A paper by Yongwei Li, Yongzhi Jiang and Xinkai Wu was published inTransportation Research Part C: Emerging Technologies entitled “TrajPT: A trajectory data-based pre-trained transformer model for learning multi-vehicle interactions”. The authors propose a model designed to learn spatial\u2013temporal interactions among vehicles, trained using the pNEUMA dataset.<\/p>\n\n\n\n
Modeling and learning interactions with surrounding vehicles are critical for the safety and efficiency of autonomous vehicles. In this paper, we propose TrajPT, a Trajectory data-based Pre-trained Transformer model designed to learn spatial\u2013temporal interactions among vehicles from large-scale real-world trajectory data. Inspired by pre-trained large language models, TrajPT adopts an autoregressive learning framework and a pre-training paradigm, and can be fine-tuned for different autonomous driving downstream tasks. To capture complex spatial\u2013temporal interactions among vehicles, we utilize a spatial\u2013temporal scene graph to encode observed vehicle trajectories and introduce a novel graph-based joint spatial\u2013temporal attention module, which extracts spatial interactions within single frames and temporal dependencies across frames. TrajPT is pre-trained on pNEUMA, the largest publicly available vehicle trajectory dataset. We validate the performance of TrajPT by fine-tuning it on two downstream tasks: lane-changing prediction and trajectory prediction. Extensive experimental results demonstrate that the proposed TrajPT outperforms the baseline model and exhibits significant generalization performance across multiple datasets.<\/em><\/p>\n\n\n\n