Collaborative adaptive cruise control and energy management strategy for extended-range electric logistics van platoon

Abstract

This paper improves the economy of the extended-range electric logistics van (ERELV) platoon from two aspects of cooperative adaptive cruise control (CACC) and energy management strategy (EMS). Based on the vehicle-to-everything (V2X) communication, to improve the economy of heterogeneous vehicle platoon CACC system, a distributed model predictive controller (DMPC) with stability, comfort, and the economy as optimization goals are designed. The sufficient conditions for the asymptotic stability of the vehicle platoon closed-loop system are obtained by Lyapunov stability analysis. The multi-agent deep reinforcement learning (MADRL) algorithm is used to solve the EMS of the ERELV platoon. Under the framework of centralized training distributed execution (CTDE), the experience of all agents can be obtained during training, and the actions can be output only according to their local observation states during execution. The simulation results show that the designed ecological cooperative adaptive cruise control (Eco-CACC) effectively balances the stability and economy of a heterogeneous vehicle platoon. Taking dynamic programming (DP) as the benchmark, compared with the single-agent algorithm, EMS based on a multi-agent deep deterministic strategy gradient (MADDPG) algorithm can achieve a near-optimal solution while significantly improving the learning efficiency.