Feasible and Adaptive Multimodal Trajectory Prediction with Semantic Maneuver Fusion
Hendrik Berkemeyer,Riccardo Franceschini,Tuan Tran,Lin Che,Gordon Pipa,Hendrik Berkemeyer,Riccardo Franceschini,Tuan Tran,Lin Che,Gordon Pipa
Predicting trajectories of participating vehicles is a crucial task towards full and safe autonomous driving. General unconstrained machine learning methods often report unrealistic predictions, and need to be combined with different motion constraints. Existing work either defines some shallow maneuvers and modes to regulate the output, or uses vehicle dynamics as the main source of constraints, ...
