Empowering Children to Create AI-Enabled Augmented Reality Experiences
🤖 AI Summary
Current AI-augmented reality (AR) research predominantly treats children as passive consumers, overlooking their potential as content creators. To address this gap, we introduce Capybara—the first AR-AI integrated visual programming platform designed specifically for children. Capybara innovatively incorporates AI capabilities including text-to-3D model generation, automatic skeletal rigging, human pose estimation, and object recognition, enabling children to design personalized mixed-reality interactions without coding. Its low-cognitive-load graphical interface and natural language–guided workflow substantially lower the barrier to creative authoring. A user study with 20 children from the U.S. and Argentina demonstrated that participants independently developed diverse interactive AR applications within an average of 35 minutes. Results confirm the platform’s usability, effectiveness in fostering creative agency, and cross-cultural applicability. This work establishes a novel paradigm for cultivating children’s computational thinking and designing AI-native educational tools.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
Enables children to create AI-driven AR content
Transforms children from consumers to creators of AR
Bridges virtual and physical worlds via interactive AR
Innovation
Methods, ideas, or system contributions that make the work stand out.
AR-based AI visual programming for children
Text-to-3D generative AI for virtual characters
Vision-based AI for interactive physical-virtual behaviors
🔎 Similar Papers
No similar papers found.
