Chu, Yuan (State Key Laboratory of Automotive Safety and Energy, Tsinghua U), Ji, Xuewu (Tsinghua University)

Investigating Visual Attention and Vehicle Dynamics: A Study of Naturalistic Lane Change

Scheduled for presentation during the Poster Session "Human Drivers in Intelligent Transportation Systems" (FrAT15), Friday, September 27, 2024, 10:30−12:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 8, 2024

Abstract

The existing researches on driver attention have mainly focused on gaze responses to various driving factors and interactive patterns. Despite the major roles of vehicle motion states and driver inputs in advanced driver assistance system, only few studies have been conducted on the relationships between driver's attention patterns and vehicle dynamics during naturalistic lane change. This study aims at identifying the correlations between variables related to driver's attention patterns, steering input and vehicle lateral motion states responses in natural single lane change. We conducted experiments on public roads with twenty participants. Metrics based on glance duration, steering angle, yaw rate and lateral acceleration were analyzed. The results suggest that driver steering input and vehicle lateral motion states are obviously decoupled from the attention patterns, both in terms of the temporal dynamics and the holistic driving task, while on the other hand, to perform the lane change, strong correlations were observed in the trends of the central tendency among data frames, requiring a certain degree of attention to be dispersedly accumulated. This study will benefit the research on visual information-based human-vehicle interactive system design.