Abstract
Pedestrians follow different trajectories to avoid obsta-cles and accommodate fellow pedestrians. Any autonomousvehicle navigating such a scene should be able to foreseethe future positions of pedestrians and accordingly adjustits path to avoid collisions. This problem of trajectory pre-diction can be viewed as a sequence generation task, wherewe are interested in predicting the future trajectory of peo-ple based on their past positions. Following the recent suc-cess of Recurrent Neural Network (RNN) models for se-quence prediction tasks, we propose an LSTM model whichcan learn general human movement and predict their futuretrajectories. This is in contrast to traditional approacheswhich 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.