Differentiable Hybrid Traffic Simulation
This addresses traffic engineering problems by enabling better optimization for traffic control and flow, though it appears incremental as it builds on existing simulation methods with differentiability.
The authors tackled the problem of traffic simulation by developing a differentiable hybrid traffic simulator that combines macroscopic and microscopic models, which can be directly integrated into neural networks for traffic control and flow optimization. This is the first differentiable simulator for such hybrid models, enabling gradient computation across time steps and inhomogeneous lanes, and it provides more efficient and scalable solutions than existing algorithms.
We introduce a novel differentiable hybrid traffic simulator, which simulates traffic using a hybrid model of both macroscopic and microscopic models and can be directly integrated into a neural network for traffic control and flow optimization. This is the first differentiable traffic simulator for macroscopic and hybrid models that can compute gradients for traffic states across time steps and inhomogeneous lanes. To compute the gradient flow between two types of traffic models in a hybrid framework, we present a novel intermediate conversion component that bridges the lanes in a differentiable manner as well. We also show that we can use analytical gradients to accelerate the overall process and enhance scalability. Thanks to these gradients, our simulator can provide more efficient and scalable solutions for complex learning and control problems posed in traffic engineering than other existing algorithms. Refer to https://sites.google.com/umd.edu/diff-hybrid-traffic-sim for our project.