Safety-Aware Preference-Based Learning for Safety-Critical Control

Ryan Cosner, Maegan Tucker, Andrew Taylor, Kejun Li, Tamas Molnar, Wyatt Ubelacker, Anil Alan, Gabor Orosz, Yisong Yue, Aaron Ames
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:1020-1033, 2022.

Abstract

Bringing dynamic robots into the wild requires a tenuous balance between performance and safety. Yet controllers designed to provide robust safety guarantees often result in conservative behavior, and tuning these controllers to find the ideal trade-off between performance and safety typically requires domain expertise or a carefully constructed reward function. This work presents a design paradigm for systematically achieving behaviors that balance performance and robust safety by integrating safety-aware Preference-Based Learning (PBL) with Control Barrier Functions (CBFs). Fusing these concepts—safety-aware learning and safety-critical control—gives a robust means to achieve safe behaviors on complex robotic systems in practice. We demonstrate the capability of this design paradigm to achieve safe and performant perception-based autonomous operation of a quadrupedal robot both in simulation and experimentally on hardware.

Cite this Paper

BibTeX
@InProceedings{pmlr-v168-cosner22a, title = {Safety-Aware Preference-Based Learning for Safety-Critical Control}, author = {Cosner, Ryan and Tucker, Maegan and Taylor, Andrew and Li, Kejun and Molnar, Tamas and Ubelacker, Wyatt and Alan, Anil and Orosz, Gabor and Yue, Yisong and Ames, Aaron}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {1020--1033}, 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/cosner22a/cosner22a.pdf}, url = {https://proceedings.mlr.press/v168/cosner22a.html}, abstract = {Bringing dynamic robots into the wild requires a tenuous balance between performance and safety. Yet controllers designed to provide robust safety guarantees often result in conservative behavior, and tuning these controllers to find the ideal trade-off between performance and safety typically requires domain expertise or a carefully constructed reward function. This work presents a design paradigm for systematically achieving behaviors that balance performance and robust safety by integrating safety-aware Preference-Based Learning (PBL) with Control Barrier Functions (CBFs). Fusing these concepts—safety-aware learning and safety-critical control—gives a robust means to achieve safe behaviors on complex robotic systems in practice. We demonstrate the capability of this design paradigm to achieve safe and performant perception-based autonomous operation of a quadrupedal robot both in simulation and experimentally on hardware.} }
Endnote
%0 Conference Paper %T Safety-Aware Preference-Based Learning for Safety-Critical Control %A Ryan Cosner %A Maegan Tucker %A Andrew Taylor %A Kejun Li %A Tamas Molnar %A Wyatt Ubelacker %A Anil Alan %A Gabor Orosz %A Yisong Yue %A Aaron 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-cosner22a %I PMLR %P 1020--1033 %U https://proceedings.mlr.press/v168/cosner22a.html %V 168 %X Bringing dynamic robots into the wild requires a tenuous balance between performance and safety. Yet controllers designed to provide robust safety guarantees often result in conservative behavior, and tuning these controllers to find the ideal trade-off between performance and safety typically requires domain expertise or a carefully constructed reward function. This work presents a design paradigm for systematically achieving behaviors that balance performance and robust safety by integrating safety-aware Preference-Based Learning (PBL) with Control Barrier Functions (CBFs). Fusing these concepts—safety-aware learning and safety-critical control—gives a robust means to achieve safe behaviors on complex robotic systems in practice. We demonstrate the capability of this design paradigm to achieve safe and performant perception-based autonomous operation of a quadrupedal robot both in simulation and experimentally on hardware.
APA
Cosner, R., Tucker, M., Taylor, A., Li, K., Molnar, T., Ubelacker, W., Alan, A., Orosz, G., Yue, Y. & Ames, A.. (2022). Safety-Aware Preference-Based Learning for Safety-Critical Control. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:1020-1033 Available from https://proceedings.mlr.press/v168/cosner22a.html.

Related Material