Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hetzel, Manuel, Reichert, Hannes, Doll, Konrad, Sick, Bernhard
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.06905
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913539885629440
author Hetzel, Manuel
Reichert, Hannes
Doll, Konrad
Sick, Bernhard
author_facet Hetzel, Manuel
Reichert, Hannes
Doll, Konrad
Sick, Bernhard
contents Autonomous systems, like vehicles or robots, require reliable, accurate, fast, resource-efficient, scalable, and low-latency trajectory predictions to get initial knowledge about future locations and movements of surrounding objects for safe human-machine interaction. Furthermore, they need to know the uncertainty of the predictions for risk assessment to provide safe path planning. This paper presents a lightweight method to address these requirements, combining Long Short-Term Memory and Mixture Density Networks. Our method predicts probability distributions, including confidence level estimations for positional uncertainty to support subsequent risk management applications and runs on a low-power embedded platform. We discuss essential requirements for human trajectory prediction in autonomous vehicle applications and demonstrate our method's performance using multiple traffic-related datasets. Furthermore, we explain reliability and sharpness metrics and show how important they are to guarantee the correctness and robustness of a model's predictions and uncertainty assessments. These essential evaluations have so far received little attention for no good reason. Our approach focuses entirely on real-world applicability. Verifying prediction uncertainties and a model's reliability are central to autonomous real-world applications. Our framework and code are available at: https://github.com/kav-institute/mdn_trajectory_forecasting.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06905
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reliable Probabilistic Human Trajectory Prediction for Autonomous Applications
Hetzel, Manuel
Reichert, Hannes
Doll, Konrad
Sick, Bernhard
Computer Vision and Pattern Recognition
Autonomous systems, like vehicles or robots, require reliable, accurate, fast, resource-efficient, scalable, and low-latency trajectory predictions to get initial knowledge about future locations and movements of surrounding objects for safe human-machine interaction. Furthermore, they need to know the uncertainty of the predictions for risk assessment to provide safe path planning. This paper presents a lightweight method to address these requirements, combining Long Short-Term Memory and Mixture Density Networks. Our method predicts probability distributions, including confidence level estimations for positional uncertainty to support subsequent risk management applications and runs on a low-power embedded platform. We discuss essential requirements for human trajectory prediction in autonomous vehicle applications and demonstrate our method's performance using multiple traffic-related datasets. Furthermore, we explain reliability and sharpness metrics and show how important they are to guarantee the correctness and robustness of a model's predictions and uncertainty assessments. These essential evaluations have so far received little attention for no good reason. Our approach focuses entirely on real-world applicability. Verifying prediction uncertainties and a model's reliability are central to autonomous real-world applications. Our framework and code are available at: https://github.com/kav-institute/mdn_trajectory_forecasting.
title Reliable Probabilistic Human Trajectory Prediction for Autonomous Applications
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.06905