Comparing Truck Driving Performance in a Simulator and Instrumented Vehicle

Hanowski, Richard J.; Morgan, Justin F.; Soccolich, Susan; Tidwell, Scott A. · 2022 · Crossref

DOI: 10.54941/ahfe100755

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 critical question of simulator validity in commercial motor vehicle (CMV) training, specifically comparing driving performance measures collected in a high-fidelity truck simulator versus behind-the-wheel (BTW) real-world driving. Motivated by demographic trends predicting a shortage of qualified CMV drivers and the increasing adoption of simulator-based training to improve efficiency, the research seeks to determine if simulator performance accurately reflects real-world capabilities. The authors note that while simulators offer safety and cost benefits, it remains unclear whether they elicit performance comparable to actual road conditions, which is essential for validating simulators as testing platforms. The study utilized data from 65 entry-level CDL candidates enrolled in a training program at Delaware Technical Community College. Participants were divided into two groups: a conventional group receiving 50 hours of BTW training and a simulator group receiving 32 hours of simulator training and 23 hours of BTW training. Both groups underwent identical road and range tests administered in both the simulator and real trucks. The simulator (FAAC TT-2000-V7) and the three Class-8 road trucks were equipped with identical data acquisition systems (DAS) to record sensor data and video. Performance was evaluated using standardized CDL exam criteria, including 13 specific road test items and six range maneuvers, as well as objective measures of lane departures (LDs) derived from the DAS. The results revealed significant discrepancies between simulator and BTW performance. For the road test, drivers trained conventionally performed significantly better in the BTW environment than in the simulator, whereas simulator-trained drivers showed no significant difference between the two environments. For range tests, both groups performed significantly better in the BTW environment compared to the simulator. Analysis of specific road test items showed that only general driving scores correlated significantly between platforms for both groups; other maneuvers showed little to no correlation. Most notably, the rate of lane departures was 250% higher in the simulator (0.48 per minute) than on the actual road (0.19 per minute), a difference that was statistically significant (p = 0.01). The study concludes that simulation may not be an appropriate platform for testing on-road performance due to these significant differences in scores and behavioral measures. While the findings suggest that simulator-based training does not negatively transfer to real-world skills (as BTW test scores were equivalent across training groups), the lack of equivalence in performance metrics indicates that simulator results cannot be directly generalized to real-world driving. The authors caution researchers and industry stakeholders that simulator findings may not reflect actual driver behavior, emphasizing the need for careful validation before using simulators for assessment purposes.

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.

StageOutcomeToolModelPromptAttemptsCompleted
discover success Crossref 1 2026-06-07
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
promote success 1 2026-06-07
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.

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).