Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data
Published in
European Conference on Computer Vision(2020)External Links:
TL
TL;DR
Trajectron++ is a modular, graph-structured recurrent model that forecasts the trajectories of a general number of diverse agents while incorporating agent dynamics and heterogeneous data and outperforming a wide array of state-of-the-art deterministic and generative methods.