Economic Adaptive Cruise Control for Electric Vehicles Based on Multi-step Tree Backtracking Algorithm in Q-Learning Framework

Car driving safety, comfort, energy economy and battery life extension are important factors for electric vehicles. To optimize these factors, this paper proposes an economic adaptive cruise control (Eco-ACC) strategy for electric vehicles based on multi-step tree backtracking algorithm in the Q-Learning framework. First, the vehicle’s longitudinal dynamics and energy storage models are established, and the control objectives are presented. Then, the control and state variables, reward and value functions are defined, and the Eco-ACC control strategy based on the multi-step tree backtracking algorithm is designed. Finally, simulations are performed, and compared with the benchmark algorithm, the proposed method achieves lower energy consumption and longer battery life.