When Context Is Not Enough: Modeling Unexplained Variability in Car-Following Behavior

TL;DR

This paper presents an interpretable stochastic modeling framework for car-following behavior that captures both context-dependent dynamics and residual variability, improving prediction accuracy and uncertainty quantification in traffic simulations.

Contribution

It introduces a novel deep neural network combined with nonstationary Gaussian processes to model latent driver variability beyond observable context, enhancing interpretability and predictive performance.

Findings

Outperforms traditional models in predictive accuracy on the HighD dataset.

Provides interpretable uncertainty quantification in acceleration, speed, and spacing.

Effectively captures latent driver intentions and perception errors.

Abstract

Modeling car-following behavior is fundamental to microscopic traffic simulation, yet traditional deterministic models often fail to capture the full extent of variability and unpredictability in human driving. While many modern approaches incorporate context-aware inputs (e.g., spacing, speed, relative speed), they frequently overlook structured stochasticity that arises from latent driver intentions, perception errors, and memory effects -- factors that are not directly observable from context alone. To fill the gap, this study introduces an interpretable stochastic modeling framework that captures not only context-dependent dynamics but also residual variability beyond what context can explain. Leveraging deep neural networks integrated with nonstationary Gaussian processes (GPs), our model employs a scenario-adaptive Gibbs kernel to learn dynamic temporal correlations in acceleration decisions, where the strength and duration of correlations between acceleration decisions evolve with the driving context. This formulation enables a principled, data-driven quantification of uncertainty in acceleration, speed, and spacing, grounded in both observable context and latent behavioral variability. Comprehensive experiments on the naturalistic vehicle trajectory dataset collected from the German highway, i.e., the HighD dataset, demonstrate that the proposed stochastic simulation method within this framework surpasses conventional methods in both predictive performance and interpretable uncertainty quantification. The integration of interpretability and accuracy makes this framework a promising tool for traffic analysis and safety-critical applications.