Traffic signal timing estimation using a support vector regression model

Abstract

A method and apparatus for traffic signal timing estimation are disclosed. Traffic signal timing estimation may include a vehicle identifying transportation network information representing a vehicle transportation network including an intersection. The transportation network information may include expected traffic control device state information corresponding to the intersection, such as a support vector regression based machine learning model trained for the intersection. The vehicle may identify a route through the vehicle transportation network that includes the intersection based on the expected traffic control device state information and may control the traversal of the vehicle transportation network by the vehicle based on the expected traffic control device state information to minimize one or more operational cost metrics. Training the model may include identifying training data from input data previously generated and stored by a traffic control device controller of the intersection.