Active Deformation through Visual Servoing of Soft Objects

Abstract

In this paper, we propose the ADVISEd (Active Deformation through VIsual SErvoing) method, a novel modelfree deformation servoing method able to deform a soft object towards a desired shape. ADVISEd relies on an online estimation of the deformation Jacobian that relates the motion of the robot end-effector to the deformation behavior of the object. The estimation is based on a weighted least-squares minimization with a sliding window. The robustness of the method to observation noise is ensured using an eigenvaluebased confidence criterion. The ADVISEd method is validated through comparisons with a model-based and a model-free state-of-the-art methods. Two experimental setups are proposed to compare the methods, one to perform a marker-based active shaping task and one to perform several marker-less active shaping and shape preservation tasks. Experiments showed that our approach can interactively control the deformations of an object in different tasks while ensuring better robustness to external perturbations than the state-of-the-art methods.

Model Predictive Manipulation of Compliant Objects with Multi-Objective Optimizer and Adversarial Network for Occlusion Compensation

“…Many methods have been proposed to address this issue, e.g. the Broyden update rule [21] is a classical algorithm to iteratively estimate this transformation matrix [7], [22], [23]. Although these types of algorithms do not require knowledge of the model's structure, its estimation properties are only valid locally.…”

“…In addition to the feedback shape error s * − s k , we also compare T max (i.e., the number of steps from start to finish), t d (the steps from s * − s 0 to 10% of this value), t s (the steps from 10% s * − s 0 to the threshold value), and d ef f (the total moving distance of the end-effector), [11], [23]. Fig.…”

Model-Free 3D Shape Control of Deformable Objects Using Novel Features Based on Modal Analysis

“…Navarro-Alarcon et al [19] developed a series of works for geometric features of 3D control points [7], 2D curve descriptors using the spline-based method [20], as well as 2D contour descriptors using the Fourier-based [9] and the moment-based [10] methods. Lagneau et al [21] proposed an active deformation controller for marker-based and markerless 3D point features using online Jacobian estimation with a sliding window. Nevertheless, as these geometric deformation features become more complex or global, the deformation Jacobian matrix becomes more difficult to be formulated and estimated.…”

Vision-based manipulation of deformable and rigid objects using subspace projections of 2D contours

“…A classical model-free approach in manipulating deformable objects is developed in (Berenson, 2013). More recent research (Lagneau et al, 2020a) and (Lagneau et al, 2020b) proposes a method for online estimation of the deformation Jacobian, based on weighted least square minimization with a sliding window. In (Navarro-Alarcon et al, 2014) and (Navarro-Alarcon and Liu, 2018), the vision-based deformable objects manipulation is termed as shape servoing.…”