Energy Efficient and Battery SOC-aware Coordinated Control of Connected and Autonomous Electric Vehicles

A longitudinal control of autonomous electric vehicle platoons is proposed for improved energy efficiency and battery management. The proposed control scheme consists of two phases: the resequencing phase and the platooning phase. The introduction of the resequencing phase overcomes the issue that the leader vehicle’s battery charge diminishes excessively fast in the traditional platoon control schemes, where the platoon is fixed, thereby extending the driving distance per charge cycle. A Monte Carlo reinforcement learning approach is used to find the optimal sequence of all vehicles. The platooning control is realized by a multi-agent formation control algorithm.