Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account

Shulou

MIT researchers have developed a new type of robotic hand that can recognize objects with a single scratch.

2025-01-15 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >

Share

Shulou(Shulou.com)11/24 Report--

CTOnews.com, April 4 (Xinhua)-- inspired by human fingers, researchers at the Massachusetts Institute of Technology (MIT) have developed a robotic hand that can use high-resolution tactile sensors to accurately identify the shapes and features of objects with only one grip.

According to CTOnews.com, at present, many robotic hands focus all the sensors on their fingertips, so objects must be in full contact with these fingertips before they can be identified, which may require multiple grasps. Other designs use low-resolution sensors distributed throughout the fingers, but these sensors cannot capture enough detail, so they often need to be re-grasped multiple times.

In contrast, the MIT team created a robotic finger that consists of a rigid 3D printed inner skeleton and a soft transparent "skin". Two pairs of high-precision tactile sensors, called GelSight sensors, are embedded in the inner skeleton, which use cameras and LED lights to collect the contours of the object's surface. These sensors are distributed in the upper and middle of the fingers, and overlap with each other, so that the fingers can perceive continuously over the whole length.

When the robot finger grabs the object, the camera captures the outline image produced by the LED light illuminating the skin from the inside. Then, an algorithm reverses the contours of the object surface based on these images, and uses the machine learning model to identify the object.

Using this design, the researchers created a robotic hand consisting of three fingers that can identify objects with about 85% accuracy while grasping objects only once. The rigid skeleton makes the fingers strong enough to pick up heavy objects, such as electric drills, while soft skin allows them to hold on to soft objects without crushing them, such as empty plastic water bottles.

These soft and hard fingers can be useful in home care robots, which can interact with the elderly, take heavy objects off shelves and help them take a bath.

The researchers hope to improve the robotic hand in the future, reduce the wear and tear of silicone over time, and add more driving force to the thumb to perform a wider range of tasks.

The study will be presented at the RoboSoft conference.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information

Wechat

© 2024 shulou.com SLNews company. All rights reserved.

12
Report