Learning Null Space Projections in Operational Space Formulation

TL;DR

This paper introduces a method for learning the null space projection matrix in constrained robotic systems without prior knowledge of the environment or constraints, enhancing adaptability across various scenarios.

Contribution

It presents a novel approach to learn null space projections directly from data, addressing the challenge of unknown constraints in kinematic systems.

Findings

Effective across different problem dimensions

Handles non-linear constraints well

Demonstrates robustness without prior environment knowledge

Abstract

In recent years, a number of tools have become available that recover the underlying control policy from constrained movements. However, few have explicitly considered learning the constraints of the motion and ways to cope with unknown environment. In this paper, we consider learning the null space projection matrix of a kinematically constrained system in the absence of any prior knowledge either on the underlying policy, the geometry, or dimensionality of the constraints. Our evaluations have demonstrated the effectiveness of the proposed approach on problems of differing dimensionality, and with different degrees of non-linearity.