Pedestrian Trajectory Prediction at Un-Signalized Intersection Using Probabilistic Reasoning and Sequence Learning

Autonomous vehicles are expected to predict the near future trajectories of the pedestrian who might wait or continue crossing the road at the un-signalized intersection. This study presents a new framework for pedestrian trajectory predictions, which integrates Dynamic Bayesian Networks (DBN) and sequence to sequence (Seq2Seq) learning through an adaptive weighting strategy. DBN anticipates the pedestrian's future trajectories using a probabilistic graphical model that combines environmental clues and kinematic information. Seq2Seq predicts the future trajectories with a well-trained learning model based on the observed trajectories up to the current instant. The adaptive weighting strategy can allocate weights online for DBN and Seq2Seq using the stopping probability and prediction errors. A real-world pedestrian dataset is employed for evaluations and results show that the proposed model outperforms DBN and Seq2Seq. The mean errors and final destination errors of the proposed model when predicting one second ahead are 0.04m, 0.10m in crossing scenarios, and 0.06m, 0.17m in stopping scenarios. This study expects to provide active pedestrian protections for autonomous vehicles on urban roads.