An adversarial variational inference approach for travel demand calibration of urban traffic simulators

Martin Mladenov, Sanjay Ganapathy Subramaniam, Chih-Wei Hsu, Neha Arora, Andrew Tomkins, Craig Boutilier, Carolina Osorio

Abstract

This paper considers the calibration of travel demand inputs, defined as a set of origin-destination matrices (ODs), for stochastic microscopic urban traffic simulators. The goal of calibration is to find a (set of) travel demand input(s) that replicate sparse field count data statistics. While traditional approaches use only first-order moment information from the field data, it is well known that the OD calibration problem is underdetermined in realistic networks. We study the value of using higher-order statistics from spatially sparse field data to mitigate underdetermination, proposing a variational inference technique that identifies an OD distribution. We apply our approach to a high-dimensional setting in Salt Lake City, Utah. Our approach is flexible---it can be readily extended to account for arbitrary types of field data (e.g., road, path or trip data).
BibTeX
@inproceedings{mladenov2022adversarial,
  author = {Martin Mladenov and Sanjay Ganapathy Subramaniam and Chih-Wei Hsu and Neha Arora and Andrew Tomkins and Craig Boutilier and Carolina Osorio},
  title = {{An adversarial variational inference approach for travel demand calibration of urban traffic simulators}},
  booktitle = {SIGSPATIAL/GIS},
  year = {2022},
  doi = {10.1145/3557915.3560940},
}

Loading related content...

Figure