Visual Computing

University of Konstanz
MDPI Arts

Self-Improving Robotic Brushstroke Replication

J. Gülzow, L. Grayver, O. Deussen
Teaser of Self-Improving Robotic Brushstroke Replication

Brushstrokes are improved through automatic experimentation.

Material

Paper (.pdf, 86.4MB) Publication in MDPI Arts

Abstract

Painting robots, like e-David, are currently unable to create precise strokes in their paintings. We present a method to analyse given brushstrokes and extract their trajectory and width using a brush behaviour model and photographs of strokes painted by humans. Within the process, the robot experiments autonomously with different brush trajectories to improve the reproduction results, which are precise within a few millimetres for strokes up to 100 millimetres length. The method can be generalised to other robotic tasks with imprecise tools and visible results, like polishing or milling.

Gallery

Gorgeous gallery caption!

The main painting robot.

The mobile demonstration robot on an exhibiton in Zürich.

A piece of human writing.

An automatic reproduction of writing, as produced by the robot.

BibTeX

@inproceedings{Guelzow2018RoboticBrushstrokeReplication,
  author       = {J. Gülzow, L. Grayver, O. Deussen},
  doi          = {10.3390/arts7040084},
  journal      = {MDPI Arts},
  keywords     = {robotics;painting;art;generative method;brush},
  month        = {nov},
  number       = {4},
  organization = {Multidisciplinary Digital Publishing Institute},
  pages        = {84},
  title        = {Self-Improving Robotic Brushstroke Replication},
  url          = {http://graphics.uni-konstanz.de/publikationen/Guelzow2018RoboticBrushstrokeReplication},
  volume       = {7},
  year         = {2018}
}