Image credit: Unsplash

Programmation offline d’une cellule robotisée à l’aide de techniques innovantes

Image credit: Unsplash

Programmation offline d’une cellule robotisée à l’aide de techniques innovantes

Abstract

The use of anthropomorphic robots for tiles decoration, painting them, links the repeatability and the high rhythm of production with a precise and artistic movement. For programming such a robot dynamic, learning movements must be done in an interactive way, by releasing the user from a conventional point-by-point programming. In this project, a smart use of three cameras, calibrated and coupled in stereoscopy, allows the programmer to register the paintbrush movements. During a registration, the paintbrush used by the designer is sensorized with reflector spheres, of which the positions in space are known and traced using epipolar geometry, basic concept of stereoscopy. Through the spheres positions and a « Rigid Registration » algorithm, we are able to find the paintbrush geometry in space and therefore to find the position and the orientation of brush tip. Filtering data and registering painting sequences like models for the robot allows it to replicate the painting process, with a precision of about a millimeter.

Publication
Master Thesis defense
Avatar
Silvio Giancola
Postdoctoral Research Fellow

Silvio Giancola is a Postdoctoral Research Fellow in Computer Vision at King Abdullah University of Science and Technology (KAUST), working under the supervision of Prof. Bernard Ghanem in the Image and Video Understanding Laboratory (IVUL), part of the Visual Computing Center (VCC).