Sanghyun Son

CS PhD @ UMD

Differentiable Hybrid Traffic Simulation


Journal article


Sanghyun Son, Yi-Ling Qiao, Jason Sewall, Ming C Lin
SIGGRAPH Asia, ACM Transactions on Graphics (TOG), 2022

Arxiv Github Page
Cite

Cite

APA   Click to copy
Son, S., Qiao, Y.-L., Sewall, J., & Lin, M. C. (2022). Differentiable Hybrid Traffic Simulation. SIGGRAPH Asia, ACM Transactions on Graphics (TOG).


Chicago/Turabian   Click to copy
Son, Sanghyun, Yi-Ling Qiao, Jason Sewall, and Ming C Lin. “Differentiable Hybrid Traffic Simulation.” SIGGRAPH Asia, ACM Transactions on Graphics (TOG) (2022).


MLA   Click to copy
Son, Sanghyun, et al. “Differentiable Hybrid Traffic Simulation.” SIGGRAPH Asia, ACM Transactions on Graphics (TOG), 2022.


BibTeX   Click to copy

@article{son2022a,
  title = {Differentiable Hybrid Traffic Simulation},
  year = {2022},
  journal = {SIGGRAPH Asia, ACM Transactions on Graphics (TOG)},
  author = {Son, Sanghyun and Qiao, Yi-Ling and Sewall, Jason and Lin, Ming C}
}

Abstract

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.

Share


Follow this website


You need to create an Owlstown account to follow this website.


Sign up

Already an Owlstown member?

Log in