{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:25:41Z","timestamp":1761060341123,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,5,4]],"date-time":"2017-05-04T00:00:00Z","timestamp":1493856000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Swiss National Science Foundation through the National Centre of Competence in Research Robotics"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2018,1]]},"DOI":"10.1007\/s10514-017-9636-y","type":"journal-article","created":{"date-parts":[[2017,5,4]],"date-time":"2017-05-04T10:24:10Z","timestamp":1493893450000},"page":"45-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Learning motions from demonstrations and rewards with time-invariant dynamical systems based policies"],"prefix":"10.1007","volume":"42","author":[{"given":"Joel","family":"Rey","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9528-770X","authenticated-orcid":false,"given":"Klas","family":"Kronander","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farbod","family":"Farshidian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Buchli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aude","family":"Billard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,4]]},"reference":[{"issue":"13","key":"9636_CR1","doi-asserted-by":"crossref","first-page":"1642","DOI":"10.1177\/0278364912464668","volume":"31","author":"A Ajoudani","year":"2012","unstructured":"Ajoudani, A., Tsagarakis, N., & Bicchi, A. (2012). Tele-impedance: Teleoperation with impedance regulation using a body-machine interface. The International Journal of Robotics Research, 31(13), 1642\u20131656.","journal-title":"The International Journal of Robotics Research"},{"key":"9636_CR2","doi-asserted-by":"crossref","unstructured":"Billard, A., Calinon, S., Dillmann, R., & Schaal, S. (2008). Handbook of Robotics Chapter 59: Robot Programming by Demonstration. In Handbook of Robotics. Springer.","DOI":"10.1007\/978-3-540-30301-5_60"},{"issue":"7","key":"9636_CR3","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1177\/0278364911402527","volume":"30","author":"J Buchli","year":"2011","unstructured":"Buchli, J., Stulp, F., Theodorou, E., & Schaal, S. (2011). Learning variable impedance control. The International Journal of Robotics Research, 30(7), 820\u2013833.","journal-title":"The International Journal of Robotics Research"},{"issue":"6862","key":"9636_CR4","doi-asserted-by":"crossref","first-page":"4469","DOI":"10.1038\/35106566","volume":"414","author":"E Burdet","year":"2001","unstructured":"Burdet, E., Osu, R., Franklin, D. W., Milner, T. E., & Kawato, M. (2001). The central nervous system stabilizes unstable dynamics by learning optimal impedance. Nature, 414(6862), 4469.","journal-title":"Nature"},{"key":"9636_CR5","doi-asserted-by":"crossref","unstructured":"Calinon, S., Bruno, S., & Caldwell, D.G. (2014). A task-parameterized probabilistic model with minimal intervention control. In IEEE International Conference on Robotics and Automation (pp. 3339\u20133344).","DOI":"10.1109\/ICRA.2014.6907339"},{"key":"9636_CR6","doi-asserted-by":"crossref","unstructured":"Calinon, S., Sardellitti, I., Caldwell, D. (2010). Learning-based control strategy for safe human-robot interaction exploiting task and robot redundancies. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 249\u2013254).","DOI":"10.1109\/IROS.2010.5648931"},{"issue":"2","key":"9636_CR7","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MRA.2010.936947","volume":"17","author":"S Calinon","year":"2010","unstructured":"Calinon, S., D\u2019halluin, F., Sauser, E. L., Caldwell, D. G., & Billard, A. G. (2010). Learning and reproduction of gestures by imitation. Robotics & Automation Magazine, IEEE, 17(2), 44\u201354.","journal-title":"Robotics & Automation Magazine, IEEE"},{"issue":"4","key":"9636_CR8","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/j.robot.2012.09.012","volume":"61","author":"S Calinon","year":"2013","unstructured":"Calinon, S., Kormushev, P., & Caldwell, D. G. (2013). Compliant skills acquisition and multi-optima policy search with EM-based reinforcement learning. Robotics and Autonomous Systems, 61(4), 369\u2013379.","journal-title":"Robotics and Autonomous Systems"},{"key":"9636_CR9","doi-asserted-by":"crossref","unstructured":"Daniel, C., Neumann, G., & Peters, J. (2012). Learning concurrent motor skills in versatile solution spaces. In Intelligent Robots and Systems (IROS), IEEE\/RSJ International Conference on 2012. IEEE, (pp. 3591\u20133597).","DOI":"10.1109\/IROS.2012.6386047"},{"key":"9636_CR10","doi-asserted-by":"crossref","unstructured":"Farshidian, F., Neunert, M., & Buchli, J. (2014). Learning of closed-loop motion control. In IEEE International Conference on Intelligent Robots and Systems, no. IROS (pp. 1441\u20131446).","DOI":"10.1109\/IROS.2014.6942746"},{"key":"9636_CR11","doi-asserted-by":"crossref","unstructured":"Garabini, M., Passaglia, A., Belo, F., Salaris, P., & Bicchi, A. (2012). Optimality principles in stiffness control: The VSA kick. In IEEE International Conference on Robotics and Automation (pp. 3341\u20133346).","DOI":"10.1109\/ICRA.2012.6225176"},{"issue":"1","key":"9636_CR12","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1177\/0278364910376251","volume":"30","author":"E Gribovskaya","year":"2010","unstructured":"Gribovskaya, E., Khansari-Zadeh, S. M., & Billard, A. (2010). Learning non-linear multivariate dynamics of motion in robotic manipulators. The International Journal of Robotics Research, 30(1), 80\u2013117.","journal-title":"The International Journal of Robotics Research"},{"issue":"13","key":"9636_CR13","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1163\/156855307782148550","volume":"21","author":"F Guenter","year":"2007","unstructured":"Guenter, F., Hersch, M., Calinon, S., & Billard, A. (2007). Reinforcement learning for imitating constrained reaching movements. Advanced Robotics, 21(13), 1521\u20131544.","journal-title":"Advanced Robotics"},{"issue":"1","key":"9636_CR14","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/37.257890","volume":"14","author":"V Gullapalli","year":"1994","unstructured":"Gullapalli, V., Franklin, J. A., & Benbrahim, H. (1994). Acquiring robot skills via reinforcement learning. Control Systems, IEEE, 14(1), 13\u201324.","journal-title":"Control Systems, IEEE"},{"issue":"12","key":"9636_CR15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1115\/1.3140702","volume":"107","author":"N Hogan","year":"1985","unstructured":"Hogan, N. (1985). Impedance control: An approach to manipulation. Journal of Dynamic Systems Measurement and Control, 107(12), 1\u201324.","journal-title":"Journal of Dynamic Systems Measurement and Control"},{"issue":"4","key":"9636_CR16","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1109\/TRO.2013.2256311","volume":"29","author":"M Howard","year":"2013","unstructured":"Howard, M., Braun, D. J., & Vijayakumar, S. (2013). Transferring human impedance behavior to heterogeneous variable impedance actuators. IEEE Transactions on Robotics, 29(4), 847\u2013862.","journal-title":"IEEE Transactions on Robotics"},{"key":"9636_CR17","doi-asserted-by":"crossref","unstructured":"Ijspeert, A.J., Nakanishi, J., & Schaal, S. (2002). Movement imitation with nonlinear dynamical systems in humanoid robots. In Proceedings of the 2002 IEEE International Conference on Robotics and Automation, IEEE (Vol.\u00a02, pp. 1398\u20131403).","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"9636_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TRO.2010.2090064","volume":"27","author":"SM Khansari-Zadeh","year":"2011","unstructured":"Khansari-Zadeh, S. M., & Billard, A. (2011). Learning stable non-linear dynamical systems with Gaussian Mixture Models. IEEE Transactions on Robotics, 27, 1\u201315.","journal-title":"IEEE Transactions on Robotics"},{"issue":"5","key":"9636_CR19","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1109\/TRO.2011.2159412","volume":"27","author":"SM Khansari-Zadeh","year":"2011","unstructured":"Khansari-Zadeh, S. M., & Billard, A. (2011). Learning stable nonlinear dynamical systems with gaussian mixture models. IEEE Transactions on Robotics, 27(5), 943\u2013957.","journal-title":"IEEE Transactions on Robotics"},{"key":"9636_CR20","doi-asserted-by":"crossref","unstructured":"Kober, J., & Peters, J. (2009). Learning motor primitives for robotics. In IEEE International Conference on Robotics and Automation, 2009, ICRA\u201909, IEEE (pp. 2112\u20132118).","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"9636_CR21","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J. A., & Peters, J. (2013). Reinforcement learning in robotics: A survey. The International Journal of Robotics Research, 32, 1238\u20131274.","journal-title":"The International Journal of Robotics Research"},{"issue":"1\u20132","key":"9636_CR22","first-page":"171","volume":"84","author":"J Kober","year":"2010","unstructured":"Kober, J., & Peters, J. (2010). Policy search for motor primitives in robotics. Machine Learning, 84(1\u20132), 171\u2013203.","journal-title":"Machine Learning"},{"issue":"2","key":"9636_CR23","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/MRA.2010.936952","volume":"17","author":"J Kober","year":"2010","unstructured":"Kober, J., & Peters, J. (2010). Imitation and reinforcement learning. IEEE Robotics Automation Magazine, 17(2), 55\u201362.","journal-title":"IEEE Robotics Automation Magazine"},{"key":"9636_CR24","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.robot.2015.03.010","volume":"70","author":"K Kronander","year":"2015","unstructured":"Kronander, K., Khansari-Zadeh, S. M., & Billard, A. (2015). Incremental motion learning with locally modulated dynamical systems. Robotics and Autonomous Systems, 70, 52\u201362.","journal-title":"Robotics and Autonomous Systems"},{"issue":"3","key":"9636_CR25","first-page":"1","volume":"7","author":"K Kronander","year":"2013","unstructured":"Kronander, K., & Billard, A. (2013). Learning compliant manipulation through kinesthetic and tactile human-robot interaction. Transactions on Haptics, 7(3), 1\u201316.","journal-title":"Transactions on Haptics"},{"issue":"1","key":"9636_CR26","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/LRA.2015.2509025","volume":"1","author":"K Kronander","year":"2016","unstructured":"Kronander, K., & Billard, A. (2016). Passive interaction control with dynamical systems. Robotics and Automation Letters, 1(1), 106\u2013113.","journal-title":"Robotics and Automation Letters"},{"key":"9636_CR27","doi-asserted-by":"crossref","unstructured":"Lee, A.\u00a0X., Lu, H., Gupta, A., Levine, S., & Abbeel, P. (2015). Learning force-based manipulation of deformable objects from multiple demonstrations. In IEEE International Conference on Robotics and Automation.","DOI":"10.1109\/ICRA.2015.7138997"},{"key":"9636_CR28","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neucom.2014.02.012","volume":"141","author":"A Lemme","year":"2014","unstructured":"Lemme, A., Neumann, K., Reinhart, R., & Steil, J. (2014). Neural learning of vector fields for encoding stable dynamical systems. Neurocomputing, 141, 3\u201314.","journal-title":"Neurocomputing"},{"key":"9636_CR29","doi-asserted-by":"crossref","unstructured":"Medina, J., Sieber, D., & Hirche, S. (2013). Risk-sensitive interaction control in uncertain manipulation tasks. In IEEE International Conference on Robotics and Automation.","DOI":"10.1109\/ICRA.2013.6630621"},{"issue":"5","key":"9636_CR30","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1177\/0278364910387653","volume":"30","author":"D Mitrovic","year":"2011","unstructured":"Mitrovic, D., Klanke, S., & Vijayakumar, S. (2011). Learning impedance control of antagonistic systems based on stochastic optimization principles. The International Journal of Robotics Research, 30(5), 556\u2013573.","journal-title":"The International Journal of Robotics Research"},{"key":"9636_CR31","unstructured":"Paraschos, A., Daniel, C., Peters, J., & Neumann, G. (2013). Probabilistic movement primitives. Neural Information Processing Systems (pp. 1\u20139)."},{"key":"9636_CR32","doi-asserted-by":"crossref","unstructured":"Pastor, P., Righetti, L., Kalakrishnan, M., & Schaal, S. (2011). Online movement adaptation based on previous sensor experiences. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2011. IEEE (pp. 365\u2013371).","DOI":"10.1109\/IROS.2011.6095059"},{"issue":"7\u20139","key":"9636_CR33","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1016\/j.neucom.2007.11.026","volume":"71","author":"J Peters","year":"2008","unstructured":"Peters, J., & Schaal, S. (2008). Natural actor-critic. Neurocomputing, 71(7\u20139), 1180\u20131190.","journal-title":"Neurocomputing"},{"key":"9636_CR34","doi-asserted-by":"crossref","unstructured":"Rozo, L., Calinon, S., Caldwell, D., Jimenez, P., Torras, C., & Jim\u00e9nez, P. (2013). Learning collaborative impedance-based robot behaviors. In AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v27i1.8543"},{"issue":"January","key":"9636_CR35","first-page":"1","volume":"6","author":"EA R\u00fcckert","year":"2013","unstructured":"R\u00fcckert, E. A., Neumann, G., Toussaint, M., & Maass, W. (2013). Learned graphical models for probabilistic planning provide a new class of movement primitives. Frontiers in Computational Neuroscience, 6(January), 1\u201320.","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"1431","key":"9636_CR36","doi-asserted-by":"crossref","first-page":"53747","DOI":"10.1098\/rstb.2002.1258","volume":"358","author":"S Schaal","year":"2003","unstructured":"Schaal, S., Ijspeert, A., & Billard, A. (2003). Computational approaches to motor learning by imitation. Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences, 358(1431), 53747.","journal-title":"Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences"},{"issue":"40","key":"9636_CR37","first-page":"1260616","volume":"29","author":"LPJ Selen","year":"2009","unstructured":"Selen, L. P. J., Franklin, D. W., & Wolpert, D. M. (2009). Impedance control reduces instability that arises from motor noise. The Journal of Neuroscience, 29(40), 1260616.","journal-title":"The Journal of Neuroscience"},{"key":"9636_CR38","unstructured":"Stulp, F., & Sigaud, O. (2012). Policy improvement methods: Between black-box optimization and episodic reinforcement learning."},{"key":"9636_CR39","unstructured":"Stulp, F., Sigaud, O. (2012). Path integral policy improvement with covariance matrix adaptation. In Proceedings of the 29th International Conference on Machine Learning (ICML-12) (pp. 281\u2013288)."},{"key":"9636_CR40","unstructured":"Sung, H.G. (2004). Gaussian mixture regression and classification (Ph.D. dissertation, Rice University)."},{"issue":"1","key":"9636_CR41","first-page":"1","volume":"9","author":"RS Sutton","year":"1998","unstructured":"Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning. Learning, 9(1), 1\u201323.","journal-title":"Learning"},{"key":"9636_CR42","doi-asserted-by":"crossref","unstructured":"Tedrake, R., Zhang, T.\u00a0W., & Seung, H.S. (2004). Stochastic policy gradient reinforcement learning on a simple 3d biped. In Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings of IEEE\/RSJ International Conference on 2004. IEEE (Vol.\u00a03, pp. 2849\u20132854).","DOI":"10.1109\/IROS.2004.1389841"},{"issue":"1","key":"9636_CR43","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s00422-009-0348-z","volume":"102","author":"KP Tee","year":"2010","unstructured":"Tee, K. P., Franklin, D. W., Kawato, M., Milner, T. E., Burdet, E., Peng, K., et al. (2010). Concurrent adaptation of force and impedance in the redundant muscle system. Biological Cybernetics, 102(1), 31\u201344.","journal-title":"Biological Cybernetics"},{"key":"9636_CR44","first-page":"3137","volume":"11","author":"E Theodorou","year":"2010","unstructured":"Theodorou, E., Buchli, J., & Schaal, S. (2010). A generalized path integral control approach to reinforcement learning. The Journal of Machine Learning Research, 11, 3137\u20133181.","journal-title":"The Journal of Machine Learning Research"},{"issue":"3","key":"9636_CR45","doi-asserted-by":"crossref","first-page":"032104","DOI":"10.1103\/PhysRevE.91.032104","volume":"91","author":"S Thijssen","year":"2015","unstructured":"Thijssen, S., & Kappen, H. (2015). Path integral control and state-dependent feedback. Physical Review E, 91(3), 032104.","journal-title":"Physical Review E"},{"issue":"9","key":"9636_CR46","first-page":"23","volume":"3","author":"M Toussaint","year":"2009","unstructured":"Toussaint, M. (2009). Probabilistic inference as a model of planned behavior. K\u00fcnstliche Intelligenz, 3(9), 23\u201329.","journal-title":"K\u00fcnstliche Intelligenz"},{"issue":"2","key":"9636_CR47","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/s10514-009-9132-0","volume":"27","author":"N Vlassis","year":"2009","unstructured":"Vlassis, N., Toussaint, M., Kontes, G., & Piperidis, S. (2009). Learning model-free robot control by a monte carlo EM algorithm. Autonomous Robots, 27(2), 123\u2013130.","journal-title":"Autonomous Robots"},{"issue":"5","key":"9636_CR48","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1109\/TRO.2011.2158251","volume":"27","author":"C Yang","year":"2011","unstructured":"Yang, C., Ganesh, G., Haddadin, S., Parusel, S., Albu-Schaffer, A., & Burdet, E. (2011). Human-like adaptation of force and impedance in stable and unstable interactions. IEEE Transactions on Robotics, 27(5), 918\u2013930.","journal-title":"IEEE Transactions on Robotics"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10514-017-9636-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-017-9636-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-017-9636-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T06:17:40Z","timestamp":1658989060000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10514-017-9636-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,4]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["9636"],"URL":"https:\/\/doi.org\/10.1007\/s10514-017-9636-y","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"type":"print","value":"0929-5593"},{"type":"electronic","value":"1573-7527"}],"subject":[],"published":{"date-parts":[[2017,5,4]]}}}