Heterogeneous Traffic Trajectory Prediction via Spatial Attention Network for Internet of Vehicles.

There are different types of traffic agents in urban scenes. Their movement behaviors influence each other. Accu-rately predicting trajectories of these traffic agents contributes to the advancement of autonomous driving technology. In recent years, deep learning technology has become a more popular method for extracting motion features. However, most of the studies cannot properly simulate the interaction between agents, which affects the performance of the algorithm. This paper proposes a heterogeneous traffic trajectory prediction algorithm based on spatial attention network. We combine the features of different types of agents to optimize the attention mechanism, so that the algorithm can adaptively extract the spatial relationship between them. In addition, we use LSTM to combine the interaction effects of traffic agents with their own movement patterns from both spatial and temporal perspectives. Finally, the future moving positon sequence of the agent is obtained. We use different datasets to evaluate the performance of the algorithm, and its prediction error is reduced by 15% compared with other methods.