Visuotactile Sensors With Emphasis on GelSight Sensor: A Review

Abad, Alexander C.; Ranasinghe, Anuradha

doi:10.1109/jsen.2020.2979662

Cited by 106 publications

(32 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vision-based sensing provides advantages to soft tactile skin, including high spatial resolution and sensitivity, in that a camera is employed to document deformation of artificial skin for conversion to tactile information [11], [12]. Such technology can sense deformation of a large area of soft robotic skin without embedded sensors, markedly reducing wiring, electronics, and risk of damage.…”

Section: Introductionmentioning

confidence: 99%

Large-Scale Vision-Based Tactile Sensing for Robot Links: Design, Modeling, and Evaluation

Duong

2021

IEEE Trans. Robot.

View full text Add to dashboard Cite

The sense of touch allows individuals to physically interact with and better perceive their environment. Touch is even more crucial for robots, as robots equipped with thorough tactile sensation can more safely interact with their surroundings, including humans. This article describes a recently developed large-scale tactile sensing system for a robotic link, called TacLINK, which can be assembled to form a whole-body tactile sensing robot arm. The proposed system is an elongated structure comprising a rigid transparent bone covered by continuous artificial soft skin. The soft skin of TacLINK not only provides tactile force feedback but can change its form and stiffness by inflation at low pressure. Upon contact with the surrounding environment, TacLINK perceives tactile information through the three-dimensional (3-D) deformation of its skin, resulting from the tracking of an array of markers on its inner wall by a stereo camera located at both ends of the transparent bone. A finite element model (FEM) was formulated to describe the relationship between applied forces and the displacements of markers, allowing detailed tactile information, including contact geometry and distribution of applied forces, to be derived simultaneously, regardless of the number of contacts. TacLINK is scalable in size, durable in operation, and low in cost, as well as being a high-performance system, that can be widely exploited in the design of robotic arms, prosthetic arms, and humanoid robots, etc. This article presents the design, modeling, calibration, implementation, and evaluation of the system.

show abstract

Section: Introductionmentioning

confidence: 99%

Large-Scale Vision-Based Tactile Sensing for Robot Links: Design, Modeling, and Evaluation

Duong

2021

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…The layer needs to be thin, uniform and smooth. A matte coating, made by mixing silicone and fine metallic powders [51], is preferable for tactile sensing, as it is effective at revealing detailed shapes on the contact surface. We use a platinum-cure silicone named Psycho Paint (see Table I), and we disperse aluminum powder into a silicone paint base for the coating on top of the elastomer base.…”

Section: B Coated Elastomer Componentmentioning

confidence: 99%

F-TOUCH Sensor: Concurrent Geometry Perception and Multi-Axis Force Measurement

Alomainy

Vitanov

et al. 2021

IEEE Sensors J.

View full text Add to dashboard Cite

Force and tactile sensing has experienced a surge of interest over recent decades, as it conveys a range of information through physical interaction. Tactile sensors aim to obtain tactile information (including pressure, texture etc.). However, current tactile sensors have difficulties in accurately acquiring force signals with regards to magnitude and direction. This is because tactile sensors such as the GelSight sensor estimate shear forces from discrete markers embedded in a compliant sensor interface, employing image processing techniquesthe resultant force errors are sizeable. This paper presents a novel design for a force/tactile sensor, namely the F-TOUCH (Force and Tactile Optically Unified Coherent Haptics) sensor, representing an advancement on current vision-based tactile sensors. In addition to acquiring geometric features at a high spatial resolution, our sensor incorporates a number of deformable structural elements allowing us to measure translational and rotational force and torque along six axes with high accuracy. The proposed sensor contains three key components: a coated elastomer layer acting as the compliant sensing medium, spring mechanisms acting as deformable structural elements, and a camera for image capture. The camera records the deformation of the structural elements as well as the distortion of the compliant sensing medium, concurrently acquiring force and tactile information. The sensor is calibrated with the use of a commercial ATI force sensor. An experimental study shows that the F-TOUCH sensor outperforms the GelSight sensor with regard to its capabilities to sense force signals and capturing the geometry of the contacted object. Index Terms-Tactile sensing; force/torque sensor; contact sensing; vision; image processing; robotics I. INTRODUCTION orce and tactile sensing has garnered much research interest over past decades, for it admits of information gathering through direct physical contact between a sensing device and

show abstract

“…Optical tactile sensors are often soft because they rely on viewing physical changes to the sensing surface, usually from inside the sensor with an internal light source. Optical touch sensing dates back to the mid-1960s [19], with the earliest example relaying the view of a photoelastic skin via optic fibres to a TV camera whose signal was viewed remotely to teleoperate a robotic gripper [20].…”

Section: Soft Biomimetic and Optical Tactile Sensingmentioning

confidence: 99%

“…For soft camera-based tactile sensors, there are many proposals for imaging surface deformation [19] with categories including [21]: (i) soft marker-based optical tactile sensors, which typically measure the (lateral) shear deformation of the sensing surface, such as the GelForce (2004) which has markers embedded in a supporting gel [22]; and (ii) soft reflectionbased optical tactile sensors, which typically measure the (normal) indentation of the sensing surface, such as the GelSight (2009) which uses the surface shading from multiple internal light sources to infer a depth map via photometric stereo [3]. Combinations are also considered, such as by printing markers on the GelSight skin [23] and by mixing coloured markers to indicate depth [24].…”

Section: Soft Biomimetic and Optical Tactile Sensingmentioning

confidence: 99%

Soft Biomimetic Optical Tactile Sensing with the TacTip: A Review

Lepora

2021

Preprint

View full text Add to dashboard Cite

<div>Reproducing the capabilities of the human sense of touch in machines is an important step in enabling robot manipulation to have the ease of human dexterity. A combination of robotic technologies will be needed, including soft robotics, biomimetics and the high-resolution sensing offered by optical tactile sensors. This combination is considered here as a SoftBOT (Soft Biomimetic Optical Tactile) sensor. This article reviews the BRL TacTip as a prototypical example of such a sensor. Topics include the relation between artificial skin morphology and the transduction principles of human touch, the nature and benefits of tactile shear sensing, 3D printing for fabrication and integration into robot hands, the application of AI to tactile perception and control, and the recent step-change in capabilities due to deep learning. This review consolidates those advances from the past decade to indicate a path for robots to reach human-like dexterity.</div><div><br></div>

show abstract

Visuotactile Sensors With Emphasis on GelSight Sensor: A Review

Cited by 106 publications

References 58 publications

Large-Scale Vision-Based Tactile Sensing for Robot Links: Design, Modeling, and Evaluation

Large-Scale Vision-Based Tactile Sensing for Robot Links: Design, Modeling, and Evaluation

F-TOUCH Sensor: Concurrent Geometry Perception and Multi-Axis Force Measurement

Soft Biomimetic Optical Tactile Sensing with the TacTip: A Review

Contact Info

Product

Resources

About