Title: Twin delayed deep deterministic reinforcement learning application in vehicle electrical suspension control

Authors: Daoyu Shen; Shilei Zhou; Nong Zhang

Addresses: School of Mechanical & Mechatronic Engineering, Faculty of Engineering and IT, University of Technology Sydney, 15 Broadway, Ultimo NSW, 2007, Australia ' School of Mechanical & Mechatronic Engineering, Faculty of Engineering and IT, University of Technology Sydney, 15 Broadway, Ultimo NSW, 2007, Australia ' Automotive Research Institute, Hefei University of Technology, 193 Tunxi Rd, Baohe District, Hefei, China

Abstract: Coming with the rising focus of the driving comfort request, more efforts are being delivered into the study of suspension system. Comparing with other traditional control methods, the machine learning control strategy has demonstrated its optimality in dealing with different class of roads. The work presented in this paper is to apply twin delayed deep deterministic policy gradients (TD3) in suspension control which enables suspension controller to go beyond searching for an optimal set of system parameters from traditional control method in dealing with different class of pavements. To achieve this, a suspension model has been established together with a reinforcement learning algorithm and an input signal of pavement. The performance of the twin delayed reinforcement agent is compared against deep deterministic policy gradients (DDPG) and deep Q-learning (DQN) algorithms under different types of pavement. The simulation result shows its superiority, robustness and learning efficiency over other reinforcement learning algorithms.

Keywords: vehicle vertical vibration; suspension system control; artificial intelligence; reinforcement learning; twin delayed deep deterministic policy (TD3); neural network design.

DOI: 10.1504/IJVP.2023.133852

International Journal of Vehicle Performance, 2023 Vol.9 No.4, pp.429 - 446

Received: 29 Jun 2022
Accepted: 04 Nov 2022
Published online: 04 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article