Safety-Aware Preference-Based Learning for Safety-Critical Control
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
Text
Cosner et al. "Safety-Aware Preference-Based Learning for Safety-Critical Control." Proceedings of The 4th Annual Learning for Dynamics and Control Conference, 2022.Markdown
[Cosner et al. "Safety-Aware Preference-Based Learning for Safety-Critical Control." Proceedings of The 4th Annual Learning for Dynamics and Control Conference, 2022.](https://mlanthology.org/l4dc/2022/cosner2022l4dc-safetyaware/)BibTeX
@inproceedings{cosner2022l4dc-safetyaware,
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},
year = {2022},
pages = {1020-1033},
volume = {168},
url = {https://mlanthology.org/l4dc/2022/cosner2022l4dc-safetyaware/}
}