Learning Partially Contracting Dynamical Systems from Demonstrations

Harish Ravichandar, Iman Salehi, Ashwin Dani
; Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:369-378, 2017.

Abstract

An algorithm for learning the dynamics of point-to-point motions from demonstrations using an autonomous nonlinear dynamical system, named contracting dynamical system primitives (CDSP), is presented. The motion dynamics are approximated using a Gaussian mixture model (GMM) and its parameters are learned subject to constraints derived from partial contraction analysis. Systems learned using the proposed method generate trajectories that accurately reproduce the demonstrations and are guaranteed to converge to a desired goal location. Additionally, the learned models are capable of quickly and appropriately adapting to unexpected spatial perturbations and changes in goal location during reproductions. The CDSP algorithm is evaluated on shapes from a publicly available human handwriting dataset and also compared with two state-of-the-art motion generation algorithms. Furthermore, the CDSP algorithm is also shown to be capable of learning and reproducing point-to-point motions directly from real-world demonstrations using a Baxter robot.

Cite this Paper


BibTeX
@InProceedings{pmlr-v78-ravichandar17a, title = {Learning Partially Contracting Dynamical Systems from Demonstrations}, author = {Harish Ravichandar and Iman Salehi and Ashwin Dani}, booktitle = {Proceedings of the 1st Annual Conference on Robot Learning}, pages = {369--378}, year = {2017}, editor = {Sergey Levine and Vincent Vanhoucke and Ken Goldberg}, volume = {78}, series = {Proceedings of Machine Learning Research}, month = {13--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v78/ravichandar17a/ravichandar17a.pdf}, url = {http://proceedings.mlr.press/v78/ravichandar17a.html}, abstract = {An algorithm for learning the dynamics of point-to-point motions from demonstrations using an autonomous nonlinear dynamical system, named contracting dynamical system primitives (CDSP), is presented. The motion dynamics are approximated using a Gaussian mixture model (GMM) and its parameters are learned subject to constraints derived from partial contraction analysis. Systems learned using the proposed method generate trajectories that accurately reproduce the demonstrations and are guaranteed to converge to a desired goal location. Additionally, the learned models are capable of quickly and appropriately adapting to unexpected spatial perturbations and changes in goal location during reproductions. The CDSP algorithm is evaluated on shapes from a publicly available human handwriting dataset and also compared with two state-of-the-art motion generation algorithms. Furthermore, the CDSP algorithm is also shown to be capable of learning and reproducing point-to-point motions directly from real-world demonstrations using a Baxter robot.} }
Endnote
%0 Conference Paper %T Learning Partially Contracting Dynamical Systems from Demonstrations %A Harish Ravichandar %A Iman Salehi %A Ashwin Dani %B Proceedings of the 1st Annual Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2017 %E Sergey Levine %E Vincent Vanhoucke %E Ken Goldberg %F pmlr-v78-ravichandar17a %I PMLR %J Proceedings of Machine Learning Research %P 369--378 %U http://proceedings.mlr.press %V 78 %W PMLR %X An algorithm for learning the dynamics of point-to-point motions from demonstrations using an autonomous nonlinear dynamical system, named contracting dynamical system primitives (CDSP), is presented. The motion dynamics are approximated using a Gaussian mixture model (GMM) and its parameters are learned subject to constraints derived from partial contraction analysis. Systems learned using the proposed method generate trajectories that accurately reproduce the demonstrations and are guaranteed to converge to a desired goal location. Additionally, the learned models are capable of quickly and appropriately adapting to unexpected spatial perturbations and changes in goal location during reproductions. The CDSP algorithm is evaluated on shapes from a publicly available human handwriting dataset and also compared with two state-of-the-art motion generation algorithms. Furthermore, the CDSP algorithm is also shown to be capable of learning and reproducing point-to-point motions directly from real-world demonstrations using a Baxter robot.
APA
Ravichandar, H., Salehi, I. & Dani, A.. (2017). Learning Partially Contracting Dynamical Systems from Demonstrations. Proceedings of the 1st Annual Conference on Robot Learning, in PMLR 78:369-378

Related Material