Machine Learning Based Path Prediction System - Adapting One Model for All Intersections

Abstract

To reduce the number of accidents, this thesis proposes a vehicle path prediction system to predict the future direction when a vehicle is about to cross an intersection. The GPS sensor is used to collect the dataset of vehicle trajectories at intersections. The trend of vehicle movements are derived from the heading in the trajectories, which is then combined with the vehicle speed to generate training data. In our path prediction algorithm, two ensemble learning algorithms, i.e., Random Forests and AdaBoost, are adopted for model training. The experiment results indicate that the Random Forest algorithm exhibits the best performance, and the Adaboost algorithm performs better than the base learner (i.e., Decision Tree).