Abstract

We present an approach to generate rapid and fluid drawing movements on a compliant Baxter robot, by taking advantage of the kinematic redundancy and torque control capabilities of the robot. We concentrate on the task of reproducing graffiti-stylised letter-forms with a marker. For this purpose, we exploit a compact lognormal-stroke based representation of movement to generate natural drawing trajectories. An Expectation-Maximisation (EM) algorithm is used to iteratively improve tracking performance with low gain feedback control. The resulting system captures the aesthetic and dynamic features of the style under investigation and permits its reproduction with a compliant controller that is safe for users surrounding the robot.

Bibtex reference

@inproceedings{Berio16IROS,
  author="Berio, D. and Calinon, S. and Fol Leymarie, F.",
  title="Learning dynamic graffiti strokes with a compliant robot",
  booktitle="Proc. {IEEE/RSJ} Intl Conf. on Intelligent Robots and Systems ({IROS})",
  year="2016",
  month="Oct.",
  address="Daejeon, Korea",
  pages="3981--3986"
}

Video

When Baxter is taking a rest from its daily duty working in universities and factories across the globe, the robot is also cultivating an artistic passion! The proposed video demonstrates the skilled capability of Baxter in 2D drawing and 3D light painting tasks. The robot draws computer generated calligraphy and graffiti art with a marker on paper, or traces contours and shapes in the air in a robotized “light painting” performance. The traces are generated through physiologically plausible models of handwriting motions, which are used to guide the motion of the robot. We exploit the kinematic redundancy, compliance and torque control capabilities of Baxter to generate rapid and fluid drawing movements.

The video builds upon our ongoing research that aims at reproducing a variety of drawing and painting styles on robotic platforms. We are interested in the process and dynamics of human motion that underlie the production of various forms of art, and we are developing computational models that will enable the transfer of complex and personal artistic skills to robots. We envision the use of Baxter in human-robot collaboration scenarios, in which the bimanual robot will work alongside with artists, by sharing the same canvas, learning from their gestures, and serving as an innovative tool to foster creativity.

Video credit: Daniel Berio

Go back to the list of publications