Learning from Demonstration with Weakly Supervised Disentanglement

TL;DR

This paper introduces a weakly supervised learning approach for robotic manipulation from demonstrations, aligning high-level concepts with high-dimensional sensory data using user-provided labels, improving interpretability and control.

Contribution

It proposes a probabilistic generative model with explicit alignment of latent variables to high-level concepts using weak labels, enhancing learning from demonstrations in robotics.

Findings

Effective in two manipulation tasks with PR2 robot

Improves interpretability of learned representations

Utilizes weak supervision to align high-level concepts

Abstract

Robotic manipulation tasks, such as wiping with a soft sponge, require control from multiple rich sensory modalities. Human-robot interaction, aimed at teaching robots, is difficult in this setting as there is potential for mismatch between human and machine comprehension of the rich data streams. We treat the task of interpretable learning from demonstration as an optimisation problem over a probabilistic generative model. To account for the high-dimensionality of the data, a high-capacity neural network is chosen to represent the model. The latent variables in this model are explicitly aligned with high-level notions and concepts that are manifested in a set of demonstrations. We show that such alignment is best achieved through the use of labels from the end user, in an appropriately restricted vocabulary, in contrast to the conventional approach of the designer picking a prior over the latent variables. Our approach is evaluated in the context of two table-top robot manipulation tasks performed by a PR2 robot -- that of dabbing liquids with a sponge (forcefully pressing a sponge and moving it along a surface) and pouring between different containers. The robot provides visual information, arm joint positions and arm joint efforts. We have made videos of the tasks and data available - see supplementary materials at: https://sites.google.com/view/weak-label-lfd.