This article discusses the use of artificial intelligence, specifically deep learning, to predict pedestrian behavior in urban traffic. By accurately predicting pedestrian trajectories, human drivers and automated vehicles can better understand and avoid collisions with pedestrians. The research aims to identify gaps in current pedestrian behavior prediction methods and develop a model that incorporates social and pedestrian-vehicle interactions. The study uses a large-scale dataset for training and evaluation and evaluates prediction accuracy using average and final displacement errors.
