Neural Network Aided Potential Field Approach for Pedestrian Prediction

Particke F, Zhou J, Hiller M, Hofmann C, Thielecke J (2019)

Publication Type: Conference contribution

Publication year: 2019

Publisher: Institute of Electrical and Electronics Engineers Inc.

Conference Proceedings Title: 2019 Symposium on Sensor Data Fusion: Trends, Solutions, Applications, SDF 2019

Event location: Bonn DE

ISBN: 9781728150857

DOI: 10.1109/SDF.2019.8916659

Abstract

Autonomous driving is one of the key challenges in recent time. As pedestrians are the most vulnerable traffic participants, collisions with pedestrians have to be avoided under all circumstances. Hence, prediction of pedestrian trajectories is of high interest for automated vehicles. For this purpose, a plethora of algorithms has been proposed to model the pedestrian in the last decades, reaching from simple kinematic models to advanced microscopic models. In addition, the machine learning community started to learn the behavior of pedestrians and showed major improvements in complex scenarios or unexpected situations. However, as most of the machine learning algorithms are treated as black boxes, the safeguarding of the software is one key challenge which has to be solved. This contribution proposes to combine classic modeling of pedestrians with machine learning algorithms by learning the model errors between a simple physical model and real data. In particular, it is proposed to combine a physical model based on potential fields with a neural network to predict the future behavior of pedestrians. It is shown that the combined approach outperforms the physical model in learnable areas, whereas the physical model without the neural network is more robust in areas where almost no training data is available. In addition, different structures of neural networks are analyzed.

Authors with CRIS profile

Florian Particke Lehrstuhl für Informationstechnik mit dem Schwerpunkt Kommunikationselektronik (Stiftungslehrstuhl) (LIKE) Jiaren Zhou Lehrstuhl für Informationstechnik mit dem Schwerpunkt Kommunikationselektronik (Stiftungslehrstuhl) (LIKE) Markus Hiller Lehrstuhl für Informationstechnik mit dem Schwerpunkt Kommunikationselektronik (Stiftungslehrstuhl) (LIKE) Christian Hofmann Lehrstuhl für Informationstechnik mit dem Schwerpunkt Kommunikationselektronik (Stiftungslehrstuhl) (LIKE) Jörn Thielecke Professur für Informationstechnik (Schwerpunkt Ortsbestimmung und Navigation)

How to cite

APA:

Particke, F., Zhou, J., Hiller, M., Hofmann, C., & Thielecke, J. (2019). Neural Network Aided Potential Field Approach for Pedestrian Prediction. In 2019 Symposium on Sensor Data Fusion: Trends, Solutions, Applications, SDF 2019. Bonn, DE: Institute of Electrical and Electronics Engineers Inc..

MLA:

Particke, Florian, et al. "Neural Network Aided Potential Field Approach for Pedestrian Prediction." Proceedings of the 2019 Symposium on Sensor Data Fusion: Trends, Solutions, Applications, SDF 2019, Bonn Institute of Electrical and Electronics Engineers Inc., 2019.

BibTeX: Download