Situation-Aware Pedestrian Trajectory Prediction with Spatio-Temporal Attention Model
This addresses collision avoidance for autonomous driving and robot navigation, representing a strong specific gain but is incremental as it builds on existing LSTM and graph-based methods.
The paper tackles pedestrian trajectory prediction in crowded environments by proposing a spatio-temporal graph LSTM network that accounts for interactions with static and dynamic elements, resulting in up to 55% and 61% reductions in Average and Final Displacement Errors over state-of-the-art methods.
Pedestrian trajectory prediction is essential for collision avoidance in autonomous driving and robot navigation. However, predicting a pedestrian's trajectory in crowded environments is non-trivial as it is influenced by other pedestrians' motion and static structures that are present in the scene. Such human-human and human-space interactions lead to non-linearities in the trajectories. In this paper, we present a new spatio-temporal graph based Long Short-Term Memory (LSTM) network for predicting pedestrian trajectory in crowded environments, which takes into account the interaction with static (physical objects) and dynamic (other pedestrians) elements in the scene. Our results are based on two widely-used datasets to demonstrate that the proposed method outperforms the state-of-the-art approaches in human trajectory prediction. In particular, our method leads to a reduction in Average Displacement Error (ADE) and Final Displacement Error (FDE) of up to 55% and 61% respectively over state-of-the-art approaches.