Hierarchical System to Predict Human Motion and Intentions for Efficient and Safe Human-Robot Interaction in Industrial Environments

Andrey Rudenko, Yufei Zhu, Tiago Rodrigues de Almeida, Tim Schreiter, Luca Castri, Nicola Belotto, Narunas Vaskevicius, Luigi Palmieri, Martin Magnusson and Achim J Lilienthal
Proceedings of German Robotics Conference 2025

 

Abstract

In this paper we present a hierarchical motion and intent prediction system prototype, designed to efficiently operate in complex environments while safely handling risks arising from diverse and uncertain human motion and activities. Our system uses an array of advanced cues to describe human motion and activities, including generalized motion patterns, full-body poses, heterogeneous agent types and causal contextual factors that influence human behavior.

@inproceedings{Rudenko1941552,
   author = {Rudenko, Andrey and Zhu, Yufei and Almeida, Tiago Rodrigues de and Schreiter, Tim and Castri, Luca and Belotto, Nicola and Linder, Timm and Vaskevicius, Narunas and Palmieri, Luigi and Magnusson, Martin and Lilienthal, Achim J.},
   booktitle = {1st German Robotics Conference : },
   institution = {Örebro University, School of Science and Technology},
   institution = {Bosch Corporate Research, Germany},
   institution = {Technical University of Munich, MIRMI, Chair of Perception for Intelligent Systems, Germany},
   institution = {University of Lincoln, UK},
   institution = {University of Lincoln, UK; University of Padua, Italy},
   institution = {Bosch Corporate Research, Germany},
   institution = {Bosch Corporate Research, Germany},
   institution = {Bosch Corporate Research, Germany},
   title = {Hierarchical System to Predict Human Motion and Intentions for Efficient and Safe Human-Robot Interaction in Industrial Environments},
   abstract = {In this paper we present a hierarchical motion and intent prediction system prototype, designed to efficiently operate in complex environments while safely handling risks arising from diverse and uncertain human motion and activities. Our system uses an array of advanced cues to describe human motion and activities, including generalized motion patterns, full-body poses, heterogeneous agent types and causal contextual factors that influence human behavior. },
   year = {2025}
}