Open Access

ARTICLE

V2X-Enabled Parameter-Estimation-Based ILC for Repetitive Trajectory Tracking of Connected Vehicles under Trial-Varying Conditions

Ping Ma^1,2, Quan Wang^1,2, Yiyang Chen^3,*

1 School of Internet of Things Engineering, Wuxi University, Wuxi, China
2 Jiangsu Provincial University Key Laboratory of Vehicle-Road Multimodal Perception and Control, Wuxi University, Wuxi, China
3 School of Mechanical and Electrical Engineering, Soochow University, Suzhou, China

* Corresponding Author: Yiyang Chen. Email:

(This article belongs to the Special Issue: Advanced Networking Technologies for Intelligent Transportation and Connected Vehicles)

Computers, Materials & Continua 2026, 89(1), 62 https://doi.org/10.32604/cmc.2026.084488

Received 23 April 2026; Accepted 01 July 2026; Issue published 13 August 2026

Abstract

Connected vehicles operating in V2X-enabled intelligent transportation systems often perform repetitive trajectory tracking in repeated tasks. In practical applications, traffic conditions, communication quality, and sensing accuracy may vary from trial to trial. These variations induce time-varying dynamics across repeated runs and reduce the effectiveness of iterative learning control (ILC) schemes when fixed or inaccurately identified models are used. To address this issue, this paper proposes a parameter-estimation-based ILC framework for connected vehicles. Parameter estimation is integrated with a norm-optimal ILC design through an expectation-maximization strategy. The time-varying model parameters and the learning input are updated iteratively. By exploiting the estimated parameter information at each trial, the proposed method improves tracking performance under random noise and trial-varying operating conditions. Convergence properties are analyzed for both noise-free and noisy cases. Comparative results demonstrate improved tracking accuracy and convergence performance over several benchmark methods.

---

Keywords

---