Acquisition and Application of a Tactile Database

Author

Schö, Matthias ; Ritter, Helge ; Heidemann, Gunther

Author_Institution

Fac. of Technol., Bielefeld Univ.

fYear

2007

fDate

10-14 April 2007

Firstpage

1517

Lastpage

1522

Abstract

We present a database of 2D pressure profile time series as a testbed for tactile object and surface recognition. The tactile database captures the surfaces of household and toy objects by moving a 2D pressure sensor mounted to an industrial robot arm around the objects using real-time trajectory calculation. Thus, it represents different "views" of the objects in a similar way as the well known Columbia Object Image Library (COIL) captures different views of an object by a camera. As a first application, objects in the database are classified using a neural network architecture.

Keywords

image recognition; manipulators; neural nets; tactile sensors; time series; visual databases; 2D pressure profile time series; 2D pressure sensor; camera; image database; industrial robot arm; neural network architecture; pattern recognition; robot tactile systems; surface recognition; tactile database; tactile object; trajectory calculation; Cameras; Image databases; Libraries; Neural networks; Robot sensing systems; Robot vision systems; Service robots; Tactile sensors; Testing; Toy industry; Image databases; Neural Networks; Pattern Recognition; Robot tactile systems; Tactile systems (non-biological);

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 2007 IEEE International Conference on

Conference_Location

Roma

ISSN

1050-4729

Print_ISBN

1-4244-0601-3

Electronic_ISBN

1050-4729

Type

conf

DOI

10.1109/ROBOT.2007.363539

Filename

4209303