A flexible way to grasp objects consciously: Engineers create a robot gripper
Speaking of monotone and lumbering, the idea of a giant metal robot deliberately moving up the steps is hard to shake. But those who train in the field of soft robotics have a completely different picture in mind – autonomous devices with softer adaptive parts to the touch, much more closely resembling human fingers than the R2-D2 or Robbie the Robot.
That model is now being followed by Professor Edward Adelson and his team of cognitive scientists at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). In a recent project, Adelson and Sandra Liu – a mechanical engineering Ph.D. The student at CSAIL has created a robotic gripper using the novel “GelSight Fin Ray”, which is as delicate as human hands and can handle objects. What sets this work apart from other endeavors in the field is that Liu and Adelson have provided their gripper with touch sensors that can meet or violate the sensitivity of human skin.
Their work was presented last week at the 2022 IEEE 5th International Soft Robotics Conference.
Fin Ray has become a popular subject in soft robotics since its discovery in 1997 by the German biologist Leif Nice. When he pushes his finger on the tail of a fish, he notices that the beam is bent, almost embracing his finger, rather than leaning towards the applied force. The design has become popular, but it lacks tactile sensitivity. “It’s versatile because it can be passively transformed into different forms, so different objects can be understood,” Liu explains. “But in order to go beyond what others in the industry have already done, we began to incorporate a rich tactile sensor into our gripper.”
The gripper has two flexible paddle beams that correspond to the shape of the object with which they interact. Fingers are collected from flexible plastic materials made in 3D printer, which is very stable in the field. However, the fingers commonly used in soft robotic grippers have supportive cross-sleeves that run across the length of their insides, while Liu and Adelson emptied the insides.
At one end of the concave cavity the camera is illuminated by LEDs. The camera faces a layer of “sensory” pads containing silicone gel (known as “gelside”), which is glued to a thin layer of acrylic material. The acrylic sheet, in turn, is attached to the plastic finger piece at the opposite end of the inner cavity. Once an object is touched, the finger will wrap around it seamlessly and merge with the contours of the object. By accurately determining how silicone and acrylic sheets are deformed during this interaction, the camera – along with its associated computational algorithms – can estimate the general shape of the object, its surface hardness, its orientation in space and the force applied. For each finger).
Liu and Adelson tested their gripper in an experiment in which one of the two fingers was “sensitive”. Their device successfully handles items such as a mini screwdriver, plastic strawberry, acrylic paint tube, ball mason jar, and wine glass. For example, when a clipper holds a fake strawberry, the internal sensor is able to detect “seeds” on its surface. Fingers grasped the paint tube without pressing until it broke the container and spilled its contents.
The GelSight sensor can even create characters in a Mason jar, and it did so in a very brilliant way. The overall shape of the jar was first discovered by looking at how the acrylic sheet was curved around. That form, by computer algorithm, was subtracted from the decay of the silicon pad, and what remained was a very subtle decay due to the characters.
Glass objects are challenging for optical robots due to the refraction of light. Tactile sensors resist such optical ambiguity. When the catcher picks up the wine glass, it is able to feel the stem orientation and point the glass straight before slowly lowering it. When the foundation touched the tablet, the gel pad felt the contact. Seven of the 10 experiments got the right place and, fortunately, no glass was affected during the filming of this experiment.
Vincent Juan, an assistant professor at the Robotics Institute at Carnegie Mellon University who is not involved in research, says, “Perception is a big challenge with soft robots because sensors are hard to set up. Soft bodies,” says Juan. “This paper offers an elegant solution to that problem. The authors used a very clever design to work with their vision-based sensor-compatible gripper, in this way robots make excellent results when understanding objects or interacting with the external environment. . ”
Liu and Adelson can anticipate many potential applications for the gelside fin rake, but they first think about some improvements. By hollowing out the finger to free up space for their sensory system, they introduced a structural instability that they believed could be countered by the tendency to turn, by better design. They want to develop GelSight sensors that are compatible with soft robots designed by other research teams. They also plan to create a three-finger gripper that will be useful in tasks such as picking pieces of fruit and evaluating their ripeness.
Tactile sensitivity, in their approach, is based on the cheaper components: a camera, some gel and some LEDs. With technology like Gelsite, Liu believes it is “possible to bring sensors at a practical and affordable price.” At the very least, she and others in the lab have a goal to strive for.
<div class="article-main__explore my-4 d-print-none"> <a class="text-medium text-info mt-2 d-inline-block" href="https://phys.org/news/2017-10-soft-robotic-gripper-bulbs.html">This soft robot gripper can screw up your light bulbs for you</a> </div> <hr class="mb-4"/> <div class="article-main__more p-4"> <strong>More info:</strong> Sandra Q. Liu et al, GelSight Fin Ray: Incorporating Toctile Sensing into a Soft Compliant Robotic Gripper, arXiv: 2204.07146 [cs.RO] <a href="https://arxiv.org/abs/2204.07146" target="_blank" rel="noopener">arxiv.org/abs/2204.07146</a> </div> <div class="d-inline-block text-medium my-4"> Presented by the Massachusetts Institute of Technology <a class="icon_open" href="http://web.mit.edu/" target="_blank" rel="nofollow noopener"> <svg> <use href="https://techx.b-cdn.net/tmpl/v2/img/svg/sprite.svg#icon_open" x="0" y="0"/> </svg> </a> </div> <p class="article-main__note mt-4"> <i>This story is a reprint of MIT News (<a href="http://web.mit.edu/newsoffice/" target="_blank" rel="noopener">web.mit.edu/newsoffice/</a>), A popular site for news on MIT research, innovation and teaching.</i> <!-- print only --> <div class="d-none d-print-block"> <strong>Quote</strong>: A flexible way to capture objects consciously: Engineers create a robot gripper with rich sensory abilities (2022, April 15) https://techxplore.com/news/2022-04-flexible-items-robotic- Retrieved on April 15, 2022 gripper-rich.html This document is subject to copyright. No part may be reproduced without written permission, except for any reasonable manipulation for the purpose of personal study or research. Content is provided for informational purposes only. </div> </div>https://connect.facebook.net/en_US/sdk.js</p>