Ensuring Safety in Target Pursuit Control: A CBF-Safe Reinforcement Learning Approach

TL;DR

This paper introduces a CBF-safe reinforcement learning method for target pursuit that guarantees safety constraints like collision avoidance and sensing range, even with evasive targets and external disturbances.

Contribution

It develops a novel safety filter using input-constrained CBFs and a switch strategy, integrated into a CSRL algorithm with proven safety guarantees and improved pursuit performance.

Findings

Successfully maintains safety constraints in complex pursuit scenarios

Enhances control performance while ensuring collision avoidance

Proven to satisfy KKT conditions for all safety constraints

Abstract

This paper addresses the target-pursuit problem, aiming to ensure each pursuer's safety regarding collision avoidance, sensing range, and input saturation. An input-constrained CBF is proposed to dynamically regulate the pursuer's control, ensuring effective target pursuit even when the target performs evasive maneuvers. To further ensure safety, two sets of CBF constraints are designed to regulate the pursuer's position, enabling it to keep the target within the sensing range while avoiding collision in complex environments with external disturbances. These three CBFs collectively form our safety filter, which filters unsafe outputs from RL by solving a Quadratic Program (QP). Finally, the safety filter, combined with a switch strategy that enhances the feasibility of solving its QP, constitutes the Control Barrier Function (CBF)-Safe Reinforcement Learning (CSRL) algorithm, whose solutions are proven to satisfy the Karush-Kuhn-Tucker (KKT) conditions for all safety constraints. Simulation results validate the effectiveness of the CSRL algorithm, demonstrating its ability to handle complex pursuit scenarios while maintaining safety and improving control performance.