Ultra-sensitive artificial skin developed by NUS may give robots, prosthetics improved touch
SINGAPORE — Viral online videos poke fun at robots struggling to open doors or lift coffee cups but their seeming inability to master the sense of touch could change, thanks to a breakthrough by a team of Singapore researchers.
Quiz of the week
How well do you know the news? Test your knowledge.
SINGAPORE — Viral online videos poke fun at robots struggling to open doors or lift coffee cups but their seeming inability to master the sense of touch could change, thanks to a breakthrough by a team of Singapore researchers.
The team from the National University of Singapore (NUS) has just unveiled an electronic skin (e-skin) that can detect touch 1,000 times faster than the human nervous system.
The breakthrough, published in the prestigious scientific journal Science Robotics on Thursday (July 18), could lead the way to much nimbler robots and could even provide a better sense of touch for prosthetic devices fitted to people.
The e-skin is called Asynchronous Coded Electronic Skin (Aces), and is inspired by the human sensory nervous system.
The e-skin detects signals and differentiates physical contact like a human being. But unlike nerve bundles in human skin, the electronic nervous system is made of a network of sensors, connected with a single electrical conductor.
According to Assistant Professor Benjamin Tee, who leads the team of nine from the Department of Materials Science and Engineering at the NUS Faculty of Engineering, the sense of touch is an integral element in helping humans navigate the physical world, saying that “without it, we will even lose our sense of balance when walking”.
“Similarly, robots need to have a sense of touch in order to interact better with humans, but robots today still cannot feel objects very well,” he said in a press release.
The artificial skin provides a simple wiring system that can improve the responsiveness of artificial intelligence (AI) applications in robots, increasing the sensitivity of the machine to its surroundings and facilitating more effective functioning.
E-SKIN COULD HELP ROBOTS IN DISASTER RECOVERY
The development could also advance the use of intelligent robots that could perform disaster recovery tasks or take over mundane operations such as packing items in warehouses.
The innovation is an immense development from traditional sensor arrays that feature synchronous systems which can detect physical contact only one by one with each scan.
The Aces technology however, enables all sensors to work simultaneously, making detection much faster.
Functioning as an artificial nervous system, the unique sensor system can respond 1,000 times faster than the human sense of touch. It can even accurately identify the shape, texture and hardness of objects within 10 milliseconds, which is 10 times faster than a blink of an eye, according to the NUS team.
Asked if the technology’s high responsiveness might be too strong for its own good, Prof Tee said there is a risk of being too responsive, but added that the level of responsiveness can be adjusted according to the needs of the applications it is being incorporated in. This refinement is already in the works, he added.
With the application of this artificial skin, robots can better handle objects such as doors and cups, adjusting to pressure, temperature and texture among many other factors that mirror the human touch.
FASTER MANUFACTURING PRODUCTION
Prof Tee projects that this could help lower the cost of manufacturing production, noting that the new technology could aid machines in completing more than one task, which is often the case for machines used in manufacturing industries.
Prosthetic devices and other human machine interfaces such as virtual reality could also benefit from the breakthrough. Clinical trials for the implementation of the e-skin in prosthetic devices are already in the works and will be starting next year with an international candidate who will be implanting a hand prosthetic. This could mean restoring a sense of touch to individuals who need prosthetics.
Prof Tee postulates that machines that use the artificial skin could hit the commercial market within two years. But while recognising that the “field is progressing quickly”, commercial products for humans might still need to wait five to 10 years.
The NUS team filed for a patent for the technology in 2017. It is looking towards adapting its design to achieve even greater robustness to physical damage.
“Our sense of touch, for example, does not get affected when we suffer a cut. If we can mimic how our biological system works and make it even better, we can bring about tremendous advancements in the field of robotics where electronic skins are predominantly applied,” said Prof Tee.
The NUS team said that pairing Aces with the transparent, self-healing and water-resistant sensor skin layer also recently developed by Prof Tee’s team creates an electronic skin that can self-repair, like the human skin. This type of electronic skin can be used to develop more realistic prosthetic limbs that will help disabled individuals restore their sense of touch.