An Approach to Vehicle Trajectory Prediction Using Automatically Generated Traffic Maps
This addresses the problem of safe interaction in automated driving by improving prediction accuracy, though it appears incremental as it builds on existing map and prediction techniques.
The paper tackles vehicle trajectory prediction by using automatically generated traffic maps that encode typical movements and probabilities, achieving significantly more precise mid-term predictions compared to motion model-based approaches on a dataset of over 14000 trajectories.
Trajectory and intention prediction of traffic participants is an important task in automated driving and crucial for safe interaction with the environment. In this paper, we present a new approach to vehicle trajectory prediction based on automatically generated maps containing statistical information about the behavior of traffic participants in a given area. These maps are generated based on trajectory observations using image processing and map matching techniques and contain all typical vehicle movements and probabilities in the considered area. Our prediction approach matches an observed trajectory to a behavior contained in the map and uses this information to generate a prediction. We evaluated our approach on a dataset containing over 14000 trajectories and found that it produces significantly more precise mid-term predictions compared to motion model-based prediction approaches.