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

2025-07-09

AI Summary

Traditional deterministic car-following models fail to capture structured stochasticity arising from latent factors—such as driver intent, perceptual errors, and memory effects—leading to unquantifiable residual uncertainty when relying solely on observable contextual variables (e.g., spacing, speed). To address this, we propose an interpretable stochastic modeling framework that integrates a scene-adaptive Gibbs-kernel Gaussian process with a deep neural network, explicitly capturing non-stationary temporal dependencies in acceleration decisions and enabling data-driven uncertainty quantification. Experiments on the HighD dataset demonstrate that our method significantly outperforms classical deterministic models and state-of-the-art stochastic approaches in both predictive accuracy and uncertainty calibration. This advancement enhances the fidelity and interpretability of microscopic traffic simulation for complex human driving behaviors.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

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.

Problem

• Modeling unexplained variability in car-following behavior
• Capturing latent driver intentions and perception errors
• Improving predictive performance and uncertainty quantification

Innovation

• Integrates deep neural networks with Gaussian processes
• Uses scenario-adaptive Gibbs kernel for temporal correlations
• Combines observable context with latent variability