Improving Driver Engagement During L2 Automation: A Pilot Study
DOI: 10.17077/drivingassessment.1707
archive: archived pipeline: cataloged
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This pilot study addresses the safety challenge of driver disengagement during SAE Level 2 (L2) vehicle automation, where drivers remain responsible for monitoring the driving task but may become inattentive due to the convenience of automated longitudinal and lateral control. The research aimed to evaluate a conceptual driver engagement system (System A) that integrates driver state monitoring with contextual environmental data to maintain driver awareness, comparing it against a traditional gaze-only alert system (System B). The motivation stems from the risk that unprepared drivers may make delayed or dangerous decisions when required to take over control from the automation. The experiment was conducted in a high-fidelity fixed-base driving simulator equipped with a full-cab Nissan Versa and a four-camera eye-tracking system. Seven participants completed a within-subject design, driving two 15-minute highway scenarios under L2 automation while performing secondary tasks. System A utilized a multi-modal interface including a head-up display (HUD) for contextual scenario descriptions, haptic seat actuators, audio voice synthesis, and a multi-color LED light bar. It triggered alerts based on a combination of driver inattention (less than 3 seconds of road gaze in a 30-second interval) and upcoming environmental events. System B relied solely on gaze monitoring, issuing staged visual and haptic alerts after 7, 12, and 17 seconds of inattention, without providing contextual information. Both systems were implemented using a Wizard-of-Oz approach, where an experimenter manually triggered alerts based on real-time observations. Results indicated that System A yielded significantly higher driver satisfaction (M = 5.99 vs. 5.07) and trust (M = 5.79 vs. 5.09) compared to System B. Participants also reported significantly higher situation awareness with System A (M = 6.54 vs. 4.76). While overall workload, measured via NASA-TLX, showed no significant difference between the two systems, eye-tracking data revealed nuanced behavioral differences. Although drivers spent more time looking off-road during L2 automation with System A (60% vs. 52%), they spent significantly more time looking at the roadway in the seconds immediately preceding a required takeover (77% vs. 58%). This suggests that the contextual information provided by System A helped drivers maintain critical awareness during high-risk transition periods, despite allowing for longer off-road glances during stable automated driving. The findings suggest that integrating contextual data with driver monitoring can improve driver engagement and situation awareness without increasing cognitive workload. The study concludes that adaptive, multi-modal engagement systems can help retain the safety benefits of advanced driver assistance systems while mitigating the human factors risks associated with automation-induced disengagement. These results inform the development of functional prototypes for live vehicle integration, highlighting the importance of balancing driver convenience with the need for sustained situational awareness.
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.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-08-09 |
| archive | success | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | cached | — | — | 4 | 2026-08-23 |
| clean | success | clean | — | — | 1 | 2026-08-09 |
| chunk | success | chunk | — | — | 1 | 2026-08-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-08-09 |
| enrich | success | semantic_scholar | — | — | 1 | 2026-08-09 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.8-27b-gittensor | summ-v5 | 3 | 2026-08-23 |
| tag | success | vector_similarity | — | — | 10 | 2026-08-11 |
| verify | success | — | — | — | 1 | 2026-08-09 |
Summary generated by qwen3.8-27b-gittensor on 2026-08-23; verification: pending re-verification.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- hands on hands off engagement
- automation
- mode awareness
- automation surprise
- situational awareness
- temporal
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: behavioral performance data
- Methodological Resource: tool software
- Theoretical Contribution: conceptual framework