Score: 0

Learning from user's behaviour of some well-known congested traffic networks

Published: August 20, 2025 | arXiv ID: 2508.14804v1

By: Isolda Cardoso, Lucas Venturato, Jorgelina Walpen

Potential Business Impact:

Predicts traffic jams to help cars move faster.

Business Areas:
Autonomous Vehicles Transportation

We consider the problem of predicting users' behavior of a congested traffic network under an equilibrium condition, the traffic assignment problem. We propose a two-stage machine learning approach which couples a neural network with a fixed point algorithm, and we evaluate its performance along several classical congested traffic networks.

Page Count
12 pages

Category
Mathematics:
Optimization and Control