PSO-Based Modified Control Barrier Function to Avoid Collision of Vehicle

An efficient and stable algorithm for vehicle path following and obstacle avoidance is proposed in this paper. Firstly, Particle Swarm Optimization (PSO) is used as the solver for the controller, combined with the modified Control Barrier Function (CBF), to propose the PSO-CBF controller. To ensure the safety of vehicle obstacle avoidance and solve the deadlock issue, we insert an additional local path planning layer after the global path planning, which enhances the stability of the controller. In addition, we optimize the initial state of the PSO solver, reduce the population size of PSO under the conditions of satisfying basic obstacle avoidance requirements and path following. This approach effectively improving the efficiency of the algorithm. Finally, the performance of the PSO-CBF controller is verified through simulation experiments.