Probabilistic representation of 3D object shape by in-hand exploration

  title={Probabilistic representation of 3D object shape by in-hand exploration},
  author={Diego Resende Faria and Ricardo Martins and Jorge Lobo and J. Dias},
  journal={2010 IEEE/RSJ International Conference on Intelligent Robots and Systems},
  • D. Faria, Ricardo Martins, J. Dias
  • Published 3 December 2010
  • Computer Science
  • 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems
This work presents a representation of 3D object shape using a probabilistic volumetric map derived from in-hand exploration. The exploratory procedure is based on contour following through the fingertip movements on the object surface. We first consider the simple case of having single hand exploration of a static object. The cumulative pose data provides a 3D point cloud that is quantized to the probabilistic volumetric map. For each voxel we have a probability distribution for the occupancy… 

Figures from this paper

A Probabilistic Framework to Detect Suitable Grasping Regions on Objects
This work relies on a probabilistic framework to search for suitable grasping regions on objects based on occupancy grid representation that deals with the sensor uncertainty allowing later the decomposition of the object global shape into components.
Identifying objects from hand configurations during in-hand exploration
  • D. Faria, J. Lobo, J. Dias
  • Psychology, Computer Science
    2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)
  • 2012
This work uses hand configuration and contact points during in-hand object exploration to identify the manipulated objects and selects a set of the most probable objects from a database.
Iterative Surface Mapping Using Local Geometry Approximation with Sparse Measurements During Robotic Tooling Tasks
It is shown that the surface geometry can be mapped reasonably accurate with a mean absolute error below 1 mm, and different update strategies for the grid points, where the approximation is valid to consider the locality of the planar approximation are proposed.
Enhancing visual perception of shape through tactile glances
A probabilistic approach for learning object models based on visual and tactile perception through physical interaction with an object that is capable of choosing a small number of touches to construct object models similar to real object shapes and to determine similarities among acquired models.
Bimanual compliant tactile exploration for grasping unknown objects
This paper presents the first results on bimanual compliant tactile exploration, with the goal to identify objects and grasp them, using an exploration strategy to guide the motion of the two arms and fingers along the object.
Knowledge-based reasoning from human grasp demonstrations for robot grasp synthesis
Incrementally Learning Objects by Touch: Online Discriminative and Generative Models for Tactile-Based Recognition
This work proposes and compares two novel discriminative and generative tactile learners that produce probability distributions over objects during object grasping/ palpation using the sparse online infinite Echo-State Gaussian process, and indicates that tactile signals are highly relevant for making accurate object classifications.
Representation of 3D Space and Sensor Modelling Within a Probabilistic Framework
For living organisms, perception can be defined as a set of cognitive processes, in the sense that it consists in the processing of sensorial data in order to generate essential information with the


Grasp Exploration for 3D Object Shape Representation Using Probabilistic Map
In this work, Electromagnetic motion tracking sensors are used on the fingers for object contour following to acquire the 3D points to represent its shape using a probabilistic volumetric map using the object referential for its representation.
3D hand trajectory segmentation by curvatures and hand orientation for classification through a probabilistic approach
  • D. Faria, J. Dias
  • Computer Science
    2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2009
An application to estimate and classify two possible types of grasping by the reach-to-grasp movements performed by humans, important to understand some human behaviors before the object manipulation and can be used to endow a robot with autonomous capabilities.
Grasping movements recognition in 3D space using a Bayesian approach
An automated system is developed to estimate and recognize two possible types of grasping by the hand movements performed by humans that are tracked by a magnetic tracking device, which can be used to endow a robot with autonomous capabilities.
Haptic exploration for 3D shape reconstruction using five-finger hands
A framework for haptic exploration which is intended for use with both, a five-finger humanoid robot hand as well as with a human hand and shape estimation of 2D and 3D objects by the human hand is presented.
Haptic object recognition using a multi-fingered dextrous hand
  • P. Allen, K. Roberts
  • Computer Science, Psychology
    Proceedings, 1989 International Conference on Robotics and Automation
  • 1989
An approach to using tactile data in conjunction with the dextrous hand to build a library of grasping and exploration primitives that can be used in recognizing and grasping more complex multipart objects is proposed.
Robust shape recovery for sparse contact location and normal data from haptic exploration
This paper describes a robust approach for 3D shape recovery using superquadric functions, which makes use of both contact location and normal information and compares to other relevant estimation techniques using representative synthetic contact data.
Haptic exploration of fine surface features
  • A. Okamura, M. Cutkosky
  • Computer Science
    Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C)
  • 1999
This work considers the detection of small surface features, such as ridges and bumps, on the surface of an object during dextrous manipulation and presents simulated and experimental results for feature detection using a hemispherical fingertip equipped with an optical tactile sensor.
Haptic exploration of objects with rolling and sliding
Simulations and experiments with a two-fingered hand were conducted to investigate the robustness of the approach for exploring various object shapes.
Using occupancy grids for mobile robot perception and navigation
An approach to robot perception and world modeling that uses a probabilistic tesselated representation of spatial information called the occupancy grid, a multidimensional random field that maintains stochastic estimates of the occupancy state of the cells in a spatial lattice is reviewed.
Recognition-by-components: a theory of human image understanding.
Recognition-by-components (RBC) provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition.