Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization

TL;DR

This paper introduces a magnitude regularization technique to synthesize more efficient safety certificates for learning-based control, reducing conservativeness while maintaining safety guarantees.

Contribution

It proposes the SafeMR algorithm that uses reinforcement learning to synthesize less conservative energy functions for safe control.

Findings

Reduces conservativeness of energy functions

Improves controller efficiency

Maintains safety guarantees

Abstract

Energy-function-based safety certificates can provide provable safety guarantees for the safe control tasks of complex robotic systems. However, all recent studies about learning-based energy function synthesis only consider the feasibility, which might cause over-conservativeness and result in less efficient controllers. In this work, we proposed the magnitude regularization technique to improve the efficiency of safe controllers by reducing the conservativeness inside the energy function while keeping the promising provable safety guarantees. Specifically, we quantify the conservativeness by the magnitude of the energy function, and we reduce the conservativeness by adding a magnitude regularization term to the synthesis loss. We propose the SafeMR algorithm that uses reinforcement learning (RL) for the synthesis to unify the learning processes of safe controllers and energy functions. Experimental results show that the proposed method does reduce the conservativeness of the energy functions and outperforms the baselines in terms of the controller efficiency while guaranteeing safety.