Spatial-Temporal Block and LSTM Network for Pedestrian Trajectories Prediction
This work addresses collision avoidance in autonomous driving by improving trajectory prediction, but it is incremental as it builds on existing LSTM and graph-based methods.
The paper tackles pedestrian trajectory prediction for autonomous driving by proposing a novel LSTM-based algorithm that integrates Graph Convolutional Networks and Temporal Convolutional Networks to model social and spatial interactions, achieving state-of-the-art results on ETH and UCY datasets.
Pedestrian trajectory prediction is a critical to avoid autonomous driving collision. But this prediction is a challenging problem due to social forces and cluttered scenes. Such human-human and human-space interactions lead to many socially plausible trajectories. In this paper, we propose a novel LSTM-based algorithm. We tackle the problem by considering the static scene and pedestrian which combine the Graph Convolutional Networks and Temporal Convolutional Networks to extract features from pedestrians. Each pedestrian in the scene is regarded as a node, and we can obtain the relationship between each node and its neighborhoods by graph embedding. It is LSTM that encode the relationship so that our model predicts nodes trajectories in crowd scenarios simultaneously. To effectively predict multiple possible future trajectories, we further introduce Spatio-Temporal Convolutional Block to make the network flexible. Experimental results on two public datasets, i.e. ETH and UCY, demonstrate the effectiveness of our proposed ST-Block and we achieve state-of-the-art approaches in human trajectory prediction.