Proving ground evaluation of enhanced ADAS: context understanding ADAS

Rizgary, Daban; Strand, Niklas; Andersson, Jonas · 2023 · Crossref

DOI: 10.54941/ahfe1003812

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the challenge of improving driver trust and acceptance of Advanced Driver Assistance Systems (ADAS), which are often underutilized due to insufficient performance and poor human-machine interaction. Current ADAS rely heavily on environmental sensors but lack broader context awareness, such as driver state or high-definition map data. The research aimed to evaluate a prototype "Context Understanding ADAS" that integrates external sensors, map data, and camera-based driver monitoring to enhance situation awareness and safety. The specific goal was to determine if these enhanced functionalities improved trust, acceptance, efficiency, and perceived situation awareness compared to a baseline SAE Level 2 system. The evaluation was conducted on the AstaZero proving ground in Sweden using a 2018 Lincoln MKZ. Twenty-four participants (13 men, 11 women, mean age 42) drove four 5.7-kilometer laps at 70 km/h: a familiarization lap, a baseline lap, a gaze-related functionality lap, and an active ADAS functionality lap. The baseline condition featured standard Adaptive Cruise Control (ACC) and Lane Centering Assist (LCA). The gaze-related functionality used driver monitoring to ensure correct blind-spot and turning gaze behaviors at intersections and during lane changes, providing visual cues via the HMI. The active ADAS functionality included two features: automatically increasing the ACC time gap when driver distraction was detected, and alerting the driver to upcoming scenarios outside the Operational Design Domain (ODD), such as roadworks, requiring a takeover. Data were collected using the Van Der Laan acceptance scale and standalone questions on trust, efficiency, and situation awareness, analyzed via paired t-tests. The results indicated that the enhanced functionalities were generally accepted and performed comparably to the baseline in most metrics. Specifically, the gaze-related functionality yielded a significant increase in perceived usefulness and satisfaction compared to the baseline. The active ADAS functionality also showed a significant increase in satisfaction relative to the baseline. However, no significant differences were found between the conditions for trust, perceived situation awareness, efficiency, or preference. The authors attribute the lack of difference in trust and situation awareness to the low complexity of the driving environment, which featured few dynamic events. Despite the lack of statistical significance in some areas, participants rated the prototype highly across all metrics, suggesting it was as trustworthy and efficient as the baseline while offering greater acceptance in specific contexts. The study concludes that integrating driver monitoring and map data into ADAS creates a more context-aware system that can improve driver satisfaction and usefulness. The findings suggest that while the prototype did not significantly alter trust or efficiency in this controlled setting, the enhanced acceptance indicates promise for real-world application. The authors recommend future research to isolate specific functional elements and incorporate objective eye-tracking metrics to better evaluate the impact of gaze-related functionalities on safe driving behavior. This work highlights the potential of holistic data integration to bridge the gap between technical ADAS capabilities and user acceptance.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• situational awareness
• adas effectiveness
• hud ar windshield
• automation
• automation surprise

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: self report data
• Methodological Resource: tool software, validation psychometrics