An Ensemble Learning Framework for Vehicle Trajectory Prediction in Interactive Scenarios

TL;DR

This paper introduces IETP, an ensemble learning framework that combines multiple interaction-aware predictors to enhance vehicle trajectory prediction accuracy in interactive scenarios, demonstrating improved performance and data efficiency.

Contribution

The paper presents a novel ensemble learning framework, IETP, that integrates multiple interaction-aware predictors for more accurate and data-efficient vehicle trajectory prediction.

Findings

IETP improves prediction accuracy over base learners.

IETP reduces error variance compared to individual models.

IETP performs well with only 50% of training data.

Abstract

Precisely modeling interactions and accurately predicting trajectories of surrounding vehicles are essential to the decision-making and path-planning of intelligent vehicles. This paper proposes a novel framework based on ensemble learning to improve the performance of trajectory predictions in interactive scenarios. The framework is termed Interactive Ensemble Trajectory Predictor (IETP). IETP assembles interaction-aware trajectory predictors as base learners to build an ensemble learner. Firstly, each base learner in IETP observes historical trajectories of vehicles in the scene. Then each base learner handles interactions between vehicles to predict trajectories. Finally, an ensemble learner is built to predict trajectories by applying two ensemble strategies on the predictions from all base learners. Predictions generated by the ensemble learner are final outputs of IETP. In this study, three experiments using different data are conducted based on the NGSIM dataset. Experimental results show that IETP improves the predicting accuracy and decreases the variance of errors compared to base learners. In addition, IETP exceeds baseline models with 50% of the training data, indicating that IETP is data-efficient. Moreover, the implementation of IETP is publicly available at https://github.com/BIT-Jack/IETP.