Improvement of Vehicle Stability Using Reinforcement Learning

Abstract

This paper presents a preliminary study on the use of reinforcement learning to control the torque vectoring of a small rear wheel driven electric race car in order to improve vehicle handling and vehicle stability. The reinforcement learning algorithm used is Neural Fitted Q Iteration and the sampling of experiences is based on simulations of the vehicle behavior using the software CarMaker. The cost function is based on the position of the states on the phase-plane of sideslip angle and sideslip angular velocity. The resulting controller is able to improve the vehicle handling and stability with a significant reduction in vehicle sideslip angle.

Actor-Critic Traction Control Based on Reinforcement Learning with Open-Loop Training

“…However, the real-time implementation of these algorithms is limited due to the iterative effort necessary to find the action which corresponds to the maximum value function. One example of this limitation is the research of de Amaral et al [16] which implemented an electronic stability control (ESC) strategy based on an RL algorithm. The author uses the IPG CarMaker virtual environment to generate the dataset and testing; however, the implemented algorithm, which finds the higher reward and consequently the better action, presents runtime limitations.…”