skip to main content


Title: AI Meets Holographic Pepper’s Ghost: A Co-Creative Public Dance Experience
In this demonstration, we present a holographic projected version of LuminAI, which is an interactive art installation that allows participants to collaborate with an AI dance partner by improvising movements together. By utilizing a mix of a top-down and bottom-up approach, we seek to understand embodied co-creativity in an improvisational dance setting to better develop the design of the modular AI agent to creatively collaborate with a dancer. The purpose of this demonstration is to describe the five-module agent design and investigate how we can design an immersive experience that is design-efficient, portable, light, and duo-user participation. Through this installation in an imitated black box space, audience members and dancers engage in an immersive co-creative dance experience, inspiring discussion on the limitless applications of dance and technology in the realms of learning, training, and creativity.  more » « less
Award ID(s):
2123597
PAR ID:
10461749
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
DIS '23 Companion: Companion Publication of the 2023 ACM Designing Interactive Systems Conference
Page Range / eLocation ID:
274 to 278
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Engineering educators have increasingly sought strategies for integrating the arts into their curricula. The primary objective of this integration varies, but one common objective is to improve students’ creative thinking skills. In this paper, we sought to quantify changes in student creativity that resulted from participation in a mechanical engineering course targeted at integrating engineering, technology, and the arts. The course was team taught by instructors from mechanical engineering and art. The art instructor introduced origami principles and techniques as a means for students to optimize engineering structures. Through a course project, engineering student teams interacted with art students to perform structural analysis on an origami-based art installation, which was the capstone project of the art instructor’s undergraduate origami course. Three engineering student teams extended this course project to collaborate with the art students in the final design and physical installation. 
    more » « less
  2. Generative, ML-driven interactive systems have the potential to change how people interact with computers in creative processes - turning tools into co-creators. However, it is still unclear how we might achieve effective human-AI collaboration in open-ended task domains. There are several known challenges around communication in the interaction with ML-driven systems. An overlooked aspect in the design of co-creative systems is how users can be better supported in learning to collaborate with such systems. Here we reframe human-AI collaboration as a learning problem: Inspired by research on team learning, we hypothesize that similar learning strategies that apply to human-human teams might also increase the collaboration effectiveness and quality of humans working with co-creative generative systems. In this position paper, we aim to promote team learning as a lens for designing more effective co-creative human-AI collaboration and emphasize collaboration process quality as a goal for co-creative systems. Furthermore, we outline a preliminary schematic framework for embedding team learning support in co-creative AI systems. We conclude by proposing a research agenda and posing open questions for further study on supporting people in learning to collaborate with generative AI systems. 
    more » « less
  3. Analyzing dance moves and routines is a foundational step in learning dance. Videos are often utilized at this step, and advancements in machine learning, particularly in human-movement recognition, could further assist dance learners. We developed and evaluated a Wizard-of-Oz prototype of a video comprehension tool that offers automatic in-situ dance move identification functionality. Our system design was informed by an interview study involving 12 dancers to understand the challenges they face when trying to comprehend complex dance videos and taking notes. Subsequently, we conducted a within-subject study with 8 Cuban salsa dancers to identify the benefits of our system compared to an existing traditional feature-based search system. We found that the quality of notes taken by participants improved when using our tool, and they reported a lower workload. Based on participants’ interactions with our system, we offer recommendations on how an AI-powered span-search feature can enhance dance video comprehension tools. 
    more » « less
  4. The demand is growing for a populace that is AI literate; such literacy centers on enabling individuals to evaluate, collaborate with, and effectively use AI. Because the middle school years are a critical time for developing youths’ perceptions and dispositions toward STEM, creating engaging AI learning experiences for middle grades students (ages 11 to 14) is paramount. The need for providing enhanced access to AI learning opportunities is especially pronounced in rural areas, which are typically underserved and underresourced. Inspired by prior research that game design holds significant potential for cultivating student interest and knowledge in computer science, we are designing, developing, and iteratively refining an AI-centered game development environment that infuses AI learning into game design activities. In this work, we review design principles for game design interventions focused on middle grades computer science education and explore how to introduce AI learning experiences into interactive game-design activities. We also discuss results from our initial co-design sessions with middle grades students and teachers in rural communities. 
    more » « less
  5. In this paper, we describe a methodology for determining audience engagement designed specifically for stage performances in a virtual space. We use a combination of galvanic skin response data (GSR), self-reported emotional feedback using the positive and negative affect schedule (PANAS), and a think aloud methodology to assess user reaction to the virtual reality experience. We describe a case study that uses the process to explore the role of immersive viewing of a performance by comparing users’ engagement while watching a virtual dance performances on a monitor vs. using an immersive head mounted display (HMD). Results from the study indicate significant differences between the viewing experiences. The process can serve as a potential tool in the development of a VR storytelling experience. 
    more » « less