The paper presents a data-driven method for tire pressure estimation and an LPV-based control design for autonomous vehicles. The motivation of the research is that the pressures of the tires have high impacts on the lateral dynamics of the vehicle, because the loss of tire pressure may result in degradation in the lateral vehicle motion. First, a machine learning-based estimation algorithm, which uses only signals of on-board sensors, is proposed. Second, an LPV-based lateral control design is proposed, which uses the estimated tire pressure as a scheduling variable. The control is able to handle situations, in which the tire pressure decreases. The efficiency and the operation of the control system is illustrated through a comprehensive simulation example using the high-fidelity simulation software CarMaker.
Paper
Full text
LPV control for autonomous vehicles using a machine learning-based tire pressure estimation
Semantic Scholar · Engineering · 2020
Abstract
The paper presents a data-driven method for tire pressure estimation and an LPV-based control design for autonomous vehicles. The motivation of the research is that the pressures of the tires have high impacts on the lateral dynamics of the vehicle, because the loss of tire pressure may result in degradation in the lateral vehicle motion. First, a machine learning-based estimation algorithm, which uses only signals of on-board sensors, is proposed. Second, an LPV-based lateral control design is proposed, which uses the estimated tire pressure as a scheduling variable. The control is able to handle situations, in which the tire pressure decreases. The efficiency and the operation of the control system is illustrated through a comprehensive simulation example using the high-fidelity simulation software CarMaker.