A Driving Simulator Investigation on the Aggressiveness of an Automatic Lane-Change System
Most existing personalized automatic lane-change systems rely on manual driving data, but obtaining such data for future highly automated driving systems will become increasingly difficult. Emphasis should be placed on the bidirectional interaction between humans and intelligent vehicles. However, l...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11031412/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Most existing personalized automatic lane-change systems rely on manual driving data, but obtaining such data for future highly automated driving systems will become increasingly difficult. Emphasis should be placed on the bidirectional interaction between humans and intelligent vehicles. However, little research has explored how the aggressiveness of automated driving systems affects drivers, hindering personalization through human-vehicle interaction. To address this, this study investigates how the aggressiveness of automated lane-change systems affects drivers’ subjective perception and gaze behavior. A driving simulator experiment was conducted where 22 participants experienced automatic lane-change systems. These systems featured varying levels of aggressiveness in lane change decisions, implemented using a previously proposed fuzzy-based model. The experiment entailed the collection of both subjective perceptions and gaze patterns from the participants. The research findings indicate that the aggressiveness of automatic lane changes simultaneously affects drivers’ perceptions, particularly safety evaluations and decision agreement, as well as gaze patterns toward the rear vehicle in the target lane. This implies that the relative driving status of the rear vehicle is the primary factor influencing drivers’ subjective perceptions during automatic lane changes. These results affirm the potential of personalizing automated driving systems through human-machine interaction, promising advancement in future highly automated driving systems. Further analysis of the experimental results provides practical suggestions for implementing this personalization approach. |
|---|---|
| ISSN: | 2169-3536 |