Shape Control of Elastic Objects Based on Implicit Sensorimotor Models and Data-Driven Geometric Features

TL;DR

This paper introduces a data-driven, real-time control method for shaping elastic objects using implicit sensorimotor models and geometric features, validated through robotic manipulation of elastic rods.

Contribution

It presents a novel approach combining implicit functions and geometric features for shape control of elastic objects, enabling analytical Jacobian computation for shape servoing.

Findings

Successful manipulation of elastic rods into desired shapes

Real-time geometric model parameter identification

Effective shape servoing controller implementation

Abstract

This paper proposes a general approach to design automatic controls to manipulate elastic objects into desired shapes. The object's geometric model is defined as the shape feature based on the specific task to globally describe the deformation. Raw visual feedback data is processed using classic regression methods to identify parameters of data-driven geometric models in real-time. Our proposed method is able to analytically compute a pose-shape Jacobian matrix based on implicit functions. This model is then used to derive a shape servoing controller. To validate the proposed method, we report a detailed experimental study with robotic manipulators deforming an elastic rod.