GL-DEAR: Global Dynamic Drone Assisted Lane Change Maneuver for Risk Prevention and Collision Avoidance

This paper introduces a drone-assisted lane change platform based on a reinforcement learning agent, more specifically, DEAR (DEep Q-network with a dynAmic Reward). In order to achieve a satisfactory lane change performance, the reward function is designed from safety, comfort and efficiency perspectives. In particular, the weights of the three rewards are adjusted according to the surrounding traffic condition. On the other hand, the drones hovering over the highway provide global information (i.e. road vehicular density) to the ego vehicle. In addition, the drones also perform global control by 1) computing and sending a dynamic collision reward to the ego vehicle; 2) sending an Urgent Lane Change Request (ULCR) to the ego vehicle when a road risk ahead, or an emergency vehicle behind the ego vehicle is detected. The proposed lane change platform is tested with the authentic Next Generation Simulation (NGSIM) dataset. Simulation results prove that the platform is able to perform safe and efficient lane change on a road prone to risks and emergency vehicles.