Learning for Safety-Critical Control with Control Barrier Functions

Andrew Taylor, Andrew Singletary, Yisong Yue, Aaron Ames
Proceedings of the 2nd Conference on Learning for Dynamics and Control, PMLR 120:708-717, 2020.

Abstract

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

Cite this Paper

BibTeX
@InProceedings{pmlr-v120-taylor20a, title = {Learning for Safety-Critical Control with Control Barrier Functions}, author = {Taylor, Andrew and Singletary, Andrew and Yue, Yisong and Ames, Aaron}, booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control}, pages = {708--717}, year = {2020}, editor = {Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie}, volume = {120}, series = {Proceedings of Machine Learning Research}, month = {10--11 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v120/taylor20a/taylor20a.pdf}, url = {https://proceedings.mlr.press/v120/taylor20a.html}, abstract = {Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.} }
Endnote
%0 Conference Paper %T Learning for Safety-Critical Control with Control Barrier Functions %A Andrew Taylor %A Andrew Singletary %A Yisong Yue %A Aaron Ames %B Proceedings of the 2nd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2020 %E Alexandre M. Bayen %E Ali Jadbabaie %E George Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire Tomlin %E Melanie Zeilinger %F pmlr-v120-taylor20a %I PMLR %P 708--717 %U https://proceedings.mlr.press/v120/taylor20a.html %V 120 %X Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.
APA
Taylor, A., Singletary, A., Yue, Y. & Ames, A.. (2020). Learning for Safety-Critical Control with Control Barrier Functions. Proceedings of the 2nd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 120:708-717 Available from https://proceedings.mlr.press/v120/taylor20a.html.

Related Material