Pedestrian Prediction by Planning using Deep Neural Networks
Accurate traffic participant prediction is the prerequisite for collision avoidance of autonomous vehicles. In this work, we predict pedestrians by emulating their own motion planning. From online observations, we infer a mixture density function for possible destinations. We use this result as the...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Accurate traffic participant prediction is the prerequisite for collision
avoidance of autonomous vehicles. In this work, we predict pedestrians by
emulating their own motion planning. From online observations, we infer a
mixture density function for possible destinations. We use this result as the
goal states of a planning stage that performs motion prediction based on common
behavior patterns. The entire system is modeled as one monolithic neural
network and trained via inverse reinforcement learning. Experimental validation
on real world data shows the system's ability to predict both, destinations and
trajectories accurately. |
---|---|
DOI: | 10.48550/arxiv.1706.05904 |