MADRID, 3 Abr. (EUROPA PRESS) –
Taking inspiration from the human finger, MIT researchers have developed a robotic hand with tactile sensors capable of accurately identify an object after grabbing it just once.
Many robotic hands place all of their powerful sensors in their fingertips, so an object must be in full contact with those fingertips to be identified. which can force multiple grabs. Other designs use lower-resolution sensors spread across the entire length of the finger, but these don’t capture as much detail, so multiple grips are often required as well.
Instead, the MIT team built a robotic finger with a rigid skeleton encased in a soft outer shell which has multiple high-resolution sensors embedded under its transparent “skin”. Using a camera and LEDs to gather visual information about an object’s shape, the sensors provide continuous detection along the entire length of the finger. Each finger captures rich data on many parts of an object simultaneously.
Using this design, the researchers built a three-fingered robotic hand that could identify objects after a single grasp, with an accuracy of around 85 percent. The rigid skeleton makes the fingers strong enough to lift a heavy object, such as a drill, while the soft skin allows them to securely grip a flexible objectlike an empty plastic water bottle, without crushing it.
These soft, stiff fingers could be especially useful in a home care robot designed to interact with an elderly person. The robot could lift a heavy item from a shelf with the same hand you use to help the person bathe.
“Having soft and rigid elements is very important in any hand, but so is being able to do great detection over a really large area, especially if we want to consider doing very complicated manipulation tasks like what our bare hands can do. Our goal with this work was to combine all the things that make our human hands so good into a robotic finger that can do tasks that other robotic fingers cannot currently do,” he says. it’s a statement mechanical engineering graduate student Sandra Liu, co-lead author of a research paper on the robotic finger.
The research is being presented at the RoboSoft Conference in Singapore, April 3-7.. It is already available on the prepress server arXiv.
The robotic finger is made up of a rigid 3D-printed endoskeleton that is placed in a mold and wrapped in a transparent silicone “skin.” Casting the finger in a mold eliminates the need for fasteners or adhesives to keep the silicone in place.
A CURVED MOLD
The researchers designed the mold with a curved shape so that the robotic fingers are slightly curved when at rest, just like human fingers.
“Silicone wrinkles when it bends, so we thought if we have our finger molded into this curved position, when you bend it further to grip an object, it won’t cause as many wrinkles. Wrinkles are good in some ways: it can help the finger glides along the surfaces very smoothly and easily, but we didn’t want wrinkles that we couldn’t control,” says Liu.
The endoskeleton of each finger contains a pair of detailed touch sensors, known as GelSight sensors, embedded in the upper and middle sections, under the transparent skin. The sensors are placed so that the range of the cameras overlaps slightly, which provides the finger with continuous detection throughout its entire length.
Using the illuminated contours that appear on the smooth skin, an algorithm performs backward calculations to map the contours onto the surface of the grasped object. The researchers trained a machine learning model to identify objects using raw camera image data.