GelSight: High-Resolution Robot Tactile Sensors for Estimating Geometry and Force

By Wenzhen Yuan, Siyuan Dong, Edward H. Adelson. Italian National Conference on Sensors, 2017

1,395 citations recorded by the source corpus.

Tactile sensing is an important perception mode for robots, but the existing tactile technologies have multiple limitations. What kind of tactile information robots need, and how to use the information, remain open questions. We believe a soft sensor surface and high-resolution sensing of geometry should be important components of a competent tactile sensor. In this paper, we discuss the development of a vision-based optical tactile sensor, GelSight. Unlike the traditional tactile sensors which measure contact force, GelSight basically measures geometry, with very high spatial resolution. The sensor has a contact surface of soft elastomer, and it directly measures its deformation, both vertical and lateral, which corresponds to the exact object shape and the tension on the contact surface. The contact force, and slip can be inferred from the sensor’s deformation as well. Particularly, we focus on the hardware and software that support GelSight’s application on robot hands. This paper reviews the development of GelSight, with the emphasis in the sensing principle and sensor design. We introduce the design of the sensor’s optical system, the algorithm for shape, force and slip measurement, and the hardware designs and fabrication of different sensor versions. We also show the experimental evaluation on the GelSight’s performance on geometry and force measurement. With the high-resolution measurement of shape and contact force, the sensor has successfully assisted multiple robotic tasks, including material perception or recognition and in-hand localization for robot manipulation.

Subfields: Biomedical Engineering, Cognitive Neuroscience, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/209a2428749696b5e42a7cddde77494cf824e4fe

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Cognitive Neuroscience

In Control and Systems Engineering

Citations in the corpus

DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor With Application to In-Hand Manipulation (2020, background): “Among these, GelSight sensors have been quite popular in the recent robotic literature, and several sensors have been presented [11], [12] that use a soft reflective elastomer with printed markers as the contact surface, and outputs images of the surface deformations.”
Trends and challenges in robot manipulation (2019, background): “2, left) or use an optical sensor that renders deformation of an object’s geometry at a high spatial resolution (22).”
Soft magnetic skin for super-resolution tactile sensing with force self-decoupling (2021, background): “Mechanical decoupling (11, 12, 18, 19, 22) could be a reliable solution for accurately separating the normal and tangential forces, but sensors based on mechanical decoupling are not suitable for daily grasping and manipulation tasks, considering the complex and bulky structure as well as the undeve”
Rearrangement: A Challenge for Embodied AI (2020, background): “A variety of sensor types are common: color vision cameras, depth sensors, contact/collision sensors, tactile sensors [50], LiDAR, microphones, and elastomeric sensors such as GelSight [38, 80] are prominent examples.”
More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch (2018, methodology): “ing of a 7-DoF Sawyer arm, a Weiss WSG-50 parallel gripper, and two GelSight sensors [33], one for each finger.”
Challenges and Outlook in Robotic Manipulation of Deformable Objects (2021, background): “In [33], the GelSight [34], a vision-based highresolution tactile sensor, measures the 3D geometry of the contact surface, and the normal/shear forces.”
Manipulation by Feel: Touch-Based Control with Deep Predictive Models (2019, methodology): “d) Tactile sensor: For tactile sensing, we use a custom elastomer-based sensor based on the GelSight design [7] with a diameter of 4 cm.”
Cable manipulation with a tactile-reactive gripper (2019, methodology): “Cable pose estimation First, we compute depth images from GelSight images with Fast Poisson Solver [1].”
Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, neutral): “Thisapproachcansigniﬁcantlyenhancetheaccuracy andfeasibilityoftaskplanning,betteraddressingthechallenges ofreal-worldenvironments.”
A Review of Tactile Information: Perception and Action Through Touch (2020, methodology): “Machine-learning [72], [73] and traditional image-based approaches [68], [74]–[76] are widely used to estimate the position of contacts and identify salient features such as edges, corners, and small protrusions.”
GelSlim: A High-Resolution, Compact, Robust, and Calibrated Tactile-sensing Finger (2018, background): “A detailed review of different versions of GelSight sensors can be found in [16].”
ReSkin: versatile, replaceable, lasting tactile skins (2021, background): “While optical sensors provide high spatial resolution data, they also require a clear line of sight between the camera and elastomer to observe deformations[1, 21, 22].”