Learning a Better Control Barrier Function Under Uncertain Dynamics

TL;DR

This paper introduces a learning-based method to refine control barrier functions and system dynamics from conservative estimates, enabling safer control in safety-critical systems without extra environment interactions.

Contribution

It proposes a novel loss function and an episodic learning approach to simultaneously learn valid CBFs and system dynamics from conservative initial guesses.

Findings

Successfully learned valid CBFs for all tested systems

Accurately estimated system dynamics without additional environment interactions

Demonstrated improved safety control in simulations

Abstract

Using control barrier functions (CBFs) as safety filters provides a computationally inexpensive yet effective method for constructing controllers in safety-critical applications. However, using CBFs requires the construction of a valid CBF, which is well known to be a challenging task, and accurate system dynamics, which are often unavailable. This paper presents a learning-based approach to learn a valid CBF and the system dynamics starting from a conservative handcrafted CBF (HCBF) and the nominal system dynamics. We devise new loss functions that better suit the CBF refinement pipeline and are able to produce well-behaved CBFs with the usage of distance functions. By adopting an episodic learning approach, our proposed method is able to learn the system dynamics while not requiring additional interactions with the environment. Additionally, we provide a theoretical analysis of the quality of the learned system dynamics. We show that our proposed learning approach can effectively learn a valid CBF and an estimation of the actual system dynamics. The effectiveness of our proposed method is empirically demonstrated through simulation studies on three systems, a double integrator, a unicycle, and a two-link arm.