Enhancing the Driver's Comprehension of ADS's System Limitations: An HMI for Providing Request-to-Intervene Trigger Information

TL;DR

This study tackles the problem of drivers misunderstanding ADS limitations when RtI is triggered by multiple cues. It introduces a voice-based RtI HMI that delivers trigger cues and post-event explanations to help drivers form an accurate mental model of ADS limitations. A driving-simulator experiment shows that the HMI significantly improves comprehension and can increase proactive takeover timing, with a trend toward fewer collisions, though statistical significance for collisions is marginal due to sample size. The findings suggest that informative RtI cues can enhance safe ADS operation and provide a basis for designing more effective HMIs in automated driving systems.

Abstract

Level 3 automated driving systems (ADS) have attracted significant attention and are being commercialized. A Level 3 ADS prompts the driver to take control by requesting to intervene (RtI) when its operational design domain (ODD) or system limitations are exceeded. However, complex traffic situations may lead drivers to perceive multiple potential triggers of RtI simultaneously, causing hesitation or confusion during take-over. Therefore, drivers must clearly understand the ADS's system limitations to understand the triggers of RtI and ensure safe take-over. In this study, we propose a voice-based HMI for providing RtI trigger cues to help drivers understand ADS's system limitations. The results of a between-group experiment using a driving simulator showed that incorporating effective trigger cues into the RtI enabled drivers to comprehend the ADS's system limitations better and reduce collisions. It also improved the subjective evaluations of drivers, such as the comprehensibility of system limitations, hesitation in response to RtI, and acceptance of ADS behaviors when encountering RtI while using the ADS. Therefore, enhanced comprehension resulting from trigger cues is essential for promoting a safer and better user experience using ADS during RtI.

Figures (6)

• Figure 1: Illustration of a complex traffic scenario where the driver may encounter challenges in determining the cause of an RtI trigger.
• Figure 2: Driving simulator used in this experiment. A HUD shows the ADS status.
• Figure 4: The various traffic scenarios used in the experiment, where the red car is the ego AV with a speed of 80 km/h. The scenarios (a), (b), and (c) are used in the phase I; (d) and (e) are used in the phase II; and (f) and (g) are used in the phase III; (h) is used in the phase IV.
• Figure 5: Examples of the designed traffic scenarios as seen from the driver's view. (a) and (b) show thick and thin fog scenarios, respectively, while (c) and (d) show sharp and slight curves. Traffic signs show the curvature of curve roads.
• Figure 6: Illustration of an active take-over and an inactive take-over in the RtI failure scenario, i. e., phase IV.