Fast robotic pencil drawing based on image evolution by means of genetic algorithm
Michal Adamik, Jozef Goga, Jarmila Pavlovičová, Andrej Babinec, Ivan Sekaj
Abstract
Even if pencil drawing is the basic method of human artistic expression, it remains at the forefront of scientific attention in the field of robotics, which focuses mainly on painting. Although various methods of artistic robotic drawing have been developed in the past, the results are not always satisfactory. The vast majority of existing systems focus only on sketches, and detailed pencil drawings are time-consuming. In this article, we present a novel general robotic system for creating realistic pencil drawings based on image evolution. We show that by procedural image generation approach using genetic algorithms, we can create realistic drawings with an element of machine creativity. Furthermore, we show that the image approximation using even simple line segments leads to aesthetic and fast drawings. Finally, we describe a hardware solution using an industrial robot, a software implementation, and preliminary experimental results.