Title: Heavy-duty vehicle longitudinal automation with hydraulic retarder via H infinity control and off-policy reinforcement learning

Authors: Chaoxian Wu; Xuexun Guo; Bo Yang; Xiaofei Pei; Zhenfu Chen

Addresses: Hubei Key Laboratory of Advanced Technology for Automotive Components, Automobile Engineering Institute, Wuhan University of Technology, Wuhan, 430000, China ' Hubei Collaborative Innovation Center for Automotive Components Technology, Wuhan University of Technology, Wuhan, 430000, China ' Hubei Key Laboratory of Advanced Technology for Automotive Components, Automobile Engineering Institute, Wuhan University of Technology, Wuhan, 430000, China ' Hubei Collaborative Innovation Center for Automotive Components Technology, Wuhan University of Technology, Wuhan, 430000, China ' Hubei Collaborative Innovation Center for Automotive Components Technology, Wuhan University of Technology, Wuhan, 430000, China

Abstract: A novel hierarchical heavy-duty vehicle (HDV) longitudinal control strategy with a hydraulic retarder is proposed in this paper to achieve the HDV down-hill longitudinal automation in the deceleration process. The upper level controller generates the optimal desired retarder torque through the H infinity control and the off-policy reinforcement learning (RL), in which the H infinity control is able to attenuate those disturbances and the off-policy RL can solve the H infinity control with completely unknown system dynamics. Then, according to the optimal desired retarder torque, the lower level controller can calculate the desired control pressure for the retarder to control the HDV. The effectiveness of this HDV longitudinal control strategy is verified by simulations based on an experimentally verified retarder model. Compared to the sliding-mode-control (SMC) based controller, the simulation result shows the proposed control strategy has better capability to attenuate the disturbances and guarantee the longitudinal speed tracking performance.

Keywords: HDV; heavy-duty vehicle; longitudinal control; hydraulic retarder; reinforcement learning.

DOI: 10.1504/IJVD.2020.113914

International Journal of Vehicle Design, 2020 Vol.82 No.1/2/3/4, pp.97 - 119

Received: 01 Oct 2019
Accepted: 18 May 2020

Published online: 01 Apr 2021 *

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