Academic Commons

Articles

Integration of vision and force sensors for grasping

Allen, Peter K.; Miller, Andrew T.; Oh, Paul Y.; Leibowitz, Brian S.

This paper describes a set of methods that can be used to integrate real-time external vision sensing with internal force and position sensing to estimate contact forces by the fingers of a hand. Estimating these forces and contacts is essential to performing dextrous manipulation tasks. Most robotic hands are either sensorless or lack the ability to accurately and robustly report position and force information relating to contact. By adding external vision sensing, we can complement any internal sensors to more accurately estimate forces and contact positions. Experiments are described that use real-time visual trackers in conjunction with internal strain gauges and a new tactile sensor to accurately estimate finger contacts and applied forces for a three fingered robotic hand.

Subjects

Files

Also Published In

Title
MFI '96, 1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems, December 8-11, 1996, Washington, D.C., U.S.A.
Publisher
IEEE
DOI
https://doi.org/10.1109/MFI.1996.572200

More About This Work

Academic Units
Computer Science
Published Here
November 7, 2012
Academic Commons provides global access to research and scholarship produced at Columbia University, Barnard College, Teachers College, Union Theological Seminary and Jewish Theological Seminary. Academic Commons is managed by the Columbia University Libraries.