Digger Finger: GelSight Tactile Sensor for Object Identification Inside Granular Media

A robot able to look for objects buried in granular media would be useful in such domains as deep-sea exploration, mining, or agriculture. However, this area is still underexplored because of a lot of difficulties. For instance, when using tactile sensors, the media can jam and prevent downward movement. Also, the granular media particles get stuck between the sensor and object.

Example of a granular material. Image credit: Slymart35 via Pixabay, free licence

Recently, researchers from MIT presented a prototype of Digger Finger, a compact wedge-shaped sensor, that addresses these issues. It relies on a novel modification of GelSight, a vision-based tactile sensor. Mechanical vibrations are used to fluidize granular media during penetration.

High-resolution tactile sensing lets to identify object shapes even when distorted by the particles. The suggested sensor opens the way to possible manipulation in both simple operations as scooping litter and industrial applications such as finding buried cables.

Left: Digger Finger. Middle: Penetration motion. Right: Tactile data showing zero contact, granular media (rice), and object contact. Image credit: Radhen Patel et al., arXiv:2102.10230 / MIT

In this paper we present an early prototype of the Digger Finger that is designed to easily penetrate granular media and is equipped with the GelSight sensor. Identifying objects buried in granular media using tactile sensors is a challenging task. First, particle jamming in granular media prevents downward movement. Second, the granular media particles tend to get stuck between the sensing surface and the object of interest, distorting the actual shape of the object. To tackle these challenges we present a Digger Finger prototype. It is capable of fluidizing granular media during penetration using mechanical vibrations. It is equipped with high resolution vision based tactile sensing to identify objects buried inside granular media. We describe the experimental procedures we use to evaluate these fluidizing and buried shape recognition capabilities. A robot with such fingers can perform explosive ordnance disposal and Improvised Explosive Device (IED) detection tasks at a much a finer resolution compared to techniques like Ground Penetration Radars (GPRs). Sensors like the Digger Finger will allow robotic manipulation research to move beyond only manipulating rigid objects.

Research paper: Patel, R., Ouyang, R., Romero, B., and Adelson, E., “Digger Finger: GelSight Tactile Sensor for Object Identification Inside Granular Media”, 2021. Link: https://arxiv.org/abs/2102.10230


Notify of
Inline Feedbacks
View all comments
Would love your thoughts, please comment.x