Haptische Intelligenz Embodied Vision Robotics Conference Paper 2025

Visuo-Tactile Object Pose Estimation for a Multi-Finger Robot Hand with Low-Resolution In-Hand Tactile Sensing

Thumb ticker sm dsc00314
Embodied Vision
Research Associate
Thumb ticker sm gr%c3%bcninger felix 400
Robotics
  • Research Engineer
Thumb ticker sm ben
Haptische Intelligenz
  • Postdoctoral Researcher
no image
Embodied Vision
Thumb ticker sm thumb ticker kjk 2024
Haptische Intelligenz
Director
Thumb ticker sm profilepic stueckler
Embodied Vision
Max Planck Research Group Leader

Accurate 3D pose estimation of grasped objects is an important prerequisite for robots to perform assembly or in-hand manipulation tasks, but object occlusion by the robot's own hand greatly increases the difficulty of this perceptual task. Here, we propose that combining visual information with binary, low-resolution tactile contact measurements from across the interior surface of an articulated robotic hand can mitigate this issue. The visuo-tactile object-pose-estimation problem is formulated probabilistically in a factor graph. The pose of the object is optimized to align with the two kinds of measurements using a robust cost function to reduce the influence of outlier readings. The advantages of the proposed approach are first demonstrated in simulation: a custom 15-DOF robot hand with one binary tactile sensor per link grasps 17 YCB objects while observed by an RGB-D camera. This low-resolution in-hand tactile sensing significantly improves object-pose estimates under high occlusion and also high visual noise. We also show these benefits through grasping tests with a preliminary real version of our tactile hand, obtaining reasonable visuo-tactile estimates of object pose at approximately 12.9 Hz on average.

Author(s): Lukas Mack and Felix Grüninger and Benjamin A. Richardson and Regine Lendway and Katherine J. Kuchenbecker and Joerg Stueckler
Book Title: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)
Year: 2025
Month: May
Bibtex Type: Conference Paper (inproceedings)
Address: Atlanta, USA
State: Accepted

BibTex

@inproceedings{Mack25-ICRA-Visuo,
  title = {Visuo-Tactile Object Pose Estimation for a Multi-Finger Robot Hand with Low-Resolution In-Hand Tactile Sensing},
  booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)},
  abstract = {Accurate 3D pose estimation of grasped objects is an important prerequisite for robots to perform assembly or in-hand manipulation tasks, but object occlusion by the robot's own hand greatly increases the difficulty of this perceptual task. 
  Here, we propose that combining visual information with binary, low-resolution tactile contact measurements from across the interior surface of an articulated robotic hand can mitigate this issue. The visuo-tactile object-pose-estimation problem is formulated probabilistically in a factor graph. The pose of the object is optimized to align with the two kinds of measurements using a robust cost function to reduce the influence of outlier readings. The advantages of the proposed approach are first demonstrated in simulation: a custom 15-DOF robot hand with one binary tactile sensor per link grasps 17 YCB objects while observed by an RGB-D camera. This low-resolution in-hand tactile sensing significantly improves object-pose estimates under high occlusion and also high visual noise. 
  We also show these benefits through grasping tests with a preliminary real version of our tactile hand, obtaining reasonable visuo-tactile estimates of object pose at approximately 12.9 Hz on average.},
  address = {Atlanta, USA},
  month = may,
  year = {2025},
  slug = {mack25-icra-visuo},
  author = {Mack, Lukas and Gr{\"u}ninger, Felix and Richardson, Benjamin A. and Lendway, Regine and Kuchenbecker, Katherine J. and Stueckler, Joerg},
  month_numeric = {5}
}