Empowering Children to Create AI-Enabled Augmented Reality Experiences

TL;DR

This paper presents Capybara, an AI-powered AR programming environment that enables children to create and animate virtual characters and interactive experiences, fostering creativity and engagement in AR content creation.

Contribution

Introduction of Capybara, a novel visual programming environment that combines AI and AR to empower children as creators of interactive virtual experiences.

Findings

Children successfully created personalized AR experiences using Capybara.

User studies showed increased engagement and creativity among children.

Capybara effectively bridges virtual and physical interactions in AR.

Abstract

Despite their potential to enhance children's learning experiences, AI-enabled AR technologies are predominantly used in ways that position children as consumers rather than creators. We introduce Capybara, an AR-based and AI-powered visual programming environment that empowers children to create, customize, and program 3D characters overlaid onto the physical world. Capybara enables children to create virtual characters and accessories using text-to-3D generative AI models, and to animate these characters through auto-rigging and body tracking. In addition, our system employs vision-based AI models to recognize physical objects, allowing children to program interactive behaviors between virtual characters and their physical surroundings. We demonstrate the expressiveness of Capybara through a set of novel AR experiences. We conducted user studies with 20 children in the United States and Argentina. Our findings suggest that Capybara can empower children to harness AI in authoring personalized and engaging AR experiences that seamlessly bridge the virtual and physical worlds.