Spray-on smart skin rapidly understands hand tasks
Researchers at Stanford University say they have developed a new smart skin that could allow users to type on invisible keyboards, identify objects by touch alone, or communicate by hand gestures with apps in immersive environments. The sensory system, which gets sprayed on the back of the hand, is based on a new type of stretchable biocompatible material that integrates a tiny electrical network that senses as the skin stretches and bends.
AI is used to interpret myriad daily tasks from hand motions and gestures. The smart skin, say the researchers, could have applications and implications in fields as far-ranging as gaming, sports, telemedicine, and robotics.
Until now, several promising methods have been actively explored to enable various hand tasks and gesturing, such as measuring muscle electrical activities using wrist bands or wearable gloves. However, these devices are bulky as multiple sensory components are needed to pinpoint movements at every single joint.
In addition, say the researchers, a large amount of data needs to be collected for each user and task in order to train the algorithm. These challenges make it difficult to adopt such devices as daily-use electronics.
Their spay-on sensory system, say the researchers, is the first practical approach that is both lean enough in form and adaptable enough in function to work for essentially any user — even with limited data. Current technologies require multiple sensor components to read each joint of the finger, making them bulky, while the new device takes a leaner approach to software to allow faster learning. Such precision could be key in virtual reality applications to convey finely detailed motions for a more realistic experience.
The enabling innovation is a sprayable electrically sensitive mesh network embedded in polyurethane — the same durable-yet-stretchable material used to make skateboard wheels and to protect hardwood floors from damage. The mesh is comprised of millions of nanowires of silver coated with gold that are in contact with each other to form dynamic electrical pathways.
This mesh is electrically active, biocompatible, breathable, and stays on unless rubbed in soap and water. It conforms intimately to the wrinkles and folds of each human finger that wears it. Then a light-weight Bluetooth module can be simply attached to the mesh which can wirelessly transfer the signal changes.
“As the fingers bend and twist, the nanowires in the mesh get squeezed together and stretched apart, changing the electrical conductivity of the mesh,” says Zhenan Bao, a K.K. Lee Professor of Chemical Engineering and senior author of the study. “These changes can be measured and analyzed to tell us precisely how a hand or a finger or a joint is moving.”
A spray-on approach directly on skin was chosen so that the mesh is supported without a substrate. This key engineering decision eliminated unwanted motion artifacts and allowed the researchers to use a single trace of conductive mesh to generate multi-joint information of the fingers.
The spray-on nature of the device allows it to conform to any size or shaped hand, but also opens ups the possibility that the device could be adapted to the face to capture subtle emotional cues. That might enable new approaches to computer animation or lead to new avatar-led virtual meetings with more realistic facial expressions and hand gestures.
Machine learning then takes over: Computers monitor the changing patterns in conductivity and map those changes to specific physical tasks and gestures. Type an X on a keyboard, for instance, and the algorithm learns to recognize that task from the changing patterns in the electrical conductivity. Once the algorithm is suitably trained, the physical keyboard is no longer necessary. The same principles can be used to recognize sign language or even to recognize objects by tracing their exterior surfaces, say the researchers.
And while existing technologies are computationally intensive and require vast amounts of data that must be laboriously labeled by humans—by hand, the researchers say they have developed a learning scheme that is far more computationally efficient.
“We brought the aspects of human learning that rapidly adapt to tasks with only a handful of trials known as ‘meta-learning’,” says Kyun Kyu “Richard” Kim, a post-doctoral scholar in Bao’s lab, who is first author of the study. “This allows the device to rapidly recognize arbitrary new hand tasks and users with a few quick trials.”
“Moreover,” says Kim, “it’s a surprisingly simple approach to this complex challenge that means we can achieve faster computational processing time with less data because our nanomesh captures subtle details in its signals.”
The researchers have built a prototype that recognizes simple objects by touch and can even do predictive two-handed typing on an invisible keyboard. The algorithm was able to type, “No legacy is so rich as honesty” from William Shakespeare and “I am the master of my fate, I am the captain of my soul” from William Ernest Henley’s poem “Invictus.”
For more, see “A substrate-less nanomesh receptor with meta-learning for rapid hand task recognition.”
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
