Abstract-Many human skills can be described in terms of performing a set of prioritised tasks. While a number of tools have become available that recover the underlying control policy from constrained movements, few have explicitly considered learning how constraints should be imposed in order to perform the control policy. In this paper, a method for learning the self-imposed constraints present in movement observations is proposed. The problem is formulated into the operational space control framework, where the goal is to estimate the constraint matrix and its null space projection that decompose the task space and any redundant degrees of freedom. The proposed method requires no prior knowledge about either the dimensionality of the constraints nor the underlying control policies. The techniques are evaluated on a simulated three degree-of-freedom arm and on the AR10 humanoid hand.

No 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 taskand null-space parts, and (iii) uncovering the underlying null space control policy. It is a powerful tool to analyse and decompose many everyday tasks, such as wiping, reaching and drawing. The library also includes several tutorials that demonstrate its use 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 indepth experience in learning constraints and underlying control policies in the context of redundant robotic systems.

Reliable communication is a critical factor for ensuring robust performance of multi-robot teams. A selection of results are presented here comparing the impact of poor network quality on team performance under several conditions. Two different processes for emulating degraded network signal strength are compared in a physical environment: modelled signal degradation (MSD), approximated according to increasing distance from a connected network node (i.e. robot), versus effective signal degradation (ESD). The results of both signal strength processes exhibit similar trends, demonstrating that ESD in a physical environment can be modelled relatively well using MSD.