Vehicle Behavior Prediction and Generalization Using Imbalanced Learning Techniques
This addresses prediction challenges for autonomous vehicles using imbalanced data, though it is incremental with hybrid methods.
The paper tackles vehicle behavior prediction with imbalanced datasets by proposing an LSTM autoencoder-SVM model with a multiclass balancing ensemble, showing improved classification accuracy and generalization to unseen traffic data from different road configurations.
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.