A Versatile Underactuated Robotic Hand for Cloth Manipulation
xinhao chen, Alberto ElÃas Petrilli BarcelÃ3, Saeed Shiry Ghidary, Dayuan Chen, Jose Victorio Salazar Luces, Yasuhisa Hirata
AI summary
Problem
Low-DOF grippers simplify hardware but struggle with the unpredictable deformation of fabrics, while specialized grippers lack the versatility needed for multi-task garment handling in automation.
Approach
The authors designed a human-hand-like underactuated gripper that combines a controlled vacuum suction system with a mechanical clamping finger, enabling adaptive point and line contact for fabric manipulation.
Key results
- Integrated suction and clamping mechanism enables reliable single-layer fabric pickup
- Underactuated linkage design allows seamless transition between point and line contact
- Vacuum leakage control strategy prevents dual-pickup while maintaining grip force
- Demonstrates versatile multi-task capability with a simplified, low-actuator design
Why it matters
Provides a practical, cost-effective hardware solution for textile automation that reduces dependency on complex vision and control algorithms.
Abstract
Traditional cloth manipulationg often employs low- DOF grippers to simplify hardware. However, this approach presents significant challenges for algorithms due to the complex and dynamic behavior of fabrics. To address these limitations, we propose a novel approach based on a human-hand-like design that integrates an underactuated grasping mechanism with a suction system. By incorporating multiple single-layer suction principles, the robotic hand achieves greater adaptability and flexibility, en- abling it to perform tasks that would typically require high-DOF hands and complex control strategies. This letter outlines the design of the robot hand with a suction system and evaluates its perfor- mance in various tasks.