Classifying object-hand and object-world interactions using dynamic tactile array sensing

Placeholder Show Content

Abstract/Contents

Abstract
The manipulation of objects held in a robotic hand or gripper is typically accompanied by events such as slippage, between the fingers and a grasped object or between that object and external surfaces. Humans can identify such events as occurring at one or the other of these interface using a combination of superficial and deep mechanoreceptors. These events excite the mechanoreceptors differently, allowing them to be reacted to as appropriate. In robotic systems however, slip research has primarily focused on the detection of slip occurring between the hand and the held object, without specific consideration of slip at other interfaces. In order to extend the capabilities of robotic systems, we propose two simple features which can be extracted from dynamic tactile array data and used individually to discriminate between slips occurring at these two interfaces. The first is motivated by the function and response of human mechanoreceptors, while the second is based on an analysis of the interaction between a held object in contact with a soft fingertip containing embedded sensors. The performance and generalizability of these two features are verified with extensive testing. Three separate sensing suites are used, with a total of five different sensor transduction technologies. In addition, the manipulation, texture, speed, and grip force are varied from trial to trial to attempt to capture the wide variety of conditions that can occur during general grasping and manipulation tasks. Both features demonstrate greater than 85% accuracy in identifying the location of slip, independent of these varying contact conditions.

Description

Type of resource text
Form electronic; electronic resource; remote
Extent 1 online resource.
Publication date 2013
Issuance monographic
Language English

Creators/Contributors

Associated with Heyneman, Barrett
Associated with Stanford University, Department of Mechanical Engineering.
Primary advisor Cutkosky, Mark R
Thesis advisor Cutkosky, Mark R
Thesis advisor Khatib, Oussama
Thesis advisor Mitiguy, Paul
Advisor Khatib, Oussama
Advisor Mitiguy, Paul

Subjects

Genre Theses

Bibliographic information

Statement of responsibility Barrett Heyneman.
Note Submitted to the Department of Mechanical Engineering.
Thesis Thesis (Ph.D.)--Stanford University, 2013.
Location electronic resource

Access conditions

Copyright
© 2013 by Barrett Emerson Heyneman
License
This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).

Also listed in

Loading usage metrics...