A Library for Constraint Consistent Learning

TL;DR

This paper presents an open source library for Constraint Consistent Learning that enables data-driven analysis and decomposition of constraints and behaviors in robotic tasks, facilitating research and practical applications.

Contribution

It introduces the first open source software library for Constraint Consistent Learning, including methods for learning constraints, decomposing behaviors, and uncovering control policies.

Findings

Library supports learning state-dependent and -independent constraints

Enables decomposition of behaviors into task and null-space components

Includes tutorials with simulated and real-world data

Abstract

This paper introduces the first, open source software library for Constraint Consistent Learning (CCL). It implements a family of data-driven methods that are capable of (i) learning state-independent and -dependent constraints, (ii) decomposing the behaviour of redundant systems into task- and null-space parts, and (iii) uncovering the underlying null space control policy. It is a tool to analyse and decompose many everyday tasks, such as wiping, reaching and drawing. The library also includes several tutorials that demonstrate its use with both simulated and real world data in a systematic way. This paper documents the implementation of the library, tutorials and associated helper methods. The software is made freely available to the community, to enable code reuse and allow users to gain in-depth experience in statistical learning in this area.