2010)."},{"key":"S0263574720001186_ref54","doi-asserted-by":"crossref","unstructured":"[54] Pongas, D. , Billard, A. and Schaal, S. , \u201cRapid Synchronization and Accurate Phase-Locking of Rhythmic Motor Primitives,\u201d IEEE\/RSJ International Conference Intelligent Robots and Systems, Edmonton, Canada (2005) pp. 2911\u20132916.","DOI":"10.1109\/IROS.2005.1545257"},{"key":"S0263574720001186_ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.09.017"},{"key":"S0263574720001186_ref18","doi-asserted-by":"crossref","unstructured":"[18] Pastor, P. , Kalakrishnan, M. , Chitta, S. , Theodorou, E. and Schaal, S. , \u201cSkill Learning and Task Outcome Prediction for Manipulation,\u201d IEEE International Conference on Robotics and Automation, Shanghai, China (2011) pp. 9\u201313.","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"S0263574720001186_ref15","unstructured":"[15] Ijspeert, A. J. , Nakanishi, J. and Schaal, S. , \u201cLearning Attractor Landscapes for Learning Motor Primitives,\u201d In: Advances in Neural Information Processing Systems ( Becker, S. , Thrun, S. and Obermayer, K. , eds.), vol. 15 (Vancouver, Canada, 2003) pp. 1523\u20131530."},{"key":"S0263574720001186_ref48","doi-asserted-by":"crossref","unstructured":"[48] Kober, J. and Peters, J. , \u201cPolicy Search for Motor Primitives in Robotics,\u201d Advances in Neural Information Processing Systems, vol. 22, Vancouver, Canada (2009) pp. 171\u2013203.","DOI":"10.1007\/s10994-010-5223-6"},{"key":"S0263574720001186_ref24","doi-asserted-by":"crossref","unstructured":"[24] Kalakrishnan, M. , Pastor, P. , Righetti, L. and Schaal, S. , \u201cLearning Objective Functions for Manipulation,\u201d IEEE International Conference on Robotics and Automation, Karlsruhe, Germany (2013) pp. 1323\u20131328.","DOI":"10.1109\/ICRA.2013.6630743"},{"key":"S0263574720001186_ref29","unstructured":"[29] Paraschos, A. , Daniel, C. , Peters, J. and Neumann, G. , \u201cProbabilistic Movement Primitives,\u201d Advances in Neural Information Processing Systems, vol. 26, Lake Tahoe, USA (2013) pp. 2616\u20132624."},{"key":"S0263574720001186_ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4076(03)00157-X"},{"key":"S0263574720001186_ref36","volume-title":"Geometric Structure of High-Dimensional Data and Dimensionality Reduction","author":"Wang","year":"2012"},{"key":"S0263574720001186_ref30","first-page":"1","volume-title":"International Workshop on Pattern Recognition in Neuroimaging","author":"He","year":"2018"},{"key":"S0263574720001186_ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"S0263574720001186_ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-009-0295-8"},{"key":"S0263574720001186_ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"S0263574720001186_ref35","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"S0263574720001186_ref50","doi-asserted-by":"crossref","unstructured":"[50] Kormushev, P. , Calinon, S. and Caldwell, D. G. , \u201cRobot Motor Skill Coordination with EM-based Reinforcement Learning,\u201d IEEE\/RSJ International Conference Intelligent Robots and Systems, on Intelligent Robots and Systems, Taipei, Taiwan (2010) pp. 3232\u20133237.","DOI":"10.1109\/IROS.2010.5649089"},{"key":"S0263574720001186_ref11","unstructured":"[11] McGovern, A. and Barto, A. G. , \u201cAutomatic Discovery of Subgoals in Reinforcement Learning Using Diverse Density,\u201d Proceedings of the Eighteenth International Conference on Machine Learning, Williamstown, MA, USA (2001)."},{"key":"S0263574720001186_ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574711001056"},{"key":"S0263574720001186_ref8","doi-asserted-by":"crossref","unstructured":"[8] da Silva, B. C. , Baldassarre, G. , Konisidaris, G. and Barto, A. , \u201cLearning Parameterized Motor Skills on a Humanoid Robot,\u201d IEEE International Conference on Robotics and Automation, Hong Kong, China (2014) pp. 5239\u20135244.","DOI":"10.1109\/ICRA.2014.6907629"},{"key":"S0263574720001186_ref27","first-page":"1","volume-title":"The Path to Autonomous Robots","author":"de Granville","year":"2009"},{"key":"S0263574720001186_ref5","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"S0263574720001186_ref12","doi-asserted-by":"crossref","unstructured":"[12] Kober, J. , Oztop, E. and Peters, J. , \u201cReinforcement Learning to Adjust Robot Movements to New Situations,\u201d International Joint Conference on Artificial Intelligence, Barcelona, Spain (2011) pp. 2650\u20132655.","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"S0263574720001186_ref23","doi-asserted-by":"crossref","unstructured":"[23] Stulp, F. and Schaal, S. , \u201cHierarchical Reinforcement Learning with Movement Primitives,\u201d IEEE-RAS International Conference on Humanoid Robots, Bled, Slovenia (2011) pp. 231\u2013238.","DOI":"10.1109\/Humanoids.2011.6100841"},{"key":"S0263574720001186_ref32","volume-title":"International Conference on Learning Representations","author":"Basri","year":"2017"}],"container-title":["Robotica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0263574720001186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T07:19:48Z","timestamp":1623136788000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0263574720001186\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,18]]},"references-count":54,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["S0263574720001186"],"URL":"https:\/\/doi.org\/10.1017\/s0263574720001186","relation":{},"ISSN":["0263-5747","1469-8668"],"issn-type":[{"value":"0263-5747","type":"print"},{"value":"1469-8668","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,18]]}}}