Safety-Aware Preference-Based Learning for Safety-Critical Control
This work addresses the problem of conservative behavior in safety-critical control for robotic systems, offering a systematic design paradigm to improve trade-offs without requiring domain expertise.
The paper tackles the challenge of balancing performance and safety in dynamic robots by integrating safety-aware Preference-Based Learning with Control Barrier Functions, demonstrating safe and performant perception-based autonomous operation of a quadrupedal robot in simulation and on hardware.
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.