Menu Close


LuminAI is an interactive art installation in which participants can engage in collaborative movement improvisation with an artificially intelligent virtual dance partner. The line between human and non-human is blurred, spurring participants to examine their relationship with AI-based technology and how it can be expressive, social, and playful.

The LuminAI installation ultimately examines how humans and machines can co-create experiences together as equals, but it does so in a lighthearted environment. Participants are able to creatively explore movement while having fun. LuminAI’s virtual agent analyzes participant movements through procedural representations of the Viewpoints movement theory (from theater and dance) and improvises responses from transformed memories of past interactions with people. In other words, the agent learns how to dance by dancing with us.

Current work on the LuminAI project includes:

  • Investigating Laban movement theory as an alternative way for the agent to understand and reason about movement
  • Developing a machine learning toolkit for visualizing how the agent clusters similar gestures together as it is learning
  • Exploring how to use LuminAI to engage the public with AI in informal learning environments, as a way of increasing understanding and awareness of AI and improving computational literacy.

Selected Videos


  • Long, D., Jacob, M., Davis, N., and Magerko, B. (2017). “Designing for Socially Interactive Systems.” To appear in Proceedings of the 11th Conference on Creativity and Cognition.
  • Jacob, M., and Magerko, B. (2015).  “Interaction-based Authoring for Scalable Co-creative Agents.”  In the Proceedings of the Sixth International Conference on Computational Creativity (ICCC), Park City, UT, 8 pgs. (pdf)
  • Jacob, M., Coisne, G., Gupta, A., Sysoev, I., Verma, G., and Magerko, B. (2013).  “Viewpoints AI.”  In the Proceedings of the Ninth Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), Boston, MA, 7 pgs. (pdf)
  • Jacob, M., Zook, A., and Magerko, B. (2013).  “Viewpoints AI: Procedurally Representing and Reasoning about Gestures.”  In the Proceedings of DiGRA 2013, Atlanta, GA, 15 pgs. (pdf)