“As my artist’s statement explains, my work is utterly incomprehensible and is therefore full of deep significance”
CALVIN, CALVIN AND HOBBES
MEET DRAWYER
​Well--maybe hopefully not utterly incomprehensible. Meet Drawyer, a Sawyer fitted with a fat Sharpie that can draw any image you feed it. Simple line drawing? Got it. A picture of a bowl of fruit? Easy. Maybe Drawyer’s drawings aren’t perfect, but you can grant a robot a little bit of artistic license, can’t you?
​
Welcome to a new era of art! An era fueled by algorithms: mapping muse to canvas, finding paths of lines, and executing via robot. You think art is meant only for humans to create? O’Keeffe it to yourself; that’s a load of Pollocks. It’s okay; we’ve Goya back. We’ll introduce you to Drawyer and robot-created art, one step at a time.
​
AN INTRODUCTION
​​In order to get Sawyer to produce some beautiful art, we needed to tackle a number of subproblems, ranging from computer vision to inverse kinematics. In particular, we needed not only to detect edges in an image, but also to determine when nearby edges should be treated as part of a single curve and to plan paths between points to approximate these curves.
​
Although it is unlikely that a drawing robot will be needed for real-life applications anytime soon, the above problems and techniques are relevant to many practical issues. For example, object detection and segmentation would be essential for packaging robots and self-driving vehicles, while path planning would be necessary for assistive remote surgical robots.
​
In the distant era of widespread machine-brain interfaces, drawing robots could provide the essential link between artist vision and execution. Imagine the thousands of potential Monets or van Goghs who could never realize their artistic aspirations because they lacked the time or willpower to practice painting or drawing.