Vehicle Trajectory Prediction Based on Intention-Aware Non-Autoregressive Transformer With Multi-Attention Learning for Internet of Vehicles

As a core function of autonomous driving (AD) and the Internet of Vehicles (IoV), accurately predicting the trajectory of vehicles can significantly improve traffic safety and reduce crash injuries. In this article, we propose an intention-aware non-autoregressive Transformer model with multi-attention learning for multimodal vehicle trajectory prediction. We first present social attention learning (SAL) where graph attention is properly integrated with the Transformer encoder so as to model the social interaction between vehicles. Then, the social and temporal dependency across consecutive frames is captured by temporal attention learning (TAL). The above social and temporal attention modules can be interleaved and stacked to achieve the coupled modeling and thus extract abundant features from trajectory data. To implement precise prediction as well as efficient inference, we further put forward an intention-aware decoder query generation approach to produce multiple possible trajectories concurrently. Finally, cross-attention learning (CAL) is devised to make full use of the encoded features, therefore, yielding future predictions. The proposed model is evaluated on two large-scale vehicle trajectory datasets and the experimental results verify that our algorithm achieves better performance compared with some state-of-the-art models. The root-mean-square error (RMSE) of the predicted trajectory over 5-s time horizon for the next generation simulation (NGSIM) and HighD datasets is 3.43 and 1.10 m, respectively.