Emergence by John McCormick, Steph Hutchison and an emerging performing agent, is a duet performed between a human dancer and an artificially intelligent performing agent. The agent has learnt to dance through a rehearsal process with the dancer, sharing the dancer’s movement and style. Emergence sees the dancer and agent co-creating an interactive semi-improvised dance performance. Visualisations of their relationship are projected in glorious Stereoscopic 3D. The neural network based […]
The dance version of Recognition is part of the performance Emergence. Steph and the performing agent dance together but independently. The agent has learnt to dance from Steph. When Steph is onstage dancing, the morphing form uses her movement data to animate itself. When she leaves the stage the morphing form uses the agents movement. Together Steph and the agent provide a continuous stream of movement data for the morphing […]
Verbose Mode by John McCormick with Steph Hutchison. Part of the performance Emergence. A performing software agent has learnt to recognise some short dance phrases performed by Steph. When it recognises the phrases it responds with commentary on Steph’s performance. Performed at Motion.lab, Deakin University Melbourne. Supported by Motion.lab and Centre for Intelligent Systems Research.
A neural network software agent has learnt to recognise some movement phrases taught to it by Steph. When it thinks it has recognised a movement it responds with some thoughts related to name of the movement. There are six movement phrases in this study. We are using Artificial Neural Networks (ANN) combined with Hidden Markov Models (HMM) to perform the recognition. This allows the agent to recognise longer movement phrases […]
A neural network based software agent has learnt some movement from Steph and can generate dance phrases using this learnt vocabulary. When Steph dances, the “body”, the morphing form, uses her movement to animate itself, when Steph leaves, the body uses the agent’s movement. Movement is tracked with a kinect sensor. The two different “dresses” on the body are Steph and my irises shot close up.
A neural network based software agent has learnt some semi-improvised dance phrases from Steph. Here Steph provides movements which the agent then uses as starting points for the generation of its own movement phrases as a response. Steph’s avatar is white, the Agent’s avatar is red. We are using an optical motion capture system to provide the agent with Steph’s movement stream both for learning and so it can discern […]