Tech

Implement monocular intuitive tactile sensors for powerful manipulation


Implement monocular intuitive tactile sensors for powerful manipulation

(a) Marker-based visual tactile sensor (MVTS). (b) Intuitive tactile sensor based on feedback sensor (RSVTS). Source: Rui Li, Chongqing University

Tactile perception is essential information for humans to perceive the world physically. And tactile perception plays an important role in improving the performance of planning and control for robot operators, to achieve complex robot operations.

Although there have been many different approaches to achieve tactile sensor, visual-tactile sensors are becoming a practical means of implementing tactile sensors, as vision is a low-cost and efficient source to provide rich information. In recent years, thanks to significant advances in visual information processingThe use of vision to build tactile sensors has become one of the major areas of the research community.

A recent study conducted by a research team from the School of Automation, Chongqing University, proposed a framework for building a low-cost, monocular tactile sensor for manipulative tasks. of robots. In addition, they introduced a method to estimate contact location. The design is low-cost and can be processed in a very short time, making it suitable for use as an exploratory study in a laboratory. The article was published in the journal Cyborg and Bionic System.

At present, the main visual-tactile sensing principles can be divided into marker-based visual-tactile sensors (MVTS) and classical sensor-based visual-tactile sensors (RSVTS). .

MVTS is easy to build due to its simple structure and lack of strict light source requirements. Its accuracy mainly depends on the density of the markers and the minimum resolution at which the camera can recognize the markers. Spherical markers are often used for easy detection. The key point is the design of the markers and the acquisition of the spatial position of each marker.

RSVTS, due to its feedback sensing technique, is able to make full use of the camera pixels to obtain a high resolution image of distortion in the elastic layer. Since such devices require an undisturbed lighting system, the camera and the lighting in such devices are often enveloped by the chamber environment.

While RSVTS helps to achieve highly accurate measurements, the requirements for lighting systems, elastomers, and custom sensor components still make it expensive to replicate these designs. Therefore, the motivation of this paper is to provide a framework for designing a low-cost, easy-to-build marker-based visual-tactile sensor.

To ensure that the intuitive tactile sensor is designed to be low cost and easy to fabricate, it is necessary to keep the number of components of the sensor as small as possible and to limit the preparation of each component to as little as possible.

The elastic layer is called “skin” and is the contact point between the object and the sensor. Once the object is pressed against the elastic layer, geometric deformation occurs. The camera is the core component used to sense the deformation of the elastic layer through changes in the captured image. The connectors are used to combine the elastic layer with the camera then secure them to the camera arm.

The elastic layer is where the contact occurs. With long-term use, this part will inevitably wear out and age. Therefore, materials with properties such as wear resistance, ease of processing, ease of replacement and low cost should be considered. In this work, the researchers used silicone resin as the elastomeric layer material.

To prepare the elastic layer, we recommend the following pipeline: Step 1: mold design. The shape of the mold determines the shape of the elastic layer. Step 2: Design the marker. The marker affects strain detection performance. Step 3: Produce the elastic layer. A series of processes, such as scaling, mixing, air-bubble removal and curing, will be performed to obtain the desired elastic layer.

After completing the overall design, the team started case study in which they designed a finger-like elastic layer, similar in length and size to the distal and middle phalanges of a human finger. With the installation of a robotic finger, the entire fingertip can perceive tactile information.

To keep the shape of the elastomer as simple as possible The sensor surface is designed as a joint structure of a hemisphere and an open cylinder. Traces on the elastic layer can be in the form of dome or spherical coordinates.

To prepare the elastomer, a mold is made from aluminum. The thickness of the elastic layer is determined by the inside and outside diameters of the mold, in this case, mold A has a diameter of 8.0 and mold B has a diameter of 10.0 and 12.0 respectively. And the researchers used a vacuum oven and a scale to make the preparation precise and repeatable.

The authors 3D printed a connector to integrate the elastic layer with the camera.

The team also proposes a marker-based approach to estimate the location of contacts using ARUCO markers that can detect multiple contact areas simultaneously.

Existing work has yielded many encouraging results, but there is still plenty of room to improve the picture-tactile sensor in the following respects: (1) VTS is generally easier to fabricate than non-VTS, but the lighting system, elastomer layer, and custom sensor component still make it expensive to replicate these designs . (2) Most VTSs use flat contact surfaces, which makes them less competitive than their non-VTS counterparts.

The main advantages of this intuitive tactile sensor are as follows: first, it supports curved surface contact surfaces and adapts to more complex object shapes. Second, the transparent housing design can make full use of the visual sensor’s image information.

In the future, the team will focus on further improving the resolution of tactile perception by designing a special marker pattern. They also aim to explore the use of such sensors in applications such as home services.

More information:
Rui Li et al, Deploying One-Eye Tactile-Visual Sensors for Powerful Manipulation, Cyborg and Bionic System (In 2022). DOI: 10.34133/2022/9797562

Provided by Beijing Institute of Technology Press Co., Ltd

Quote: Implemented monocular haptic sensor for powerful manipulation (2022, Nov 3) retrieved Nov 4, 2022 from https://techxplore.com/news/2022-11-monocular -visual-tactile-sensors-robust.html

This document is the subject for the collection of authors. Apart from any fair dealing for personal study or research purposes, no part may be reproduced without written permission. The content provided is for informational purposes only.

news7f

News7F: Update the world's latest breaking news online of the day, breaking news, politics, society today, international mainstream news .Updated news 24/7: Entertainment, Sports...at the World everyday world. Hot news, images, video clips that are updated quickly and reliably

Related Articles

Back to top button