Abstract:We address the monocular visual shape servoing problem. This pushes the challenging visual servoing problem one step further from rigid object manipulation towards deformable object manipulation. Explicitly, it implies deforming the object towards a desired shape in 3D space by robots using monocular 2D vision. We specifically concentrate on a scheme capable of controlling large isometric deformations. Two important open subproblems arise for implementing such a scheme. (P1) Since it is concerned with large de… Show more
“…Other researchers explored the use of object geometries to approximate deformation behaviors under robot manipulation. They proposed control laws using the diminishing-rigidity approximation (McConachie et al (2020)), the As-Rigid-As-Possible (ARAP) model (Shetab-Bushehri et al (2022)), and the shape-template-based method (Aranda et al (2020)). Recently, increasing attention has been put to the deformation learning approaches that embed geometric graph structures into neural architectures.…”
Section: Modeling Deformation For Robot Manipulationmentioning
Deformable object manipulation (DOM) with point clouds has great potential as nonrigid 3D shapes can be measured without detecting and tracking image features. However, robotic shape control of deformable objects with point clouds is challenging due to: the unknown point correspondences and the noisy partial observability of raw point clouds; the modeling difficulties of the relationship between point clouds and robot motions. To tackle these challenges, this paper introduces a novel modal-graph framework for the model-free shape servoing of deformable objects with raw point clouds. Unlike the existing works studying the object’s geometry structure, we propose a modal graph to describe the low-frequency deformation structure of the DOM system, which is robust to the measurement irregularities. The modal graph enables us to directly extract low-dimensional deformation features from raw point clouds without extra processing of registrations, refinements, and occlusion removal. It also preserves the spatial structure of the DOM system to inverse the feature changes into robot motions. Moreover, as the framework is built with unknown physical and geometric object models, we design an adaptive robust controller to deform the object toward the desired shape while tackling the modeling uncertainties, noises, and disturbances online. The system is proved to be input-to-state stable (ISS) using Lyapunov-based methods. Extensive experiments are conducted to validate our method using linear, planar, tubular, and volumetric objects under different settings.
“…Other researchers explored the use of object geometries to approximate deformation behaviors under robot manipulation. They proposed control laws using the diminishing-rigidity approximation (McConachie et al (2020)), the As-Rigid-As-Possible (ARAP) model (Shetab-Bushehri et al (2022)), and the shape-template-based method (Aranda et al (2020)). Recently, increasing attention has been put to the deformation learning approaches that embed geometric graph structures into neural architectures.…”
Section: Modeling Deformation For Robot Manipulationmentioning
Deformable object manipulation (DOM) with point clouds has great potential as nonrigid 3D shapes can be measured without detecting and tracking image features. However, robotic shape control of deformable objects with point clouds is challenging due to: the unknown point correspondences and the noisy partial observability of raw point clouds; the modeling difficulties of the relationship between point clouds and robot motions. To tackle these challenges, this paper introduces a novel modal-graph framework for the model-free shape servoing of deformable objects with raw point clouds. Unlike the existing works studying the object’s geometry structure, we propose a modal graph to describe the low-frequency deformation structure of the DOM system, which is robust to the measurement irregularities. The modal graph enables us to directly extract low-dimensional deformation features from raw point clouds without extra processing of registrations, refinements, and occlusion removal. It also preserves the spatial structure of the DOM system to inverse the feature changes into robot motions. Moreover, as the framework is built with unknown physical and geometric object models, we design an adaptive robust controller to deform the object toward the desired shape while tackling the modeling uncertainties, noises, and disturbances online. The system is proved to be input-to-state stable (ISS) using Lyapunov-based methods. Extensive experiments are conducted to validate our method using linear, planar, tubular, and volumetric objects under different settings.
“…If the task requires to position multiple nodes, then userdefined values u * t must define a physically feasible solution. Through pseudo-inverse computation, the control law (12) can only minimize a global error on all target nodes, but not the local error on each of the target nodes.…”
Section: E Remarks On Actuation and Perception Dimensionsmentioning
confidence: 99%
“…Analysis: As shown by expressions ( 17) and ( 18), stiffness matrices have a linear dependency on E. From control law (12), the terms in E in K d , K t cancel out and the error signal still follows the first-order convergent behavior defined by (10). Practically, misidentification of the Young's modulus and neglect of other effects such as bending can be compensated by tuning the proportional gain matrix G p accordingly.…”
Section: A Sensitivity To Modeling Errorsmentioning
confidence: 99%
“…Model-based approaches: Even though popular older works are known, as evidenced by the review [11], modelbased shape servoing gets less attention than its modelfree counterpart nowadays. Non-mechanical models such as templates [12] are computationally inexpensive and well suited to visual servoing, but their results guarantee the visual convergence of some points over the surface of the object; consequently, the mechanical constraints related with its material properties are not taken into account. In some cases, low-complexity mechanical models can be used, such as catenaries for isometric linear objects [13].…”
Robots are nowadays faced with the challenge of handling deformable objects in industrial operations. In particular, the problem of shape control, which aims at giving a specific deformation state to an object, has gained interest recently in the research community. Among the proposed solutions, approaches based on finite elements proved accurate and reliable but also complex and computationally-intensive.In order to mitigate these drawbacks, we propose a scheme for shape control that does not require to run a real-time simulation or to solve an implicit optimization problem for computing the control outputs. It is based on a partition of the nodal coordinates that allows deriving a control law directly from tangent stiffness matrices. This formulation is also coupled with the introduction of reduced finite element models. Simulation and experimental results in the context of linear deformable object manipulation demonstrate the interest of the proposed approach.
“…The deformation of the surface object is estimated in [11] using non-uniform rational basis splines approximation with a RGB-D camera. A shape control of isometrically deforming objects with 2D camera is proposed in [12]. These methods show a good balance between computational cost and accuracy.…”
In recent years, there has been a growing interest in robotic manipulation of deformable objects. In order to perform certain tasks, the robot must control the shape of the object while taking care not to apply excessive stresses so as not to deform it irreversibly. This is the case when extracting elasto-plastic objects in strips from an industrial reel. In order to control the mechanical stresses within the object, we propose a vision-based control scheme to minimize tension by regulating the angular velocity of a motorized reel on which they are wound. In this paper, we propose a method, based on a catenary model and visual feedback from a low-cost RGB-D camera, to estimate the tension distribution along a rubber strip. Thus, the control strategy aims to achieve a desired tension value by varying the length of the suspended portion of the manipulated strip. Simulation and experimental results validate the proposed approach for strip-like objects of various dimensions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.