{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:29:35Z","timestamp":1780586975100,"version":"3.54.1"},"reference-count":46,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:00:00Z","timestamp":1643241600000},"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":[[2022,3]]},"abstract":"<jats:p>State-dependent dynamical systems (DSs) offer adaptivity, reactivity, and robustness to perturbations in motion planning and physical human\u2013robot interaction tasks. Learning DS-based motion plans from non-linear reference trajectories is an active research area in robotics. Most approaches focus on learning DSs that can (i) accurately mimic the demonstrated motion, while (ii) ensuring convergence to the target, i.e., they are globally asymptotically (or exponentially) stable. When subject to perturbations, a compliant robot guided with a DS will continue following the next integral curves of the DS towards the target. If the task requires the robot to track a specific reference trajectory, this approach will fail. To alleviate this shortcoming, we propose the locally active globally stable DS (LAGS-DS), a novel DS formulation that provides both global convergence and stiffness-like symmetric attraction behaviors around a reference trajectory in regions of the state space where trajectory tracking is important. This allows for a unified approach towards motion and impedance encoding in a single DS-based motion model, i.e., stiffness is embedded in the DS. To learn LAGS-DS from demonstrations we propose a learning strategy based on Bayesian non-parametric Gaussian mixture models, Gaussian processes, and a sequence of constrained optimization problems that ensure estimation of stable DS parameters via Lyapunov theory. We experimentally validated LAGS-DS on writing tasks with a KUKA LWR 4+ arm and on navigation and co-manipulation tasks with iCub humanoid robots.<\/jats:p>","DOI":"10.1177\/02783649211030952","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T03:51:48Z","timestamp":1643255508000},"page":"312-347","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":31,"title":["Locally active globally stable dynamical systems: Theory, learning, and experiments"],"prefix":"10.1177","volume":"41","author":[{"given":"Nadia","family":"Figueroa","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Computer Science and Artificial Intelligence Lab (CSAIL), Cambridge, MA, USA"},{"name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Learning Algorithms and Systems Laboratory (LASA), Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aude","family":"Billard","sequence":"additional","affiliation":[{"name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Learning Algorithms and Systems Laboratory (LASA), Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2022,1,27]]},"reference":[{"key":"e_1_3_5_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.07.008"},{"key":"e_1_3_5_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(95)00038-X"},{"key":"e_1_3_5_4_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492904000212"},{"key":"e_1_3_5_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.08.030"},{"key":"e_1_3_5_6_1","first-page":"124","article-title":"Learning stable dynamical systems using contraction theory","author":"Blocher C","year":"2017","unstructured":"Blocher C, Saveriano M, Lee D (2017) Learning stable dynamical systems using contraction theory. In: 2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pp. 124\u2013129.","journal-title":"2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)"},{"key":"e_1_3_5_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011379"},{"key":"e_1_3_5_8_1","volume-title":"Numerical Optimization \u2013 Theoretical and Practical Aspects","author":"Bonnans J","year":"2006","unstructured":"Bonnans J, Gilbert J, Lemar\u00e9chal C, Sagastiz\u00e1bal C (2006) Numerical Optimization \u2013 Theoretical and Practical Aspects. Universitext. Berlin: Springer Verlag."},{"key":"e_1_3_5_9_1","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1969-0255573-1"},{"key":"e_1_3_5_10_1","unstructured":"Faraji S M\u00fcllhaupt P Ijspeert A (2018) Imprecise dynamic walking with time-projection control. Available at: http:\/\/infoscience.epfl.ch\/record\/260430."},{"key":"e_1_3_5_11_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919835606."},{"key":"e_1_3_5_12_1","article-title":"PENLAB: A MATLAB solver for nonlinear semidefinite optimization","author":"Fiala J","year":"2013","unstructured":"Fiala J, Ko\u010dvara M, Stingl M (2013) PENLAB: A MATLAB solver for nonlinear semidefinite optimization. ArXiv e-prints.","journal-title":"ArXiv e-prints"},{"key":"e_1_3_5_13_1","article-title":"Learning complex manipulation tasks from heterogeneous and unstructured demonstrations","author":"Figueroa N","year":"2017","unstructured":"Figueroa N, Billard A (2017) Learning complex manipulation tasks from heterogeneous and unstructured demonstrations. In: Proceedings of Workshop on Synergies between Learning and Interaction, IEEE\/RSJ International Conference on Intelligent Robots and Systems.","journal-title":"Proceedings of Workshop on Synergies between Learning and Interaction, IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"e_1_3_5_14_1","first-page":"927","article-title":"A physically-consistent bayesian non-parametric mixture model for dynamical system learning","volume":"87","author":"Figueroa N","year":"2018","unstructured":"Figueroa N, Billard A (2018) A physically-consistent bayesian non-parametric mixture model for dynamical system learning. Proceedings of Machine Learning Research 87: 927\u2013946.","journal-title":"Proceedings of Machine Learning Research"},{"key":"e_1_3_5_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451881"},{"key":"e_1_3_5_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910376251"},{"key":"e_1_3_5_17_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"e_1_3_5_18_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1984.4788393"},{"key":"e_1_3_5_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2893676."},{"key":"e_1_3_5_20_1","first-page":"874","article-title":"Real-time path planning using harmonic potentials in dynamic environment","author":"Jacob H","year":"1997","unstructured":"Jacob H, Feder S, Slotine JE (1997) Real-time path planning using harmonic potentials in dynamic environment. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 874\u2013881.","journal-title":"Proceedings of the IEEE International Conference on Robotics and Automation"},{"key":"e_1_3_5_21_1","volume-title":"Nonlinear Systems","author":"Khalil H","year":"2002","unstructured":"Khalil H (2002) Nonlinear Systems. Englewood Cliffs, NJ: Prentice Hall."},{"key":"e_1_3_5_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"e_1_3_5_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9287-y"},{"key":"e_1_3_5_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.03.001"},{"key":"e_1_3_5_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"e_1_3_5_26_1","article-title":"A dynamical system approach to task-adaptation in physical human\u2013robot interaction","author":"Khoramshahi M","year":"2018","unstructured":"Khoramshahi M, Billard A (2018) A dynamical system approach to task-adaptation in physical human\u2013robot interaction. Autonomous Robots, in press.","journal-title":"Autonomous Robots"},{"key":"e_1_3_5_27_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"e_1_3_5_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509025"},{"key":"e_1_3_5_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.03.010"},{"key":"e_1_3_5_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094402"},{"key":"e_1_3_5_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.02.012"},{"key":"e_1_3_5_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08338-4_115"},{"key":"e_1_3_5_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CACSD.2004.1393890"},{"key":"e_1_3_5_34_1","first-page":"175","volume-title":"Proceedings 1st Annual Conference on Robot Learning (CoRL 2017)","author":"Medina JR","year":"2017","unstructured":"Medina JR, Billard A (2017) Learning stable task sequences from demonstration with linear parameter varying systems and hidden Markov models. In: Proceedings 1st Annual Conference on Robot Learning (CoRL 2017), Mountain View, CA, 13\u201315 November 2017, pp. 175\u2013184."},{"key":"e_1_3_5_35_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.019."},{"key":"e_1_3_5_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2536749"},{"key":"e_1_3_5_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696505"},{"key":"e_1_3_5_38_1","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1142\/S021848851340014X","article-title":"Reliable integration of continuous constraints into extreme learning machines","volume":"21","author":"Neumann K","year":"2013","unstructured":"Neumann K, Rolf M, Steil JJ (2013b) Reliable integration of continuous constraints into extreme learning machines. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 21(Suppl. 2): 35\u201350.","journal-title":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems"},{"key":"e_1_3_5_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.04.006"},{"key":"e_1_3_5_40_1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.sysconle.2016.06.018","article-title":"Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems","volume":"96","author":"Perrin N","year":"2016","unstructured":"Perrin N, Schlehuber-Caissier P (2016) Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems. Systems and Control Letters 96(Suppl. C): 51\u201359.","journal-title":"Systems and Control Letters"},{"key":"e_1_3_5_41_1","first-page":"369","article-title":"Learning partially contracting dynamical systems from demonstrations","volume":"78","author":"Ravichandar H","year":"2017","unstructured":"Ravichandar H, Salehi I, Dani A (2017) Learning partially contracting dynamical systems from demonstrations. Proceedings of Machine Learning Research 78: 369\u2013378.","journal-title":"Proceedings of Machine Learning Research"},{"key":"e_1_3_5_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/70.163777"},{"key":"e_1_3_5_43_1","doi-asserted-by":"publisher","DOI":"10.1561\/2300000065"},{"key":"e_1_3_5_44_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.4.753"},{"key":"e_1_3_5_45_1","first-page":"1025","article-title":"Augmented-SVM: Automatic space partitioning for combining multiple non-linear dynamics","volume":"25","author":"Shukla A","year":"2012","unstructured":"Shukla A, Billard A (2012) Augmented-SVM: Automatic space partitioning for combining multiple non-linear dynamics. Advances in Neural Information Processing Systems 25: 1025\u20131033.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_5_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206248"},{"key":"e_1_3_5_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649211030952","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649211030952","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649211030952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:16:53Z","timestamp":1777457813000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649211030952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,27]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["10.1177\/02783649211030952"],"URL":"https:\/\/doi.org\/10.1177\/02783649211030952","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,27]]}}}