• Corpus ID: 239024380

Active Tapping via Gaussian Process for Efficient Unknown Object Surface Reconstruction

  title={Active Tapping via Gaussian Process for Efficient Unknown Object Surface Reconstruction},
  author={Su Sun and Byung-Cheol Min},
  • Su Sun, B. Min
  • Published 18 October 2021
  • Computer Science
  • ArXiv
Object surface reconstruction brings essential benefits to robot grasping, object recognition, and object manipulation. When measuring the surface distribution of an unknown object by tapping, the greatest challenge is to select tapping positions efficiently and accurately without prior knowledge of object region. Given a searching range, we propose an active exploration method, to efficiently and intelligently guide the tapping to learn the object surface without exhaustive and unnecessary off… 

Figures from this paper


Active tactile object exploration with Gaussian processes
This paper presents an active touch strategy to efficiently reduce the surface geometry uncertainty by leveraging a probabilistic representation of object surface using a Gaussian process.
Finding safe 3D robot grasps through efficient haptic exploration with unscented Bayesian optimization and collision penalty
This paper proposes a 3D haptic exploration strategy that combines unscented Bayesian optimization with a novel collision penalty heuristic to find safe grasps in a very efficient way: while by augmenting the search-space to 3D the authors are able to find betterGrasps, the collision penalty Heuristic allows us to do so without increasing the number of exploration steps.
Active learning using mean shift optimization for robot grasping
A new robot learning framework for reproducing this ability in robot grasping using the Gaussian process regression framework and the fact that the mean-shift method provides maxima of this cost function is presented.
Artificial Tactile Sensor Structure for Surface Topography Through Sliding
An array sensor, which uses a sliding method for the precise perception of surface information, such as shapes and structures, is demonstrated and demonstrates sliding speed, pattern detection, and shape detection capabilities as well as the higher spatial resolutions allow the sensor to be utilized as an artificial tactile sensor.
Material Mapping in Unknown Environments using Tapping Sound
The goal of the proposed system is to integrate simultaneous localization and mapping (SLAM) modules and sound-based material classification to enable a mobile robot to explore an unknown environment autonomously and at the same time identify the various objects and materials in the environment.