Uncertainty-Resilient Active Intention Recognition for Robotic Assistants

Juan Carlos Saborı́o2,1, Marc Vinci1,3, Oscar Lima1,3, Sebastian Stock1, Lennart Niecksch1,3,
Martin Günther1, Alexander Sung1, Joachim Hertzberg1,3, Martin Atzmueller1,3,
1German Research Center for Artificial Intelligence (DFKI), Osnabrück, Germany. 2Osnabrück University, Joint Lab for AI & DS, Germany. 3Osnabrück University, Institute of Computer Science, Germany.
Paper arXiv Video Code

Abstract

Purposeful behavior in robotic assistants requires the integration of multiple components and technological advances. Often, the problem is reduced to recognizing explicit prompts, which limits autonomy, or is oversimplified through assumptions such as near-perfect information. We argue that a critical gap remains unaddressed – specifically, the challenge of reasoning about the uncertain outcomes and perception errors inherent to human intention recognition. In response, we present a framework designed to be resilient to uncertainty and sensor noise, integrating real-time sensor data with a combination of planners. Centered around an intention-recognition POMDP, our approach addresses cooperative planning and acting under uncertainty. Our integrated framework has been successfully tested on a physical robot with promising results.

Video

BibTeX

@inproceedings{pub15929,
  author       = {Saborio, J. C. and Vinci, M. and Lima, O. and Stock, S. and Niecksch, L. and G{\"u}nther, M. and Sung, A. and Hertzberg, J. and Atzmueller, M.},
  title        = {Uncertainty-Resilient Active Intention Recognition for Robotic Assistants},
  booktitle    = {2025 European Conference on Mobile Robots. European Conference on Mobile Robots (ECMR-2025), September 3-5, Padua, Italy}
  year         = {2025},
  publisher    = {IEEE},
}