.png){kind=icon}
.png){kind=icon}
Return
How do human factors affect the explanatory power of driver models? A methodology for comparative model assessment and validation
.png){kind=icon}
OA
AI
V
D
A
M
DOI：10.1016/j.trb.2026.103466.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Aggregate error distributions are shown to yield indeterminate model rankings. • We introduce trajectory-level pairwise calibration tests and normalised relative error metric for fair model comparison. • Verisimilitude and total sensitivity indices quantify the accuracy-robustness trade-off as model complexity increases. • 800 models are compared, obtained by augmenting IDM-family models with human factors. • We introduce a new IDM variant, the M-IDM, which outperforms all IDM-family models.
Keywords:
Driver models
Human factors
Adaptive driving
Verisimilitude
Calibration
Global sensitivity analysis
Validation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
T
IF:
0
Papers:
78
Citations:
0
Organization
Cited Papers