A Comparative Analysis of Machine Learning Methods for Lane Change Intention Recognition Using Vehicle Trajectory Data

TL;DR

This paper compares various machine learning techniques for recognizing vehicle lane change intentions from trajectory data, highlighting ensemble methods' accuracy and LightGBM's efficiency improvements.

Contribution

It provides a comprehensive comparison of ML methods for lane change intention recognition, emphasizing ensemble methods and LightGBM's superior training efficiency.

Findings

Ensemble methods achieve 98% classification accuracy.

LightGBM is six times faster to train than XGBoost.

Ensemble methods reduce misclassification errors.

Abstract

Accurately detecting and predicting lane change (LC)processes can help autonomous vehicles better understand their surrounding environment, recognize potential safety hazards, and improve traffic safety. This paper focuses on LC processes and compares different machine learning methods' performance to recognize LC intention from high-dimensionality time series data. To validate the performance of the proposed models, a total number of 1023 vehicle trajectories is extracted from the CitySim dataset. For LC intention recognition issues, the results indicate that with ninety-eight percent of classification accuracy, ensemble methods reduce the impact of Type II and Type III classification errors. Without sacrificing recognition accuracy, the LightGBM demonstrates a sixfold improvement in model training efficiency than the XGBoost algorithm.