A fully differentiable agent-based traffic simulator enables calibration and control of million-vehicle networks 173x faster than real-time.
March 27, 2026
Original Paper
Ultra-fast Traffic Nowcasting and Control via Differentiable Agent-based Simulation
arXiv · 2603.25068
The Takeaway
It moves traffic digital twins from slow, gradient-free optimization to efficient gradient-based methods. This allows for city-scale traffic nowcasting and control loops to be completed in minutes rather than hours or days.
From the 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 agen