Living Archive: An AI Performance Experiment. Choreographic Work. Co-commissioned by The Music Center and Los Angeles Philharmonic. AI choreography tool developed in collaboration with Google Arts & Culture Lab. Premiered in July 2019.
- Submitting institution
-
Trinity Laban Conservatoire of Music and Dance
- Unit of assessment
- 33 - Music, Drama, Dance, Performing Arts, Film and Screen Studies
- Output identifier
- McGregor5
- Type
- I - Performance
- Venue(s)
- Dorothy Chandler Pavilion, Music Center, Los Angeles, California
- Open access status
- Out of scope for open access requirements
- Month of first performance
- July
- Year of first performance
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
0
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In collaboration with Google’s Arts and Culture Lab, I developed the Living Archive — an artificially intelligent choreographic tool, trained on video from my back catalogue, as well as solo material created on each of the current company.
From what it learned about individual physical styles of different bodies dancing my choreography, the system could respond to any new movement phrase by suggesting multiple original possibilities for the next phrase. Through real-time dialogue, Living Archive unleashed creative movement potential stored at micro-level within former works, amplifying possibilities for choreographic decision-making, and bringing dancers of the present into contact with their predecessors. It provides an additional tool in creation, augmenting my choreographic process. It offers multiple options, but there is always a human in the loop, because there isn’t an algorithm that can judge the quality of the choreography and decide how to respond to the data as body-to-body transfer occurs.
The next step was Living Archive: An AI Performance Experiment, devised in the studio with our dancers. The digital collaborator was able to capture inputs via webcam, and instantaneously display original movement sequences of approximately five-ten seconds on screen that we could choose to work with. These AI-derived movements are rendered on screen via both stick figures and partially-abstracted human forms – any one of which might momentarily act as a supplementary ‘eleventh dancer’. Rather than copying the AI-derived movements, we translate inspiring elements of these suggested motions through our own thinking bodies: real-time, human-machine interaction.
A public tool was also devised, forming an important extension to the performance experiment; it provided a large online audience a playful way to interact with our archive. Now, anyone, anywhere can interact with my body of work to create their own piece of dance.
https://waynemcgregor.com/productions/living-archive/
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
