Teachless teach-repeat: Toward Vision-Based Programming of Industrial Robots

Mathias Perrollaz 1 Sami Khorbotly 2 Amber Cool 2 John-David Yoder 2 Eric Baumgartner 2
1 E-MOTION - Geometry and Probability for Motion and Action
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
2 Ohio Northern University
Abstract : Modern programming of industrial robots is often based on the teach-repeat paradigm: a human operator places the robot in many key positions, for teaching its task. Then the robot can repeat a path defined by these key positions. This paper proposes a vision-based approach for the automation of the teach stage. The approach relies on a constant autocalibration of the system. Therefore, the only requirement is a precise geometrical description of the part to process. The realism of the approach is demonstrated through the emulation of a glue application process with an industrial robot. Results in terms of precision are very promising.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download
https://hal.inria.fr/hal-00671209
Contributor : Mathias Perrollaz <>
Submitted on : Wednesday, May 16, 2012 - 7:00:08 AM
Last modification on : Friday, October 25, 2019 - 1:31:51 AM
Long-term archiving on: Wednesday, December 14, 2016 - 6:37:17 AM

File

ICRA2012_teachRepeat_Final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00671209, version 1

Collections

CNRS | INRIA | LIG | UGA | LIG_SIC_E-MOTION

Citation

Mathias Perrollaz, Sami Khorbotly, Amber Cool, John-David Yoder, Eric Baumgartner. Teachless teach-repeat: Toward Vision-Based Programming of Industrial Robots. IEEE International Conference on Robotics and Automation, May 2012, St Paul, Minnesota, United States. ⟨hal-00671209⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

602

Files downloads

617

 

 

Contact

archive-ouverte@inria.fr