Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies

Ivan Dario Jimenez Rodriguez, Noel Csomay-Shanklin, Yisong Yue, Aaron D. Ames
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:1060-1072, 2022.

Abstract

This work presents Neural Gaits, a method for learning dynamic walking gaits through the enforcement of set invariance that can be refined episodically using experimental data from the robot. We first frame walking as a set invariance problem enforceable via control barrier functions (CBFs) defined on the reduced-order dynamics quantifying the underactuated component of the robot: the zero dynamics. Our approach contains two learning modules: one for learning a policy that satisfies the CBF condition, and another for learning a residual dynamics model to refine imperfections of the nominal model. Importantly, learning only over the zero dynamics significantly reduces the dimensionality of the learning problem while using CBFs allows us to still make guarantees for the full-order system. Finally, the applicability of the method is demonstrated experimentally on an underactuated bipedal robot, where we are able to show agile and dynamic locomotion, even with partially unknown dynamics.

Cite this Paper

BibTeX
@InProceedings{pmlr-v168-rodriguez22a, title = {Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies}, author = {Rodriguez, Ivan Dario Jimenez and Csomay-Shanklin, Noel and Yue, Yisong and Ames, Aaron D.}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {1060--1072}, year = {2022}, editor = {Firoozi, Roya and Mehr, Negar and Yel, Esen and Antonova, Rika and Bohg, Jeannette and Schwager, Mac and Kochenderfer, Mykel}, volume = {168}, series = {Proceedings of Machine Learning Research}, month = {23--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v168/rodriguez22a/rodriguez22a.pdf}, url = {https://proceedings.mlr.press/v168/rodriguez22a.html}, abstract = {This work presents Neural Gaits, a method for learning dynamic walking gaits through the enforcement of set invariance that can be refined episodically using experimental data from the robot. We first frame walking as a set invariance problem enforceable via control barrier functions (CBFs) defined on the reduced-order dynamics quantifying the underactuated component of the robot: the zero dynamics. Our approach contains two learning modules: one for learning a policy that satisfies the CBF condition, and another for learning a residual dynamics model to refine imperfections of the nominal model. Importantly, learning only over the zero dynamics significantly reduces the dimensionality of the learning problem while using CBFs allows us to still make guarantees for the full-order system. Finally, the applicability of the method is demonstrated experimentally on an underactuated bipedal robot, where we are able to show agile and dynamic locomotion, even with partially unknown dynamics.} }
Endnote
%0 Conference Paper %T Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies %A Ivan Dario Jimenez Rodriguez %A Noel Csomay-Shanklin %A Yisong Yue %A Aaron D. Ames %B Proceedings of The 4th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2022 %E Roya Firoozi %E Negar Mehr %E Esen Yel %E Rika Antonova %E Jeannette Bohg %E Mac Schwager %E Mykel Kochenderfer %F pmlr-v168-rodriguez22a %I PMLR %P 1060--1072 %U https://proceedings.mlr.press/v168/rodriguez22a.html %V 168 %X This work presents Neural Gaits, a method for learning dynamic walking gaits through the enforcement of set invariance that can be refined episodically using experimental data from the robot. We first frame walking as a set invariance problem enforceable via control barrier functions (CBFs) defined on the reduced-order dynamics quantifying the underactuated component of the robot: the zero dynamics. Our approach contains two learning modules: one for learning a policy that satisfies the CBF condition, and another for learning a residual dynamics model to refine imperfections of the nominal model. Importantly, learning only over the zero dynamics significantly reduces the dimensionality of the learning problem while using CBFs allows us to still make guarantees for the full-order system. Finally, the applicability of the method is demonstrated experimentally on an underactuated bipedal robot, where we are able to show agile and dynamic locomotion, even with partially unknown dynamics.
APA
Rodriguez, I.D.J., Csomay-Shanklin, N., Yue, Y. & Ames, A.D.. (2022). Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:1060-1072 Available from https://proceedings.mlr.press/v168/rodriguez22a.html.

Related Material