CN-CBF: Composite Neural Control Barrier Function for Safe Robot Navigation in Dynamic Environments

TL;DR

This paper introduces a neural composite control barrier function method for safe robot navigation in dynamic environments, combining multiple neural CBFs trained via Hamilton-Jacobi reachability to improve safety and success rates.

Contribution

It proposes a novel composite neural CBF approach that effectively integrates multiple neural CBFs with residual architecture, enhancing safety guarantees in dynamic robot navigation.

Findings

Achieved up to 18% higher success rates in simulations.

Demonstrated effectiveness in hardware experiments.

Improved safety without increased conservativeness.

Abstract

Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments. One of the prevalent approaches is safety filtering based on control barrier functions (CBFs), which are easy to deploy but difficult to design. Motivated by the shortcomings of existing learning- and model-based methods, we propose a simple yet effective neural CBF design method for safe robot navigation in dynamic environments. We employ the idea of a composite CBF, where multiple neural CBFs are combined into a single CBF. The individual CBFs are trained via the Hamilton-Jacobi reachability framework to approximate the optimal safe set for single moving obstacles. Additionally, we use the residual neural architecture, which guarantees that the estimated safe set does not intersect with the corresponding failure set. The method is extensively evaluated in simulation experiments for a ground robot and a quadrotor, comparing it against several baseline methods. The results show improved success rates of up to 18\% compared to the best baseline, without increasing the conservativeness of the motion. Also, the method is demonstrated in hardware experiments for both types of robots.