ITSC 2025 Paper Abstract

Paper TH-EA-T29.6

Chen, Yuzhi (Southeast University), Lu, Chang (Southeast University), Xu, Sixuan (Southeast University), Wu, Menghan (Southeast University), Xie, Yuanchang (University of Massachusetts Lowell), Wang, Chen (Southeast University)

VUD-FC: A Heterogeneous Behavior-Oriented Adaptive Control Approach Using Variable Universe of Discourse Fuzzy Strategy

Scheduled for presentation during the Regular Session "S29b-Human Factors and Human Machine Interaction in Automated Driving" (TH-EA-T29), Thursday, November 20, 2025, 14:50−15:30, Currumbin

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords User-Centric HMI Design for Autonomous Vehicle Control Systems, Autonomous Vehicle Safety and Performance Testing, Real-time Motion Planning and Control for Autonomous Vehicles in ITS Networks

Abstract

The imbalance between uniform control modes and heterogeneous driving behaviors causes control-driver preference mismatches, decreased user comfort or acceptance, and potential safety hazards, hindering the practical benefits of Adaptive Cruise Control (ACC). This paper introduces VUD-FC, a novel heterogeneous behavior-oriented adaptive control approach that combines variable universe of discourse with fuzzy control. VUD-FC uses scaling factors to dynamically adjust control sensitivity and responsiveness, enabling adaptive control ranges for heterogeneous behaviors. A behavior recognition method is developed that extracts the following parameters through intelligent driver model calibration and classifies driving behavior patterns using fuzzy c-means clustering. A personalized safe distance strategy incorporating a behavior-specific safety coefficient is designed to align following distances with individual driving preferences, which complements control parameter adaptation. Experimental results show that VUD-FC achieves 35.2% lower overshoot and 6.67% faster rise time compared to conventional controllers, providing differentiated control responses in heterogeneous behaviors while maintaining comfort (jerk within [-2, 2] ${m/s}^{3}$) and safety (inverse time to collision below 0.25 ${s}^{-1}$).