According to its developers, the bionic hand adjusts its grasp to avoid damaging or mishandling whatever it is holding.

Source: Johns Hopkins University

In the lab, the bionic hand identified and manipulated 15 everyday objects — such as stuffed toys, dish sponges, cardboard boxes, pineapples and metal water bottles, among others — successfully handling objects with a roughly 99% rate of accuracy.

The developers believe that the technology offers a potential solution for people with hand loss and could also possibly improve how robotic arms interact with their environments.

The bionic hand features a multi-finger system with rubberlike polymers and a rigid 3D-printed internal skeleton. It also features three layers of tactile sensors — inspired by the layers of human skin — which enable the device to grasp and distinguish objects of assorted shapes and surface textures, according to a press release from Johns Hopkins.

Further, each of the hand's soft air-filled finger joints can reportedly be controlled with the forearm’s muscles while machine learning algorithms concentrate the signals from the artificial touch receptors to encourage a realistic sense of touch.

“The sensory information from its fingers is translated into the language of nerves to provide naturalistic sensory feedback through electrical nerve stimulation,” the team noted.

The team added that the technology enables the hand to operate via muscle signals from the forearm, similar to most hand prostheses. Such signals serve as a bridge between the brain and nerves, enabling the hand to flex, release or react according to its sense of touch, ultimately resulting in a robotic hand that “knows” what it’s touching — much like the nervous system does.

“If you’re holding a cup of coffee, how do you know you’re about to drop it? Your palm and fingertips send signals to your brain that the cup is slipping,” the researchers explained. “Our system is neurally inspired — it models the hand’s touch receptors to produce nervelike messages so the prosthetics brain or its computer, understands if something is hot or cold, soft or hard, or slipping from the grip.”