HSTA: A Hierarchical Spatio-Temporal Attention Model for Trajectory Prediction

Predicting the future trajectories of surrounding agents has become an crucial problem to be solved for the safety of autonomous vehicles. Recent studies based on Long Short Term Memory (LSTM) networks have shown powerful abilities to model social interactions. However, many of these approaches focus on spatial interactions of the neighborhood agents but ignore temporal interactions that accompany spatial interactions. In this paper, we propose a Hierarchical Spatio-Temporal Attention architecture (HSTA), which activates the utilization of spatial interactions with different weights, and jointly considers the temporal interactions across time steps of all agents. More specially, the graph attention mechanism (GAT) is presented to capture spatial interactions, the multi-head attention mechanism (MHA) is conducted to encode temporal correlations of interactions and a state gated fusion (SGF) layer is used to integrate spatial and temporal interactions. We evaluate our proposed method against baselines on both pedestrian and vehicle datasets. The results show that our model is effective and achieves state-of-the-art achievements.

Automated summary

In this paper, a Hierarchical Spatio-Temporal Attention architecture (HSTA) is proposed to capture spatial interactions using graph attention mechanism (GAT), encode temporal correlations with multi-head attention mechanism (MHA), and integrate spatial and temporal interactions with a state gated fusion (SGF) layer. The experimental results demonstrate that the proposed method outperforms baselines on pedestrian and vehicle datasets, achieving state-of-the-art achievements.