GelSight EndoFlex: A Soft Endoskeleton Hand with Continuous High-Resolution Tactile Sensing
Sandra Q. Liu, Leonardo Zamora Ya\~nez, Edward H. Adelson

TL;DR
This paper introduces GelSight EndoFlex, a soft, compliant three-finger robot hand with high-resolution tactile sensors along its entire length, enabling detailed object recognition from a single grasp.
Contribution
The paper presents a novel soft robotic hand with integrated high-resolution tactile sensing along its entire fingers, combining compliance, strength, and detailed tactile data collection.
Findings
Enables object recognition from a single grasp.
Provides high-resolution tactile data along entire finger length.
Demonstrates effective enveloping grasp with rich tactile feedback.
Abstract
We describe a novel three-finger robot hand that has high resolution tactile sensing along the entire length of each finger. The fingers are compliant, constructed with a soft shell supported with a flexible endoskeleton. Each finger contains two cameras, allowing tactile data to be gathered along the front and side surfaces of the fingers. The gripper can perform an enveloping grasp of an object and extract a large amount of rich tactile data in a single grasp. By capturing data from many parts of the grasped object at once, we can do object recognition with a single grasp rather than requiring multiple touches. We describe our novel design and construction techniques which allow us to simultaneously satisfy the requirements of compliance and strength, and high resolution tactile sensing over large areas. The supplementary video can be found here: https://youtu.be/H1OYADtgj9k
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Sensor and Energy Harvesting Materials · Tactile and Sensory Interactions · EEG and Brain-Computer Interfaces
