Skip to Main content Skip to Navigation
Conference papers

Visual Control Using Projective Kinematics

Andreas Ruf 1 Frederick Martin 1 Bart Lamiroy 1 Radu Horaud 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a new approach to controlling a robot from video-feedback. In contrast to classical approaches, the entire system is modeled by means of projective geometry. For the robot?s geometry in particular, we introduce a new formalism ?projective kinematics?. As a result, motions in joint- and image-space can be related without metric calibration, and a corresponding visual control law can be derived. We present experiments for projective robot calibration and visual servoing, both using uncalibrated cameras.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00590124
Contributor : Team Perception <>
Submitted on : Tuesday, May 3, 2011 - 9:24:32 AM
Last modification on : Friday, June 26, 2020 - 4:04:03 PM
Long-term archiving on: : Thursday, August 4, 2011 - 2:56:48 AM

File

rufISRR99.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00590124, version 1

Collections

IMAG | CNRS | INRIA | UGA

Citation

Andreas Ruf, Frederick Martin, Bart Lamiroy, Radu Horaud. Visual Control Using Projective Kinematics. 9th International Symposium on Robotics Research (ISRR '99), Oct 1999, Snowbird, United States. pp.97-104. ⟨inria-00590124⟩

Share

Metrics

Record views

235

Files downloads

199