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

2026-03-06

AI Summary

This work addresses the challenge of safe autonomous navigation in dynamically uncertain environments, where designing traditional control barrier functions (CBFs) is notoriously difficult. To overcome this limitation, the authors propose a composite neural CBF framework that integrates Hamilton–Jacobi reachability analysis with a residual neural network architecture. The approach trains multiple sub-CBFs to approximate the optimal safe sets for individual moving obstacles and then fuses them into a unified composite CBF, guaranteeing disjointness between the safe and failure sets. Evaluated in both ground robot and quadrotor simulations, the method achieves up to an 18% higher task success rate compared to the best-performing baseline while maintaining strong safety guarantees. Its effectiveness, non-conservativeness, and high navigation success are further validated on real robotic hardware.

Technology Category

• Natural Language Processing: Safety and Robustness
• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• safe navigation
• dynamic environments
• control barrier functions
• autonomous robots
• obstacle avoidance

Innovation

• Composite Neural CBF
• Hamilton-Jacobi reachability
• safe robot navigation
• residual neural architecture
• dynamic environments