Lane-Exchanging Driving Strategy for Autonomous Vehicle via Trajectory Prediction and Model Predictive Control

Abstract The cooperation between an autonomous vehicle and a nearby is critical to ensure driving safety in the lane-exchanging scenario. trajectory needs be predicted, from which controlled prevent possible collisions. This paper proposes strategy for cooperate with by integrating prediction motion control. A method developed anticipate trajectory. Gaussian mixture model (GMM), together kinematic model, are synthesized predict potential-field-based predictive control (MPC) approach utilized conduct maneuver. potential field of considered controller design collision avoidance. On-road data verification shows that can predicted proposed method. CarSim ® simulations validate perform maneuver avoid using strategy. thus safely vehicle.