Empirically Calibrated Differential Games for Simulating Driver Interactions
Abstract
Game-theoretic models can resolve vehicle interactions without hand-written priority rules, but whether they describe human drivers once calibrated has rarely been tested. This study formulates a general-sum differential game of vehicle interactions at urban intersections, calibrates it to observed driving, and evaluates it on data not used for calibration. Each vehicle minimizes a cost that combines speed tracking, adherence to a map-derived lane route, control effort, gap keeping based on the intelligent driver model, a predictive conflict term, and a contact barrier, while perceiving the other vehicles with a delay. The game is solved with a feedback iterative linear-quadratic algorithm, and ten behavioral parameters per vehicle are calibrated by Bayesian optimization on trajectories recorded at four intersections in Washington, D.C. The calibrated game reproduces the trajectories of 819 vehicles with a mean position error of 1.00 m. When only each vehicle's route is known, as in a simulator, it is the most accurate of the compared models on 96 held-out vehicles (7.42 m), and ten-fold cross-validation shows that it is significantly more accurate than calibrated SUMO (by 3.61 m), an inverse reinforcement learning model (by 0.93 m), and independent and cooperative variants of the same model (by 0.33 and 0.32 m). The solutions, computed in 2.1 s for a typical interaction, are verified approximate equilibria. Finally, the conflict and steering weights, which the data do not identify, can be set from safety and comfort targets; together with a stiffer contact barrier, this removes the collisions that otherwise occur in 43% of tight closed-loop conflicts.
Related
- Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence
- A multiscale lattice Boltzmann model for simulating Stokes to pre-Darcy flow
- Recurrent two-dimensional sequences over three and four letters simulating von Neumann constructions of finite ordinals
- Energy-Dissipative, High-Order BDF Schemes for Simulating Geometric Flows via Energy Increments
- Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics
BibTeX
@misc{khakpour2026empirically,
title = {{Empirically Calibrated Differential Games for Simulating Driver Interactions}},
author = {Amirmohammad Khakpour and Nachuan Li and Pedram Beigi and Yu and Nie},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32276},
eprint = {2610.32276},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32276},
}
RIS
TY - UNPB
TI - Empirically Calibrated Differential Games for Simulating Driver Interactions
AU - Amirmohammad Khakpour
AU - Nachuan Li
AU - Pedram Beigi
AU - Yu
AU - Nie
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32276
UR - https://arxiv.org/abs/2610.32276
AB - Game-theoretic models can resolve vehicle interactions without hand-written priority rules, but whether they describe human drivers once calibrated has rarely been tested. This study formulates a general-sum differential game of vehicle interactions at urban intersections, calibrates it to observed driving, and evaluates it on data not used for calibration. Each vehicle minimizes a cost that combines speed tracking, adherence to a map-derived lane route, control effort, gap keeping based on the intelligent driver model, a predictive conflict term, and a contact barrier, while perceiving the other vehicles with a delay. The game is solved with a feedback iterative linear-quadratic algorithm, and ten behavioral parameters per vehicle are calibrated by Bayesian optimization on trajectories recorded at four intersections in Washington, D.C. The calibrated game reproduces the trajectories of 819 vehicles with a mean position error of 1.00 m. When only each vehicle's route is known, as in a simulator, it is the most accurate of the compared models on 96 held-out vehicles (7.42 m), and ten-fold cross-validation shows that it is significantly more accurate than calibrated SUMO (by 3.61 m), an inverse reinforcement learning model (by 0.93 m), and independent and cooperative variants of the same model (by 0.33 and 0.32 m). The solutions, computed in 2.1 s for a typical interaction, are verified approximate equilibria. Finally, the conflict and steering weights, which the data do not identify, can be set from safety and comfort targets; together with a stiffer contact barrier, this removes the collisions that otherwise occur in 43% of tight closed-loop conflicts.
ER -