Robert Twomey
Abstract
This project creates a visual-mental-physical circuit between a Generative Adversarial Network (GAN), a co-robotic arm, and a five-year-old child. From training images to the latent space of a GAN, through pen on paper to a live human collaborator, it establishes a series of translational stages between humans and non-humans played out through the medium of drawing. Trained on a subset of the Rhoda Kellogg Child Art Collection, the neural network at the center of this piece learns its own representations of these images. The generated results, synthetic children's drawings, are of interest both for being outside of adult conventions and learned expression-like Dubuffet's art brut or Surrealist automatism-and for how they align machine learning with the human act of learning to draw.
The project layers many kinds of agency and embodiment: from the thousands of anonymous children who produced the original artwork used as training data, through the co-robot drawing from GAN-generated imagery, to the human child's active perception and graphic response to the robot. These questions of where we search for the other; when we attribute autonomy and intelligence; and why we might wish to escape our human subjectivities speak to core issues in the design and use of AI systems. This project is one attempt to think through those questions in an embodied way.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, Three Stage Drawing Transfer: Collaborative Drawing Between a Generative Adversarial Network, Co-robotic Arm, and Five-Year-Old Child
- Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. Analyzing and Improving the Image Quality of Stylegan. Proceedings of IEEE / CVF Computer Vision and Pattern Recognition. https://doi.org/10.48550/arXiv.1912.04958Google Scholar
Cross Ref
- Rhoda Kellogg. 1969. Analyzing children's art. National Press Books, Palo Alto, Calif.Google Scholar
- Rhoda Kellogg. n.d. Rhoda Kellogg Child Art Collection. Retrieved January 21, 2022 from https://www.early-pictures.ch/kellogg/archive/en/.Google Scholar
- Tzu-Mao Li. 2022. diffvg. Retrieved April 25, 2022 from https://github.com/BachiLi/diffvg.Google Scholar
- Dennis Oppenheim. 1971. 2-Stage Transfer Drawing. Retrieved January 21, 2022 from https://www.dennisaoppenheim.org/copy-of-new-page.Google Scholar
- Tate Gallery. 2022. Art brut. Tate Gallery Glossary of Art Terms. Retrieved January 21, 2022 from https://www.tate.org.uk/art/art- terms/a/art-brut.Google Scholar
- Robert Twomey. 2022. Communion and Cohabitation. In Welcome a New Neighbor, Creative Machine. Retrieved January 21, 2022 from https://roberttwomey.com/writing/.Google Scholar
- UFACTORY. 2022. UFACTORY xArm7 co-robotic arm with 7 DOF. Retrieved January 21, 2022 from https://www.ufactory.cc/products/xarm-7-2020.Google Scholar
Index Terms
Three Stage Drawing Transfer: Collaborative Drawing Between a Generative Adversarial Network, Co-robotic Arm, and Five-Year-Old Child
Recommendations
Three stage drawing transfer: collaborative drawing between a generative adversarial network, co-robotic arm, and five-year-old child
SIGGRAPH '22: ACM SIGGRAPH 2022 Art GalleryThree Stage Drawing Transfer is an experimental human-robot performance and emerging media arts research project exploring drawing, cognition, and new possibilities for creative, embodied interactions between humans and machines. The work creates a ...
Comments