Robotic Playing for Hierarchical Complex Skill Learning

TL;DR

This paper introduces a hierarchical skill learning approach for robotic manipulation, where simple controllers and environment transformation enable generalization to complex, novel tasks through autonomous playing.

Contribution

It proposes a paradigm of using simple controllers and environment transformation with hierarchical skills to improve generalization in complex manipulation tasks.

Findings

Hierarchical skills enable complex manipulation in pick-and-place tasks.

Autonomous playing allows robots to learn and refine skills.

Transforming environments facilitates generalization to new situations.

Abstract

In complex manipulation scenarios (e.g. tasks requiring complex interaction of two hands or in-hand manipulation), generalization is a hard problem. Current methods still either require a substantial amount of (supervised) training data and / or strong assumptions on both the environment and the task. In this paradigm, controllers solving these tasks tend to be complex. We propose a paradigm of maintaining simpler controllers solving the task in a small number of specific situations. In order to generalize to novel situations, the robot transforms the environment from novel situations into a situation where the solution of the task is already known. Our solution to this problem is to play with objects and use previously trained skills (basis skills). These skills can either be used for estimating or for changing the current state of the environment and are organized in skill hierarchies. The approach is evaluated in complex pick-and-place scenarios that involve complex manipulation. We further show that these skills can be learned by autonomous playing.