An Approach to Vehicle Trajectory Prediction Using Automatically Generated Traffic Maps

TL;DR

This paper introduces a novel vehicle trajectory prediction method utilizing automatically generated traffic maps with behavioral statistics, improving mid-term prediction accuracy in automated driving scenarios.

Contribution

It presents a new approach that uses automatically generated maps with behavioral data to enhance vehicle trajectory prediction accuracy.

Findings

More precise mid-term predictions than traditional motion models

Generated maps contain comprehensive vehicle movement probabilities

Evaluation on 14,000+ trajectories demonstrates effectiveness

Abstract

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.