Autonomous manipulation of deformable objects based on teleoperated demonstrations

Rambow, Matthias; Schauss, Thomas; Buss, Martin; Hirche, Sandra

doi:10.1109/iros.2012.6386002

Cited by 32 publications

(21 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Saha and Isto (2007) have discussed the motion planning for knotting linear deformable objects (LDOs) around static objects using what they called "topologically biased" probabilistic roadmap in the configuration space of the linear deformable object. Rambow et al (2012) have discussed the task of changing the starting configuration of a deformable tube to a given goal configuration. This is achieved by analyzing a human demonstration of the same task and then transferring it to the robot.…”

Section: Manipulation Of Deformable Objectsmentioning

confidence: 99%

A simple assembly planner for the insertion of ring-shaped deformable objects

Ramirez-Alpizar

Harada

Yoshida

2018

View full text Add to dashboard Cite

Purpose The aim of this work is to develop a simple planner that is able to automatically plan the motion for a dual-arm manipulator that assembles a ring-shaped elastic object into a cylinder. Moreover, it is desirable to keep the amount of deformation as small as possible, because stretching the object can permanently change its size thus failing to perfectly fit in the cylindrical part and generating undesired gaps between the object and the cylinder. Design/methodology/approach The assembly task is divided in two parts: assembly task planning and assembly step planning. The first one computes key configurations of the robot’s end-effectors, and it is based on a simple heuristic method, whereas the latter computes the robot’s motion between key configurations using an optimization-based planner that includes a potential-energy-based cost function for minimizing the object’s deformation. Findings The optimization-based planner is shown to be effective for minimizing the deformation of the ring-shaped object. A simple heuristic approach is demonstrated to be valid for inserting deformable objects into a cylinder. Experimental results show that the object can be kept without deformation for the first part of the assembly task, thus reducing the time it is being stretched. Originality value A simple assembly planner for inserting ring-shaped deformable objects was developed and validated through several experiments. The proposed planner is able to insert ring-shaped objects without using any sensor (visual and/or force) feedback. The only feedback used is the position of the robot’s end-effectors, which is usually available for any robot.

show abstract

Section: Manipulation Of Deformable Objectsmentioning

confidence: 99%

A simple assembly planner for the insertion of ring-shaped deformable objects

Ramirez-Alpizar

Harada

Yoshida

2018

View full text Add to dashboard Cite

show abstract

“…Approaches that learn control policies for specific tasks from demonstration have also been investigated [20], [23], [28], [29]. Though effective at solving problems similar to those demonstrated, it is unclear how well these methods generalize to new tasks and environments.…”

Section: Related Workmentioning

confidence: 99%

An online method for tight-tolerance insertion tasks for string and rope

Wang

Berenson

Balkcom

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

This paper presents a fast tight-tolerance threading technique for string and rope. Instead of relying on simulations of these deformable objects to plan a path or compute control actions, we control the movement of the string with a virtual magnetic vector field emanating from the narrow openings we wish to thread through. We compute an approximate Jacobian to move the tip of the string through the vector field and propose a method to promote alignment of the head of the string to the opening. We also propose a method for re-grasping the string based on the relationship between the string's configuration, the orientation of the opening, and direction of gravity. This re-grasping method in conjunction with our controller can be used to thread the string through a sequence of openings. We evaluated our method in simulation (with simulated sensor noise) and on the Da Vinci surgical robot. Our results suggest that our method is quite robust to errors in sensing, and is capable of real-world threading tasks with the da Vinci robot, where the diameter of the string (3.5mm) and opening (4.9mm) differ by only 1.4 mm.978-1-4799-6923-4/15/$31.00 ©2015 IEEE

show abstract

“…Furthermore, there are examples of insertion tasks of linear objects similar to string. Rambow et al used a variable admittance controller adjusted by tactile information during teaching to realize insertion tasks for soft linear objects by correcting the teaching trajectory using tactile information during the task [4]. Many studies have been conducted on the static manipulation of string or linear objects in a similar way.…”

Section: Introductionmentioning

confidence: 99%

Dynamic manipulation of unknown string by robot arm: Realizing momentary string shapes

Tabata

Seki

Tsuji

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper we propose dynamic manipulation for flexible object by using high speed robot arm. We consider dynamic manipulation for unknown string and describe how to manipulete it. Paticulary, we focus on the achived momentary string shapes. For example, momentary string shapes is like a J , C or d. In our strategy for dynamic manipulation of unknown string, manipulation is achieved through repeating 3steps: manipulation of string by robot arm, string parameter estimation. A string is described as the physical-dased 3D model. And ,motion data for robot arm is given as each joint angular velocity data. For simulation of motion, we input the each joint angular velocity data,and initial paramaretars of modeled string.This simulation calculate not only the motion of robot arm but also motion of modeled ropes which occured by robot motion. Parametar estimation is to string parametar by comparing image of the real manipulation with string model and motion generation by estimated model. Repeatly each step, we realize dynamic manipulation of unknown string. Finaly, we show the some experiment of dynamic manipulation ,and we demonstrate effective of parametar estimation and validity.

show abstract

Autonomous manipulation of deformable objects based on teleoperated demonstrations

Cited by 32 publications

References 13 publications

A simple assembly planner for the insertion of ring-shaped deformable objects

A simple assembly planner for the insertion of ring-shaped deformable objects

An online method for tight-tolerance insertion tasks for string and rope

Dynamic manipulation of unknown string by robot arm: Realizing momentary string shapes

Contact Info

Product

Resources

About