loading

LuminAI

Your Virtual Dance Partner

Summary

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.


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.


Investigating Laban movement theory as a 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, Engaging with the public in an informal learning environments, as a way of increasing the understanding and awareness of AI and computational literacy.


ROLE

I am a Graduate Research Assistant in Dr. Brian Magerko’s Expressive Machinery Lab, working on the project. I am responsible for imparting the learnings from Laban’s Movement Analysis to the AI. This includes: Studying Laban’s Movement Theory to identify keys aspects of human movement, Researching the various adaptations of various LMA components, Deriving computational representation of LMA components being, Adopting the Laban based computational models into AI




Laban's Movement Theory


I am a Graduate Research Assistant in Dr. Brian Magerko’s Expressive Machinery Lab, working on the project. I am responsible for imparting the learnings from Laban’s Movement Analysis to the AI. This includes: Studying Laban’s Movement Theory to identify keys aspects of human movement, Researching the various adaptations of various LMA components, Deriving computational representation of LMA components being, Adopting the Laban based computational models into AI

I am a Graduate Research Assistant in Dr. Brian Magerko’s Expressive Machinery Lab, working on the project. I am responsible for imparting the learnings from Laban’s Movement Analysis to the AI. This includes: Studying Laban’s Movement Theory to identify keys aspects of human movement, Researching the various adaptations of various LMA components, Deriving computational representation of LMA components being, Adopting the Laban based computational models into AI




Behind The Curtains

The virtual dance partner manifests itself as a shadow on the screen in front of participants. This shadow tries to follow the movements of the participant - starting with imitation and then going into response mode. In response mode, the agent can do either do random transformation on the same movement as the participant, or recall a similar gesture from its memory.


The gesture recall is based on recognition of the current movement by the agent and finding another gesture with physical similarity or temporal closeness. The agent keeps building and refining its knowledge base based on interaction with the participant.




Next Steps


Currently, we are working on adopting the ’Time’ parameter of Laban’s Efforts into the system. This is done by capturing joint velocity and acceleration, and using these to identify sudden and sustained movements. The next steps involve adoption of ‘Space’ and ‘Weight’ qualities of Effort using multi-modal input like Motion Capture suit, Kinect, EMG Band, Accelerometer etc. We will also plan on exploring spacial qualities of dance and movement using the icosahedron-based kinesphere concept of shape and space exploration.

Video