Scientists have developed highly sensitive artificial skin in the shape of a hand to help robots ‘feel’ their surroundings, a new study published in Science Robotics shows.
Researchers from University College London (UCL) and the University of Cambridge made the skin from a stretchy material called a hydrogel, which is soft, cheap and can conduct electricity.
The skin can pick up different signals like touch, texture, moisture, pressure, pain and temperature all at once, making it useful for robotic hands or future human prosthetics where a sense of touch is vital.
Study co-author and UCL Computer Science’s Dr Thomas George Thuruthel said: “We’re not quite at the level where the robotic skin is as good as human skin, but we think it’s better than anything else out there at the moment.
“Our method is flexible and easier to build than traditional sensors, and we’re able to calibrate it using human touch for a range of tasks.”
Most traditional approaches used different types of sensors to detect different types of touch – one type of sensor to detect pressure, another for temperature, and so on.
However, the signals from these different types of sensors can interfere with each other, and the materials can be more expensive and easily damaged.
The UCL and Cambridge team took a different approach, where the entire surface of the robotic skin acted as a single sensor which could recognise multiple types of touch simultaneously, similar to human skin.
Being able to detect various types of touch could allow robots to interact with the world in a more meaningful way and perform more advanced tasks in industries like robotic surgery and space exploration.
The low-cost material is also highly flexible, and can be melted down and cast into a range of complex shapes.
Dr David Hardman, lead author of the study from Cambridge’s Department of Engineering, said: “Having different sensors for different types of touch leads to materials that are complex to make.
“We wanted to develop a solution that can detect multiple types of touch at once, but in a single material.
“We’re able to squeeze a lot of information from these materials – they can take thousands of measurements very quickly.
“They’re measuring lots of different things at once, over a large surface area.”
The scientists tested the skin’s senses by blasting it with a heat gun, cutting it with a scalpel and prodding it with their fingers.
With only 32 electrodes located at the robot’s wrist, the researchers collected over 1.7 million pieces of information through 860,000 tiny pathways in the hand.
The team then trained the skin to understand what the various signals meant using a machine learning algorithm.
In the future, the researchers will look at improving the durability of the electronic skin, and test how the skin performs during different tasks.
Feature image: Cash Macanaya on Unsplash
Join the discussion