Huikun Bi

TL;DR: This work proposes a Spatial-Temporal Graph Attention network (STGAT), based on a sequence-to-sequence architecture to predict future trajectories of pedestrians, which achieves superior performance on two publicly available crowd datasets and produces more "socially" plausible trajectories for pedestrians.

TL;DR: A comprehensive review on the state‐of‐the‐art techniques for traffic simulation and animation, including various data‐driven animation techniques, and the validation and evaluation of simulated traffic flows is provided.

TL;DR: This work proposes spatiotemporal attention long short-term memory (STA-LSTM), an LSTM model with spatial-temporal attention mechanisms for explainability in vehicle trajectory prediction that not only achieves comparable prediction performance against other state-of-the-art models but, more importantly, explains the influence of historical trajectories and neighboring vehicles on the target vehicle.

TL;DR: This paper uses an oriented bounding box to represent each vehicle, and proposes a framework called VP-LSTM to predict the kinematic trajectories of both vehicles and pedestrians simultaneously, to tackle the problem of handling crowded vehicle-pedestrian-mixed scenes directly.

TL;DR: A new data-driven model to simulate the process of lane-changing in traffic simulation that can make the subject vehicle to take account of more gap options on the target lane to cut in as well as achieve more realistic lane- changing trajectories for the subject Vehicle and the follower vehicle.