Cross-Domain Transfer Learning using Attention Latent Features for Multi-Agent Trajectory Prediction

TL;DR

This paper introduces a novel Transformer-based framework with attention latent features and graph convolutional networks to improve cross-domain vehicle trajectory prediction in multi-agent traffic scenarios, demonstrating superior generalization across different cities and time periods.

Contribution

The paper presents a new spatial-temporal trajectory prediction framework that enhances cross-domain adaptation using attention latent features and dynamic graph embeddings.

Findings

Achieves better trajectory prediction accuracy than state-of-the-art models.

Effectively adapts to unseen traffic networks across different cities and time periods.

Demonstrates robustness in cross-city and cross-period case studies.

Abstract

With the advancements of sensor hardware, traffic infrastructure and deep learning architectures, trajectory prediction of vehicles has established a solid foundation in intelligent transportation systems. However, existing solutions are often tailored to specific traffic networks at particular time periods. Consequently, deep learning models trained on one network may struggle to generalize effectively to unseen networks. To address this, we proposed a novel spatial-temporal trajectory prediction framework that performs cross-domain adaption on the attention representation of a Transformer-based model. A graph convolutional network is also integrated to construct dynamic graph feature embeddings that accurately model the complex spatial-temporal interactions between the multi-agent vehicles across multiple traffic domains. The proposed framework is validated on two case studies involving the cross-city and cross-period settings. Experimental results show that our proposed framework achieves superior trajectory prediction and domain adaptation performances over the state-of-the-art models.