Closed-Loop Neural Operator-Based Observer of Traffic Density
By: Alice Harting, Karl Henrik Johansson, Matthieu Barreau
Potential Business Impact:
Improves traffic jams by predicting and fixing flow.
We consider the problem of traffic density estimation with sparse measurements from stationary roadside sensors. Our approach uses Fourier neural operators to learn macroscopic traffic flow dynamics from high-fidelity data. During inference, the operator functions as an open-loop predictor of traffic evolution. To close the loop, we couple the open-loop operator with a correction operator that combines the predicted density with sparse measurements from the sensors. Simulations with the SUMO software indicate that, compared to open-loop observers, the proposed closed-loop observer exhibits classical closed-loop properties such as robustness to noise and ultimate boundedness of the error. This shows the advantages of combining learned physics with real-time corrections, and opens avenues for accurate, efficient, and interpretable data-driven observers.
Similar Papers
Online Traffic Density Estimation using Physics-Informed Neural Networks
Machine Learning (CS)
Makes traffic jams easier to predict.
ON-Traffic: An Operator Learning Framework for Online Traffic Flow Estimation and Uncertainty Quantification from Lagrangian Sensors
Machine Learning (CS)
Predicts traffic jams using car data.
A Physics-informed Deep Operator for Real-Time Freeway Traffic State Estimation
Machine Learning (CS)
Helps cars know traffic speed and flow better.