Adaptive Cruise Control for Autonomous Electric Vehicles based on Q-learning algorithm

This work presents an ACC-like longitudinal controller for an autonomous electric vehicle, named Ego-Vehicle, based on a Deep Deterministic Reinforcement Learning algorithm. More specifically, the designed algorithm exploits the use of the Deep Deterministic Policy Gradient (DDPG) agent and the reward function explicitly takes into account both the speed and position error of the Ego-Vehicle w.r.t. the preceding one. After properly training the DDPG agent, the control ACC-like strategy is validated considering a realistic driving cycle for the preceding vehicle. Numerical results confirm the effectiveness of the designed strategy.