A Manipulation Control Strategy for Granular Materials Based on a Gaussian Mixture Model

Abstract

In the context of metal additive manufacturing, one of the most attractive tasks to be robotized is the cleaning process of metal powder after the printing operations. This task presents a challenging scenario for most of robot manipulation approaches in the literature. In this paper we present an approach, marker-less and real time affordable, which address the cleaning problem like a shape manipulation control problem. This control strategy is designed as an optimization problem. The error function is written as a lagrangian function using an objective function based on Gaussian Mixture Model (GMM). The local optimization is performed by a gradient descent and a global optimization process is used to avoid local minima.