Research on trajectory tracking of autonomous vehicle based on human imitation

Tianyu Lei; Jin Mao; Ze Yu; Junwen Pan

doi:10.1117/12.3011560

7 December 2023 Research on trajectory tracking of autonomous vehicle based on human imitation

Tianyu Lei, Jin Mao, Ze Yu, Junwen Pan

Proceedings Volume 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023); 129414X (2023) https://doi.org/10.1117/12.3011560
Event: Third International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 203), 2023, Yinchuan, China

Abstract

Aiming at the trajectory tracking problem of autonomous vehicles, a Model Predictive Control (MPC) method imitating a driver is proposed. Using vehicle's dynamics as a prediction model, a linear time-varying model predictive controller is utilized to solve the optimal front wheel angle. According to the actual situation in which the driver pays more attention to the driving conditions in the close distance, the weight proportions of different step lengths in the prediction time domain are adjusted. A vehicle model is constructed in Carsim platform, and joint simulation with MATLAB/Simulink is performed to validate the effectiveness of the proposed controller. Simulation results show, compared to the traditional MPC algorithm, that the proposed control strategy can make the lateral displacement error of trajectory tracking decrease, improves tracking accuracy, and reduces fluctuations in the front wheel angle, thereby significantly enhancing the stability of trajectory tracking.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Tianyu Lei, Jin Mao, Ze Yu, and Junwen Pan "Research on trajectory tracking of autonomous vehicle based on human imitation", Proc. SPIE 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023), 129414X (7 December 2023); https://doi.org/10.1117/12.3011560

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available