Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

G.O.G: A Versatile Gripper-On-Gripper Design for Bimanual Cloth Manipulation with a Single Robotic Arm

Dongmyoung Lee, Wei Chen, Xiaoshuai Chen, Nicolas Rojas

TL;DR

This work tackles the challenge of deformable garment manipulation by proposing G.O.G., a gripper-on-gripper end effector that enables bimanual cloth manipulation with a single robotic arm. The system combines a Width Control Gripper with two Variable Friction Grippers, enabling both firm and sliding grasps and extending usable width to about $500$ mm. Through payload, grasp-and-lift, drag, and real-robot folding experiments on household and clothing benchmarks, G.O.G. demonstrates superior performance to some commercial grippers while reducing hardware and control complexity. The results indicate that complex bimanual cloth tasks, such as folding, can be achieved with simple corner-detection perception and predefined trajectories, highlighting the practical impact of hardware-co-design in single-arm cloth manipulation. Future work will address handling fabrics larger than the gripper width and further refining the design and control to expand the operational envelope.

Abstract

The manipulation of garments poses research challenges due to their deformable nature and the extensive variability in shapes and sizes. Despite numerous attempts by researchers to address these via approaches involving robot perception and control, there has been a relatively limited interest in resolving it through the co-development of robot hardware. Consequently, the majority of studies employ off-the-shelf grippers in conjunction with dual robot arms to enable bimanual manipulation and high dexterity. However, this dual-arm system increases the overall cost of the robotic system as well as its control complexity in order to tackle robot collisions and other robot coordination issues. As an alternative approach, we propose to enable bimanual cloth manipulation using a single robot arm via novel end effector design -- sharing dexterity skills between manipulator and gripper rather than relying entirely on robot arm coordination. To this end, we introduce a new gripper, called G.O.G., based on a gripper-on-gripper structure where the first gripper independently regulates the span, up to 500mm, between its fingers which are in turn also grippers. These finger grippers consist of a variable friction module that enables two grasping modes: firm and sliding grasps. Household item and cloth object benchmarks are employed to evaluate the performance of the proposed design, encompassing both experiments on the gripper design itself and on cloth manipulation. Experimental results demonstrate the potential of the introduced ideas to undertake a range of bimanual cloth manipulation tasks with a single robot arm. Supplementary material is available at https://sites.google.com/view/gripperongripper.

G.O.G: A Versatile Gripper-On-Gripper Design for Bimanual Cloth Manipulation with a Single Robotic Arm

TL;DR

This work tackles the challenge of deformable garment manipulation by proposing G.O.G., a gripper-on-gripper end effector that enables bimanual cloth manipulation with a single robotic arm. The system combines a Width Control Gripper with two Variable Friction Grippers, enabling both firm and sliding grasps and extending usable width to about mm. Through payload, grasp-and-lift, drag, and real-robot folding experiments on household and clothing benchmarks, G.O.G. demonstrates superior performance to some commercial grippers while reducing hardware and control complexity. The results indicate that complex bimanual cloth tasks, such as folding, can be achieved with simple corner-detection perception and predefined trajectories, highlighting the practical impact of hardware-co-design in single-arm cloth manipulation. Future work will address handling fabrics larger than the gripper width and further refining the design and control to expand the operational envelope.

Abstract

The manipulation of garments poses research challenges due to their deformable nature and the extensive variability in shapes and sizes. Despite numerous attempts by researchers to address these via approaches involving robot perception and control, there has been a relatively limited interest in resolving it through the co-development of robot hardware. Consequently, the majority of studies employ off-the-shelf grippers in conjunction with dual robot arms to enable bimanual manipulation and high dexterity. However, this dual-arm system increases the overall cost of the robotic system as well as its control complexity in order to tackle robot collisions and other robot coordination issues. As an alternative approach, we propose to enable bimanual cloth manipulation using a single robot arm via novel end effector design -- sharing dexterity skills between manipulator and gripper rather than relying entirely on robot arm coordination. To this end, we introduce a new gripper, called G.O.G., based on a gripper-on-gripper structure where the first gripper independently regulates the span, up to 500mm, between its fingers which are in turn also grippers. These finger grippers consist of a variable friction module that enables two grasping modes: firm and sliding grasps. Household item and cloth object benchmarks are employed to evaluate the performance of the proposed design, encompassing both experiments on the gripper design itself and on cloth manipulation. Experimental results demonstrate the potential of the introduced ideas to undertake a range of bimanual cloth manipulation tasks with a single robot arm. Supplementary material is available at https://sites.google.com/view/gripperongripper.
Paper Structure (19 sections, 12 figures, 2 tables)

This paper contains 19 sections, 12 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related works
  3. End-effector Design for Cloth Manipulation
  4. Cloth Manipulation with Dual-arm Robotic System
  5. Methodology
  6. The Gripper-on-Gripper System Overview
  7. Width Control Gripper
  8. Variable Friction Gripper
  9. G.O.G. for Bimanual Cloth Manipulation Tasks
  10. Automatic Bimanual Cloth Folding
  11. Bimanual Cloth Hanging and Cloth Edging Flattening
  12. Experiments
  13. Gripper Payload Capacity
  14. Cloth Grasp-and-Lift
  15. Cloth Dragging
  16. ...and 4 more sections

Figures (12)

  • Figure 1: The G.O.G. gripper consists of a gripper base (palm), a Width Control Gripper (WCG), and two Variable Friction Grippers (VFG). The WCG can adjust the opening of fingers to fit various sizes of cloth, while the VFG mounted on these fingers can switch the friction model for the implementation of firm grasp and sliding grasp motions as necessary.
  • Figure 2: The G.O.G. gripper overview: (a) the CAD model of the G.O.G. gripper, showing the base, width control gripper (WCG), and variable friction grippers (VFG), (b) the range of WCG opening width, and (c) VFG gripper, detailing the variable friction module (passively switch between high friction and low friction modes), actuation, and sliding part.
  • Figure 3: Folding trajectories based on the detected corner point. The Width Control Gripper (WCG) adjusts the opening width firstly. Then, pre-grasp, grasp, folding, and release actions are executed. The VFGs are switched to high friction to ensure a firm grasp during the folding.
  • Figure 4: (a) Example of a hanging task. The task is to grasp the collar of the garment and hang it on the back of the chair. (b) Example of cloth flattening. The task is to grasp the wrinkle area of the garment and slide over the wrinkle to make the garment flattened.
  • Figure 5: The payload experimental setup: UR5 and Robotiq FT 300 sensor are employed.
  • ...and 7 more figures