Ultra-fast Traffic Nowcasting and Control via Differentiable Agent-based Simulation

TL;DR

This paper introduces a differentiable agent-based traffic simulator that enables ultra-fast calibration, nowcasting, and control of large-scale traffic networks, significantly improving efficiency over traditional methods.

Contribution

We develop a fully differentiable traffic simulation framework that allows for rapid calibration and control of large-scale networks using gradient-based optimization.

Findings

Simulates over one million vehicles at 173x real-time speed

Completes model calibration in 455 seconds using 30 minutes of data

Performs traffic nowcasting in 21 seconds and control in 728 seconds

Abstract

Traffic digital twins, which inform policymakers of effective interventions based on large-scale, high-fidelity computational models calibrated to real-world traffic, hold promise for addressing societal challenges in our rapidly urbanizing world. However, conventional fine-grained traffic simulations are non-differentiable and typically rely on inefficient gradient-free optimization, making calibration for real-world applications computationally infeasible. Here we present a differentiable agent-based traffic simulator that enables ultra-fast model calibration, traffic nowcasting, and control on large-scale networks. We develop several differentiable computing techniques for simulating individual vehicle movements, including stochastic decision-making and inter-agent interactions, while ensuring that entire simulation trajectories remain end-to-end differentiable for efficient gradient-based optimization. On the large-scale Chicago road network, with over 10,000 calibration parameters, our model simulates more than one million vehicles at 173 times real-time speed. This ultra-fast simulation, together with efficient gradient-based optimization, enables us to complete model calibration using the previous 30 minutes of traffic data in 455 s, provide a one-hour-ahead traffic nowcast in 21 s, and solve the resulting traffic control problem in 728 s. This yields a full calibration--nowcast--control loop in under 20 minutes, leaving about 40 minutes of lead time for implementing interventions. Our work thus provides a practical computational basis for realizing traffic digital twins.