Quantifying Uncertainty In Traffic State Estimation Using Generative Adversarial Networks
This work addresses uncertainty in traffic state estimation for transportation systems, representing an incremental improvement by combining existing methods.
The paper tackles uncertainty quantification in traffic state estimation by developing a physics-informed generative adversarial network (PhysGAN-TSE) framework, which is shown to be more robust than pure GAN or traffic flow models on the NGSIM dataset, with the ARZ-based version outperforming the LWR-based one.
This paper aims to quantify uncertainty in traffic state estimation (TSE) using the generative adversarial network based physics-informed deep learning (PIDL). The uncertainty of the focus arises from fundamental diagrams, in other words, the mapping from traffic density to velocity. To quantify uncertainty for the TSE problem is to characterize the robustness of predicted traffic states. Since its inception, generative adversarial networks (GAN) have become a popular probabilistic machine learning framework. In this paper, we will inform the GAN based predictions using stochastic traffic flow models and develop a GAN based PIDL framework for TSE, named ``PhysGAN-TSE". By conducting experiments on a real-world dataset, the Next Generation SIMulation (NGSIM) dataset, this method is shown to be more robust for uncertainty quantification than the pure GAN model or pure traffic flow models. Two physics models, the Lighthill-Whitham-Richards (LWR) and the Aw-Rascle-Zhang (ARZ) models, are compared as the physics components for the PhysGAN, and results show that the ARZ-based PhysGAN achieves a better performance than the LWR-based one.