Reinforcement Learning-Based Co-Optimization of Adaptive Cruise Speed Control and Energy Management for Fuel Cell Vehicles

With the development of intelligent autodriving vehicles, the co-optimization of speed control and energy management under the insurance of safe and comfortable driving has become a vital issue. Herein, the adaptive cruise control scenario is discussed. A co-optimization method for speed control and energy management for fuel cell vehicles is suggested to delay the degradation of energy sources while preserving fuel cell efficiency. A reward function based on a reinforcement learning (RL) algorithm is developed to optimize the safety coefficient, comfortability, car-following efficiency, and economy at the speed control level. The RL agent learns to control vehicle speed while avoiding collisions and maximizing the cumulative rewards. To handle the problem of energy management, an adaptive equivalent consumption minimization strategy, which takes into account the deterioration of energy sources, is implemented at the energy management level. The results indicate that the suggested method reduces the demand power by 1.7%, increases the lifetime of power sources, and reduces equivalent hydrogen consumption by 9.4% compared to the model predictive control.