Rather than directly determining a policy from high-dimensional observation data, it is better to extract essential information hidden in the observation data and then decide according to it. This is because similar problems can be regarded as the same and the autonomous robots can get the ability to easily adapt to a wide variety of problems. In this research, we are developing new methods based on a variational autoencoder to extract such information (i.e., latent space).
In particular, the following methods has been proposed to resolve the characteristics of the complex problems.
- Clustering in latent space to handle discrete events and different classes of information
- Revealing latent dynamics that does not violate mathematical assumptions
These are useful for extracting and understanding the complex latent space during physical human-robot interaction.