Benutzer: Gast  Login
Titel:

What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Christoph Schöller, Vincent Aravantinos, Florian Lay and Alois Knoll
Abstract:
Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on neural networks have been proposed to address this problem. In this work we show that - surprisingly - a simple Constant Velocity Model can outperform even state-of-the-art neural models. This indicates that either neural networks are not able to make use of the additional information they are provided with, or that this information is not as r...     »
Stichworte:
Motion Prediction, Deep Learning, Neural Networks, Pedestrians
Dewey-Dezimalklassifikation:
000 Informatik, Wissen, Systeme
Kongress- / Buchtitel:
Robotics and Automation Letters (RA-L)
Jahr:
2020
Volltext / DOI:
doi:10.1109/LRA.2020.2969925
 BibTeX