Active tactile object exploration with Gaussian processes
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4925-4930
Abstract
Accurate object shape knowledge provides important information for performing stable grasping and dexterous manipulation. When modeling an object using tactile sensors, touching the object surface at a fixed grid of points can be sample inefficient. In this paper, we present an active touch strategy to efficiently reduce the surface geometry uncertainty by leveraging a probabilistic representation of object surface. In particular, we model the object surface using a Gaussian process and use the associated uncertainty information to efficiently determine the next point to explore. We validate the resulting method for tactile object surface modeling using a real robot to reconstruct multiple, complex object surfaces.Keywords
This publication has 26 references indexed in Scilit:
- Multimodal Tactile Sensor2014
- Fusing visual and tactile sensing for 3-D object reconstruction while grasping2013
- Artificial Skin Ridges Enhance Local Tactile Shape DiscriminationSensors, 2011
- Tactile sensing for dexterous in-hand manipulation in robotics—A reviewSensors and Actuators A: Physical, 2011
- Slip detection and control using tactile and force sensorsIEEE/ASME Transactions on Mechatronics, 2000
- A Limited Memory Algorithm for Bound Constrained OptimizationSIAM Journal on Scientific Computing, 1995
- Lipschitzian optimization without the Lipschitz constantJournal of Optimization Theory and Applications, 1993
- Dynamic tactile sensing: perception of fine surface features with stress rate sensingIEEE Transactions on Robotics and Automation, 1993
- The Kinematics of Contact and GraspThe International Journal of Robotics Research, 1988
- A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of NoiseJournal of Basic Engineering, 1964