Lane-Associated MPC Path Planning for Autonomous Vehicles

As a typical module for autonomous vehicles, local path planning has received a lot of attention in recent years. This paper presents a novel lane-associated method, combining model predictive control (MPC) with artificial potential field (APF), in which way we take the decision-making process into account. The time-varying safety constraints are treated as the scope of the repulsive force. By doing so, it is easy to reduce the number of constraints in optimization. By taking the potential field function into the cost function, the local path planning problem can be formulated as a typical MPC optimization one. The particle swarm optimization (PSO) strategy is utilized to compute the optimal path. Simulations are presented to verify the validity of the proposed algorithm. The results illustrate that the designed method achieves satisfactory performance in different scenarios.