How does training influence use and understanding of advanced vehicle technologies: a simulator evaluation of driver behavior and mental models

Pradhan, Anuj; Hungund, Apoorva; Pai, Ganesh; Pamarthi, Jaji · 2023 · Crossref

DOI: 10.55329/udqk4583

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 investigates how different training methods influence novice drivers’ understanding and use of Advanced Driver Assistance Systems (ADAS), specifically Adaptive Cruise Control (ACC). As ADAS technologies become ubiquitous, drivers must develop accurate mental models of system capabilities and limitations to ensure safe operation. While training is recognized as a tool for improving driver knowledge, the specific impact of different instructional approaches on understanding complex automation remains unclear. The research aimed to determine if training improves ACC understanding and to compare the efficacy of text-based versus visualization-based training methods. The researchers employed a mixed experimental design using a high-fidelity driving simulator. Twenty-four licensed drivers with little to no prior ADAS experience were randomly assigned to one of three groups: a ‘User Manual’ group receiving text-based instructions, a ‘Visualization’ group receiving a state-diagram illustration of ACC functions, or a ‘Sham’ control group receiving information on unrelated systems. Participants completed a mental model survey (CAMMS) before and after training to assess knowledge. They then performed simulated drives involving ACC interaction, during which their real-time awareness was measured via verbal probes about system status, and their operational skills were assessed through manual responses to system control instructions. Results indicated a significant overall increase in ACC knowledge following training for the experimental groups, with both text-based and visualization methods yielding statistically significant improvements compared to the sham group. Drivers in the experimental groups also demonstrated higher accuracy in real-time verbal responses regarding system state than the control group, although this difference was not statistically significant. Similarly, while the visualization group showed slightly higher accuracy in manual system operations and faster reaction times, these behavioral differences were not statistically significant across groups. The study suggests that while training effectively enhances conceptual knowledge, the specific instructional method (text vs. visualization) did not produce distinct advantages in this experimental context, potentially due to the simplicity of the operational tasks and probe questions. The findings underscore the importance of training in improving drivers’ mental models of vehicle automation. However, the lack of significant differences in behavioral metrics highlights challenges in measuring the translation of knowledge into real-time performance. The authors conclude that current experimental measures may lack the sensitivity to detect nuanced differences in driver understanding and suggest that future research should focus on developing more robust metrics for assessing mental models and testing training effects in more complex driving scenarios. These results have implications for the design of driver education programs and policies regarding the deployment of advanced vehicle technologies.

Key finding

Training with either text-based manuals or visualizations significantly improved novice drivers' knowledge of Adaptive Cruise Control compared to a control group, but did not produce significant differences in real-time operational accuracy or response times.

Methodology

simulator

Sample size: 24

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-prismaquant on 2026-06-10; verification: verified.

Topics

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

• situational awareness
• simulator training transfer
• in vehicle coaching
• acceptance adoption
• automation surprise
• learner drivers

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).

• Applied Guidance: countermeasure evaluation
• Methodological Resource: tool software
• Theoretical Contribution: computational model