Disney Research teaches robots to dance by letting them learn from unstructured motion data
Disney researchers have managed to make a robot learn strategies from unstructured motion data. First, they extracted a latent spatial encoding by training a variational autoencoder and then used short motion windows from unstructured data as input.
Next, they used the embedding of the time-dependent latent code to train a conditional policy in a second step, enabling a mapping from kinematic inputs to dynamic outputs. By keeping these two steps separate, the team was able to benefit from self-supervised methods to obtain better latent codes and explicit imitation rewards to avoid mode collapse. The efficiency and robustness was demonstrated in simulation with unseen, user-specified movements and on a bipedal robot where dynamic movements were transferred to the real world.
LEGO Ideas Disney Hocus Pocus: The Sanderson Sisters’ Cottage collector’s building set, a unique gift idea…
- LEGO Ideas Disney Hocus Pocus Building Kit (21341) – Relive hilarious scenes from the classic Disney Halloween movie Hocus Pocus with this detailed…
- 6 LEGO minifigures – Winifred Sanderson, Sarah Sanderson, Mary Sanderson, Max Dennison, Dani Dennison and Allison Watts, plus a Thackery Binx (in…
- Fun features – Turn the waterwheel to make pink “smoke” rise from the chimney, activate the LEGO light brick to light the fire underneath the…