Summary
International Conference on Emerging Technologies for Communications
2022
Session Number:S5
Session:
Number:S5-6
An Experimental Study on Modeling Accuracy of Digital Twin for Cloud-Based Remote Vehicle Path Tracking Control
Masaki Minagawa, Yudai Yoshimoto, Ryohei Nakamura, Hisaya Hadama,
pp.-
Publication Date:2022/11/29
Online ISSN:2188-5079
DOI:10.34385/proc.72.S5-6
PDF download (1.4MB)
Summary:
Path tracking control is essential for various applications of autonomous vehicle. Cloud-server-based remote control scheme has advantages such as reducing the cost of the vehicle itself and easy information sharing at the server. However, this scheme has a problem that transmission delay in the Internet deteriorates control accuracy. Predictive control with digital twin computing is expected to solve this problem. Based on a predictive model using digital twin computing, control server can make an adequate control signal even when transmission delay exists. Accurate predictive control requires predictive model that accurately models a real vehicle. Control accuracy of path tracking control depends on modeling error and cycle of feedback signals. In this paper, we present results of an experimental evaluation of the dependence of path tracking control accuracy on modeling error and feedback cycle.