RoboArt: DALL-E and KUKA Robot Shake Hands

2023

Closed access Metadata (CSL-JSON)
DOI 10.1109/icecco58239.2023.10147156
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The use of artificial intelligence (AI) to create graphics has shown high popularity in the digital industry. Creating visuals, however, is not as stunning as creating AI-based human-like drawings on canvas, which is much more appealing in the world of aesthetics. In this article, we set a goal of teaching the robot to draw like a human artist. In this effort, the boundaries of modern art are pushed by integrating a ready-made DALL-E neural network with a KUKA robot through a CAD software module. To create 2D drawings on the canvas, a novel sort of end-effector is devised and manufactured on a 3D printer. The technique proved to be effective, as evidenced by the demonstration of a robot that draws unique images on canvas using human-like gestures.