Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning A Case Study: Overtaking Cyclists

This article examines probabilistic trajectory forecasting methods of vulnerable road users (VRU) for the motion planning of autonomous vehicles. The future trajectories of a cyclist are predicted by Quantile Surface Neural Networks (QSN) and Mixture Density Neural Networks (MDN), both modeling confidence regions around the cyclist’s expected locations. Confidence regions are approximated by diffe...