Empirical Comparison of Different Pedestrian Trajectory Prediction Methods at High Densities

Predicting human trajectories is a challenging task due to the complexity of pedestrian behavior, which is influenced by external factors such as the scene’s topology and interactions with other pedestrians. A special challenge arises from the dependence of the behaviour on the density of the scene. In the literature, deep learning algorithms show the best performance in predicting pedestrian trajectories, but so far just for situations with low-densities. In this study, we aim to investigate the suitability of these algorithms for high-density scenarios by evaluating them using two error metrics and comparing their accuracy to that of knowledge-based models. The first metric is distance-based, while the second counts the number of collisions between pedestrians. Our findings reveal that deep learning algorithms provide improved trajectory accuracy in the distance metric, but knowledge-based models perform better in avoiding collisions.