Vehicle Behavior Prediction and Generalization Using Imbalanced Learning Techniques

TL;DR

This paper introduces an interaction-aware vehicle behavior prediction model that employs imbalanced learning techniques and evaluates its generalization across different traffic datasets, improving accuracy and robustness.

Contribution

It proposes a novel combination of LSTM autoencoder, SVM classifier, and multiclass balancing ensemble to address class imbalance and enhance generalization in vehicle behavior prediction.

Findings

Improved classification accuracy with the proposed method.

Enhanced generalization to unseen traffic data.

Effective encoding of structural and static features.

Abstract

The use of learning-based methods for vehicle behavior prediction is a promising research topic. However, many publicly available data sets suffer from class distribution skews which limits learning performance if not addressed. This paper proposes an interaction-aware prediction model consisting of an LSTM autoencoder and SVM classifier. Additionally, an imbalanced learning technique, the multiclass balancing ensemble is proposed. Evaluations show that the method enhances model performance, resulting in improved classification accuracy. Good generalization properties of learned models are important and therefore a generalization study is done where models are evaluated on unseen traffic data with dissimilar traffic behavior stemming from different road configurations. This is realized by using two distinct highway traffic recordings, the publicly available NGSIM US-101 and I80 data sets. Moreover, methods for encoding structural and static features into the learning process for improved generalization are evaluated. The resulting methods show substantial improvements in classification as well as generalization performance.