DANCING WITH MACHINES
Part of Sensing Tomorrow
How do you teach a machine to move like we do? As machines get closer to understanding the finer details of human movement, how do we capture that progression, and make that curiosity tangible?
We were struck by a simple research method: machines are learning to move the way humans learn to dance. TraceGen, a robotics system developed at the University of Maryland, learns from human movement in online videos rather than from scarce real-world data, stripping away visual noise to keep only a compact 3D trace-space: the pure geometric expression of how we move through the world.
We asked what trace-space might look like if you could reach out and touch it. Using AI-driven motion capture, we abstracted dance and movement into a series of ceramic sculptures, tactile and playful.
Clay, digital and physical, was the material we gravitated towards: shaped by touch, repetition, and the memory of a guiding hand. Like a potter at the wheel, the machine learns by watching the same motions again and again, until seeing becomes understanding. The centrifugal force that pulls a vessel up from the wheel is there in dance too: weight shifting, momentum held and released, form emerging through process.
Dancing with Machines is a small snapshot of what it might look like when humans and machines begin to think together. Not a cold exchange of data, but something closer to a crafted dialogue.
____________
Sensing Tomorrow, a research brief I wrote and developed with Will Denning at Electric Theatre Collective, started from a question: as machines learn to see, move and sense the world, what happens to the way we do? Dancing with Machines was one answer, in clay.
Machine perception tends towards the abstract. We reached instead for tactility, texture and craft, to ground machine sensing in human feeling and desire, and to sit in the tension where new technologies reflect back old questions about what it means to be human.
Sculpture
⠼⠁
Sculpture
⠼⠃
Sculpture
⠼⠉
Sculpture
⠼⠙
Research & Development
CREDITS
With Will Denning, Ollie Boyle, James Britton
– ETC Research Team @ Electric Theatre Collective
ROLE –
Visual & conceptual research, r&d, art direction, animation,
lighting & texturing, styleframes & production.
TOOLS – QuickMagic (AI mocap), Cinema4D, Redshift, After Effects