Neural control for a semi-active suspension of a half-vehicle model

This paper presents a reinforcement learning algorithm using neural networks which allows a vehicle with semi-active suspension to improve continuously not only the ride comfort but also the tyre/ground contact. The proposed controller learns online, so that the system can adapt to changes produced in the environment. The neural controller has been studied using a half-vehicle model. Different road profiles have been tested to prove the robustness and reliability of the proposed semi-active suspension system. Simulation results show the effectiveness of our algorithm.