Learning Singularity Avoidance

TL;DR

This paper introduces a learning-based approach for robotic systems to avoid singularities by inferring and optimizing task constraints from demonstrations, enhancing safety and reliability in complex tasks without explicit constraint knowledge.

Contribution

It presents a novel method that learns task constraints from demonstrations to optimize manipulability and avoid singularities, applicable to both kinematic and non-kinematic systems.

Findings

Learnt manipulability can effectively prevent singularities where other policies fail.

The approach infers constraints with less than 10^-5 error in simulated 3DOF systems.

Achieves less than 10^-2 error in real-world 7DOF robotic systems.

Abstract

With the increase in complexity of robotic systems and the rise in non-expert users, it can be assumed that task constraints are not explicitly known. In tasks where avoiding singularity is critical to its success, this paper provides an approach, especially for non-expert users, for the system to learn the constraints contained in a set of demonstrations, such that they can be used to optimise an autonomous controller to avoid singularity, without having to explicitly know the task constraints. The proposed approach avoids singularity, and thereby unpredictable behaviour when carrying out a task, by maximising the learnt manipulability throughout the motion of the constrained system, and is not limited to kinematic systems. Its benefits are demonstrated through comparisons with other control policies which show that the constrained manipulability of a system learnt through demonstration can be used to avoid singularities in cases where these other policies would fail. In the absence of the systems manipulability subject to a tasks constraints, the proposed approach can be used instead to infer these with results showing errors less than 10^-5 in 3DOF simulated systems as well as 10^-2 using a 7DOF real world robotic system.