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

TL;DR

This paper introduces a new safety-aware preference-based learning framework combined with control barrier functions to enable robots to operate safely and efficiently in complex, real-world environments, validated through simulations and hardware experiments.

Contribution

It presents a novel integration of safety-aware preference-based learning with control barrier functions for improved safety-critical control in robotics.

Findings

Successfully balanced safety and performance in quadrupedal robot operation

Demonstrated effectiveness in simulation and real hardware environments

Achieved robust safety guarantees with improved operational efficiency

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.