Interaction-Aware Personalized Vehicle Trajectory Prediction Using Temporal Graph Neural Networks

TL;DR

This paper introduces a novel interaction-aware personalized vehicle trajectory prediction method using temporal graph neural networks, leveraging transfer learning and human-in-the-loop data collection to improve accuracy over generic models.

Contribution

It proposes a personalized trajectory prediction approach with a transfer learning pipeline and temporal graph neural networks, enhancing accuracy for individual drivers.

Findings

Personalized GCN-LSTM model outperforms generic models, especially for longer horizons.

Pre-training on large datasets reduces overfitting and improves personalization.

Experimental results confirm improved prediction accuracy with personalization.

Abstract

Accurate prediction of vehicle trajectories is vital for advanced driver assistance systems and autonomous vehicles. Existing methods mainly rely on generic trajectory predictions derived from large datasets, overlooking the personalized driving patterns of individual drivers. To address this gap, we propose an approach for interaction-aware personalized vehicle trajectory prediction that incorporates temporal graph neural networks. Our method utilizes Graph Convolution Networks (GCN) and Long Short-Term Memory (LSTM) to model the spatio-temporal interactions between target vehicles and their surrounding traffic. To personalize the predictions, we establish a pipeline that leverages transfer learning: the model is initially pre-trained on a large-scale trajectory dataset and then fine-tuned for each driver using their specific driving data. We employ human-in-the-loop simulation to collect personalized naturalistic driving trajectories and corresponding surrounding vehicle trajectories. Experimental results demonstrate the superior performance of our personalized GCN-LSTM model, particularly for longer prediction horizons, compared to its generic counterpart. Moreover, the personalized model outperforms individual models created without pre-training, emphasizing the significance of pre-training on a large dataset to avoid overfitting. By incorporating personalization, our approach enhances trajectory prediction accuracy.