Neural Control Barrier Functions for Safe Navigation

TL;DR

This paper introduces a data-driven method to synthesize Control Barrier Functions for safe robot navigation in unknown environments, enabling reactive safety filtering without relying on environment maps or precise localization.

Contribution

It proposes a novel joint learning approach for CBFs and safe controllers inspired by SDRE, applicable in real-time on multirotor robots with LiDAR.

Findings

Successful simulation of the approach in unknown environments.

Real-world validation on a multirotor platform with LiDAR.

Effective safety filtering without environment maps or localization.

Abstract

Autonomous robot navigation can be particularly demanding, especially when the surrounding environment is not known and safety of the robot is crucial. This work relates to the synthesis of Control Barrier Functions (CBFs) through data for safe navigation in unknown environments. A novel methodology to jointly learn CBFs and corresponding safe controllers, in simulation, inspired by the State Dependent Riccati Equation (SDRE) is proposed. The CBF is used to obtain admissible commands from any nominal, possibly unsafe controller. An approach to apply the CBF inside a safety filter without the need for a consistent map or position estimate is developed. Subsequently, the resulting reactive safety filter is deployed on a multirotor platform integrating a LiDAR sensor both in simulation and real-world experiments.