Spraying intelligent skin, understanding hand tasks with AI
2022-12-30
A new smart skin developed by Stanford University in the United States may indicate that one day people can type on an invisible keyboard, recognize objects by touch alone, or allow users to communicate with applications through gestures in an immersive environment. In a paper published recently in Nature Electronics, researchers described a new type of stretchable biocompatible material, which can be sprayed on the back of the hand like a sunscreen spray, and a micro electronic network is integrated here. It can sense the stretching and bending of the skin. By using artificial intelligence (AI), researchers can explain countless daily tasks according to hand movements and gestures. Researchers said that it may have a wide range of applications and impacts in games, sports, telemedicine, robots and other fields. This method of spraying smart skin is simple enough in form and flexible enough in function, which is basically applicable to any user. Current technology requires multiple sensor components to read each joint of the finger, which makes them very cumbersome. This new device takes a more streamlined approach to software, enabling faster learning. This precision may be the key in virtual reality applications, conveying subtle movements for a more realistic experience. The innovation of this research is a sprayable electrosensitive mesh network embedded in polyurethane. This mesh has electrical activity, biocompatibility and breathability, and will not fall off unless it is wiped with soap and water. It fits closely with the wrinkles on the fingers of the wearer. A lightweight Bluetooth module only needs to be connected to the grid to transmit signal changes wirelessly. Bao Zhenan, senior author of the study and professor of chemical engineering at Stanford University, explained that when the fingers were bent and twisted, the nanowires in the mesh were squeezed together and stretched, changing the conductivity of the mesh. These changes can be measured and analyzed to accurately tell how the hand, finger or joint moves. The spray characteristics of the device allow it to fit hands of any size or shape, but also open the possibility that the device can adapt to the face to capture subtle emotional cues. This may lead to new methods of computer animation or virtual avatar meetings with more realistic facial expressions. In addition, machine learning plays a major role. The computer monitors the pattern of conductivity changes and maps these changes to specific physical tasks and gestures. For example, if you enter an X on the keyboard, the algorithm will learn to recognize this task from the change pattern of conductivity. Once the algorithm is properly trained, the physical keyboard is no longer needed. The researchers have built a prototype that can recognize simple objects by touching, and even perform predictive two handed typing on an invisible keyboard. This algorithm can input Shakespeare's "no heritage is richer than honesty" and William Ernest Henry's "Unconquerable", "I am the master of my destiny, I am the captain of my soul". (Intern reporter Zhang Jiaxin) Editor in chief circles this is very similar to the motion capture technology commonly used in movies, that is, after tracking the moving objects, they are sent to a computer or a machine to learn and process them into images. The familiar Gulu in Avatar and Lord of the Rings is captured by action in the whole process
Edit:luoyu Responsible editor:wangerdong
Source:stdaily.com
Special statement: if the pictures and texts reproduced or quoted on this site infringe your legitimate rights and interests, please contact this site, and this site will correct and delete them in time. For copyright issues and website cooperation, please contact through outlook new era email:lwxsd@liaowanghn.com