Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

See What I See: An Attention-Guiding eHMI Approach for Autonomous Vehicles

Jialong Li, Zhenyu Mao, Zhiyao Wang, Yijun Lu, Shogo Morita, Nianyu Li, Kenji Tei

TL;DR

The Attention-Guiding eHMI (AGeHMI), a projection-based visualization that employs directional cues and risk-based color coding to actively guide pedestrians' attention toward potential environmental dangers and significantly reduces potential collision risks with surrounding vehicles is proposed.

Abstract

As autonomous vehicles are gradually being deployed in the real world, external Human-Machine Interfaces (eHMIs) are expected to serve as a critical solution for enhancing vehicle-pedestrian communication. However, existing eHMI designs typically focus solely on the ego vehicle's status, which can inadvertently capture pedestrians' attention or encourage misguided reliance on the AV's signals, leading them to neglect scanning for other surrounding hazards. To address this, we propose the Attention-Guiding eHMI (AGeHMI), a projection-based visualization that employs directional cues and risk-based color coding to actively guide pedestrians' attention toward potential environmental dangers. Evaluation through a virtual reality user study (N = 20) suggests that AGeHMI effectively influences participants' visual attention distribution and significantly reduces potential collision risks with surrounding vehicles, while simultaneously improving subjective confidence and reducing cognitive workload.

See What I See: An Attention-Guiding eHMI Approach for Autonomous Vehicles

TL;DR

The Attention-Guiding eHMI (AGeHMI), a projection-based visualization that employs directional cues and risk-based color coding to actively guide pedestrians' attention toward potential environmental dangers and significantly reduces potential collision risks with surrounding vehicles is proposed.

Abstract

As autonomous vehicles are gradually being deployed in the real world, external Human-Machine Interfaces (eHMIs) are expected to serve as a critical solution for enhancing vehicle-pedestrian communication. However, existing eHMI designs typically focus solely on the ego vehicle's status, which can inadvertently capture pedestrians' attention or encourage misguided reliance on the AV's signals, leading them to neglect scanning for other surrounding hazards. To address this, we propose the Attention-Guiding eHMI (AGeHMI), a projection-based visualization that employs directional cues and risk-based color coding to actively guide pedestrians' attention toward potential environmental dangers. Evaluation through a virtual reality user study (N = 20) suggests that AGeHMI effectively influences participants' visual attention distribution and significantly reduces potential collision risks with surrounding vehicles, while simultaneously improving subjective confidence and reducing cognitive workload.
Paper Structure (10 sections, 7 figures)

This paper contains 10 sections, 7 figures.

Table of Contents

  1. Introduction
  2. Designing Projection-based Attention-Guiding eHMI
  3. VR User Study
  4. Study Setup
  5. Measurements and Data Processing
  6. Procedure
  7. Results and Discussion
  8. Results
  9. Discussion and Limitations
  10. Conclusion and Future Work

Figures (7)

  • Figure 1: Overview of the VR user study. Left: Baseline without eHMI. Middle: Standard ego's intent-only eHMI signals the pickup's yielding intent, which potentially causes pedestrians to overlook surrounding hazards. Right: Proposed Attention-Guiding eHMI (AGeHMI). This interface not only signals the pickup's yielding intent (green bar closest to the pedestrian) but also employs directional projections to visualize surrounding risks (two red bars further away), effectively guiding pedestrian attention toward hazards.
  • Figure 2: Projection-based AGeHMI, illustrating the depth-based spatial mapping of hazards and the risk-based color coding.
  • Figure 3: Comparison of potential collision rates for each target vehicle
  • Figure 4: Distribution of visual attention for each target vehicle
  • Figure 5: Temporal percentage of button unpresses over time
  • ...and 2 more figures