Active Simulation-Based Inference for Scalable Car-Following Model Calibration

2026-02-05

AI Summary

This work addresses the challenge of capturing driver behavioral uncertainty in data-driven car-following models, which deterministic calibration methods fail to represent, while conventional Bayesian approaches—though capable of inferring posterior parameter distributions—are computationally prohibitive for large-scale naturalistic driving data. To overcome this, the authors propose an active simulation-based inference framework that integrates a residual-augmented car-following simulator with an amortized conditional density estimator, enabling the estimation of driver-specific posterior distributions in a single forward pass. Furthermore, a joint parameter–context active sampling strategy is introduced to reduce simulation cost during training. Experiments on the HighD dataset demonstrate that the proposed method outperforms Bayesian baselines in both trajectory prediction accuracy and distributional fidelity, while exhibiting strong convergence and robustness, offering an efficient and scalable solution for high-fidelity, uncertainty-aware traffic flow simulation.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Inference

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Credible microscopic traffic simulation requires car-following models that capture both the average response and the substantial variability observed across drivers and situations. However, most data-driven calibrations remain deterministic, producing a single best-fit parameter vector and offering limited guidance for uncertainty-aware prediction, risk-sensitive evaluation, and population-level simulation. Bayesian calibration addresses this gap by inferring a posterior distribution over parameters, but per-trajectory sampling methods such as Markov chain Monte Carlo (MCMC) are computationally infeasible for modern large-scale naturalistic driving datasets. This paper proposes an active simulation-based inference framework for scalable car-following model calibration. The approach combines (i) a residual-augmented car-following simulator with two alternatives for the residual process and (ii) an amortized conditional density estimator that maps an observed leader--follower trajectory directly to a driver-specific posterior over model parameters with a single forward pass at test time. To reduce simulation cost during training, we introduce a joint active design strategy that selects informative parameter proposals together with representative driving contexts, focusing simulations where the current inference model is most uncertain while maintaining realism. Experiments on the HighD dataset show improved predictive accuracy and closer agreement between simulated and observed trajectory distributions relative to Bayesian calibration baselines, with convergence and ablation studies supporting the robustness of the proposed design choices. The framework enables scalable, uncertainty-aware driver population modeling for traffic flow simulation and risk-sensitive transportation analysis.

Problem

• car-following model calibration
• uncertainty-aware simulation
• scalable inference
• Bayesian calibration
• naturalistic driving data

Innovation

• simulation-based inference
• amortized inference
• car-following model
• Bayesian calibration
• active learning