A Caltech Library Service

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

Cosner, Ryan K. and Tucker, Maegan and Taylor, Andrew J. and Li, Kejun and Molnár, Tamás G. and Ubellacker, Wyatt and Alan, Anil and Orosz, Gábor and Yue, Yisong and Ames, Aaron D. (2021) Safety-Aware Preference-Based Learning for Safety-Critical Control. . (Unpublished)

[img] PDF - Submitted Version
Creative Commons Attribution.


Use this Persistent URL to link to this item:


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.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Cosner, Ryan K.0000-0002-4035-1425
Tucker, Maegan0000-0001-7363-6809
Taylor, Andrew J.0000-0002-5990-590X
Molnár, Tamás G.0000-0002-9379-7121
Ubellacker, Wyatt0000-0002-4732-6185
Alan, Anil0000-0002-9778-8249
Orosz, Gábor0000-0002-9000-3736
Yue, Yisong0000-0001-9127-1989
Ames, Aaron D.0000-0003-0848-3177
Additional Information:© 2022 R.K. Cosner, M. Tucker, A.J. Taylor, K. Li, T.G. Molnar, W. Ubellacker, A. Alan, G. Orosz, Y. Yue & A.D. Ames. Attribution 4.0 International (CC BY 4.0).
Subject Keywords:Preference-Based Learning, Control Barrier Functions, Safety-Critical Control, Robotics
Record Number:CaltechAUTHORS:20220224-200843937
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:113589
Deposited By: George Porter
Deposited On:28 Feb 2022 17:30
Last Modified:28 Feb 2022 17:30

Repository Staff Only: item control page