Social LSTM: Human Trajectory Prediction in Crowded Spaces

TLDR

Pedestrians adjust trajectories to avoid obstacles and each other, and autonomous vehicles must predict these future positions to avoid collisions; trajectory prediction is a sequence generation task that contrasts with hand‑crafted social force models. The study aims to predict future pedestrian trajectories by framing the problem as a sequence generation task and proposes an LSTM model to learn general human movement. An LSTM network is trained on pedestrian trajectory data, evaluated on public datasets, and its predicted trajectories are analyzed to illustrate learned motion behavior. The LSTM model outperforms state‑of‑the‑art methods on several public datasets and its predictions reveal learned motion behavior.

Abstract

Pedestrians follow different trajectories to avoid obstacles and accommodate fellow pedestrians. Any autonomous vehicle navigating such a scene should be able to foresee the future positions of pedestrians and accordingly adjust its path to avoid collisions. This problem of trajectory prediction can be viewed as a sequence generation task, where we are interested in predicting the future trajectory of people based on their past positions. Following the recent success of Recurrent Neural Network (RNN) models for sequence prediction tasks, we propose an LSTM model which can learn general human movement and predict their future trajectories. This is in contrast to traditional approaches which use hand-crafted functions such as Social forces. We demonstrate the performance of our method on several public datasets. Our model outperforms state-of-the-art methods on some of these datasets. We also analyze the trajectories predicted by our model to demonstrate the motion behaviour learned by our model.