Learning-Based Vibration Control of Vehicle Active Suspension

Abstract

Vehicle active suspension systems provide possibility to bring better ride comfort, handling stability and driving safety with proper control than passive suspension. This paper utilizes deep reinforcement learning method to develop active suspension systems due to its good generalization. The controller is based on a quarter-car active suspension model, and suspension dynamic characteristics are analyzed under the condition of bump disturbance. Simulation results show that the performance of active suspension tends to be stable after proper training. Compared with the passive suspension and the Skyhook-based suspension, the deep reinforcement learning-based active suspension can reduce the vehicle body acceleration more effectively and further improve the ride comfort without sacrificing the suspension deflection and dynamic tire load. Deep reinforcement learning-based active suspension can still maintain good performance after switching bump heights or vehicle speed which verifies good generalization of the controller.