VRU Trajectory Prediction Based on SA-TF-LSTM Considering Traffic–Actor Interaction for Automated Vehicles

This paper systematically investigates the prediction of Vulnerable Road Users’ (VRU, including pedestrian, cyclist, and electric cyclist) trajectories by leveraging the Action Intention Model (AIM), Revised Social Force Model (RSFM) and Social Attention-Transformer-Long Short Term Memory Network (SA-TF-LSTM) for automated vehicles. Firstly, an AIM based on the Transformer is developed for predicting the VRUs’ crossing/waiting intention. VRU type and heterogeneity (age and gender), distance between vehicle and VRU, speed of vehicle and VRU are considered. Secondly, a micro-dynamic RSFM is used to model the trajectories of VRUs for generating initially hypothetical future trajectories, which are then merged the historical trajectories with observed time as a new feature input. Furthermore, traffic data gathered by an unmanned aerial vehicle (UAV) is acquired and examined, and the Maximum Likelihood Estimation (MLE) is utilized to adjust the parameters of the RSFM. Finally, a data driven SA-TF-LSTM is proposed for VRU trajectory prediction, and VRU crossing intention, traffic-actor interaction, VRU type and heterogeneity are considered. Social Attention is employed to ascertain the attention coefficients of the aforementioned factors. The results demonstrate that the data driven SA-TF-LSTM surpasses the existing methods, with a prediction accuracy enhancement of over 9% utilizing the collected traffic data. This significant improvement grants us substantial confidence in employing the SA-TF-LSTM within automated vehicles to bolster the safety of VRUs.