Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

06/24/2015
by   Manuel Watter, et al.
0

We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constrained to be locally linear. Our model is derived directly from an optimal control formulation in latent space, supports long-term prediction of image sequences and exhibits strong performance on a variety of complex control problems.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset