Comparative Study of Cooperative Platoon Merging Control Based on Reinforcement Learning

Abstract

The time that a vehicle merges in a lane reduction can significantly affect passengers’ safety, comfort, and energy consumption, which can, in turn, affect the global adoption of autonomous electric vehicles. In this regard, this paper analyzes how connected and automated vehicles should cooperatively drive to reduce energy consumption and improve traffic flow. Specifically, a model-free deep reinforcement learning approach is used to find the optimal driving behavior in the scenario in which two platoons are merging into one. Several metrics are analyzed, including the time of the merge, energy consumption, and jerk, etc. Numerical simulation results show that the proposed framework can reduce the energy consumed by up to 76.7%, and the average jerk can be decreased by up to 50%, all by only changing the cooperative merge behavior. The present findings are essential since reducing the jerk can decrease the longitudinal acceleration oscillations, enhance comfort and drivability, and improve the general acceptance of autonomous vehicle platooning as a new technology.

Lane-Changing Tracking Control of Automated Vehicle Platoon Based on MA-DDPG and Adaptive MPC

“…However, the literature applies the DDPG algorithm to solve the platoon cooperative control problem with a single agent, and the reward value curves of training fluctuate a lot, and the effect is more general. [47] and [48] point out that the PPO algorithm can be used to achieve cooperative control of vehicles under the platoon merging operation in the mixed traffic environment of urban road intersections and a set of PPO hyperparameters is proposed to explore the effect of the automated extraction feature on policy prediction. However, it is unclear how the PPO algorithm controls vehicle speed, acceleration, and other motion states.…”

“…The first element of the control sequence is entered into the control system as an actual control quantity as follows: (48) After the end of the current control cycle, it proceeds to the next one, where the loop iterates and achieves the tracking of the desired lane-changing trajectory.…”