Use of High-Fidelity Simulation to Evaluate Driver Performance with Vehicle Automation Systems
DOI: 10.1007/978-3-642-02728-4_36
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper examines the critical role of high-fidelity driving simulators in evaluating the safety and effectiveness of vehicle automation systems. As automation evolves to reduce driver error, it shifts the human role from operator to supervisor, creating complex human-machine interactions that require rigorous testing. The authors argue that careful evaluation is necessary to ensure that automation provides a net safety benefit and does not lead to complacency or catastrophic failure during system interventions. The study utilizes the National Advanced Driving Simulator (NADS) platforms, specifically the motion-capable NADS-1 and the fixed-base NADS-2, to assess various automation technologies classified by stage (1–5) and approach (augmented perception, control, or overall control). The paper details four specific research applications demonstrating the utility of these simulators. First, a proof-of-concept evaluation of a Stage 2 driver/environment monitoring system (SAVE-IT) tested augmented detection capabilities. Using NADS-1’s high-fidelity motion cues to simulate subtle throttle releases as haptic alerts, researchers found that while drivers mitigated distraction through task chunking, some adapted their behavior to anticipate alerts, indicating potential reliance on the system. Second, safety benefit analyses of Electronic Stability Control (ESC), a Stage 2 augmented control system, were conducted with over 650 participants. The high-fidelity motion cues were essential for reproducing loss-of-control scenarios; results showed an 88% reduction in loss of control with ESC, data that contributed to NHTSA rulemaking mandating ESC in light vehicles. Third, the paper outlines an evaluation of Adaptive Cruise Control (ACC), a Stage 1 vehicle control system. This study focuses on early adopters to identify error patterns and usage issues, particularly regarding system limitations and driver complacency. The high-fidelity motion cues of NADS-1 are required to accurately reproduce the acceleration and deceleration feedback drivers rely on to understand system status. Fourth, a design concept study for enhanced night vision systems (Stage 2 augmented perception) utilizes the fixed-base NADS-2 to evaluate alert modalities (visual, auditory, tactile) for pedestrian threats. This application prioritizes high-fidelity visuals over motion cueing. The authors conclude that high-fidelity simulators are indispensable for assessing automation technologies, particularly when realistic motion cues are needed to elicit valid driver responses in safety-critical situations. While lower-fidelity simulators may suffice for early design phases, high-fidelity environments like NADS provide definitive data for later-stage evaluations. The paper emphasizes that as automation advances toward full vehicle control, rigorous simulation-based testing will remain vital to balance the benefits of reduced human error against the risks of increased crash severity when automation fails.
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 | 2026-06-06 |
| archive | success | canonical_url | — | — | 1 | 2026-06-09 |
| extract | success | pdftotext | — | — | 2 | 2026-06-09 |
| clean | success | clean | — | — | 1 | 2026-06-09 |
| chunk | success | chunk | — | — | 1 | 2026-06-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-09 |
| enrich | failed | — | — | — | 3 | 2026-07-02 |
| promote | success | — | — | — | 1 | 2026-06-06 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-09 |
| tag | success | vector_similarity | — | — | 8 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-06-09 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-09; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- automation surprise
- situational awareness
- automation
- automation complacency bias
- mode awareness
- trust calibration
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).
- Methodological Resource: tool software, validation psychometrics
- Theoretical Contribution: conceptual framework