Scientists have designed a robotic hand that can grab objects – and not drop them – using only the movement of the wrist and the sensation in its ‘skin’.
The University of Cambridge researchers said this mechanical hand doesn’t require the fingers to move independently and uses “passive” motion using the wrists, making their technology low-cost as well as energy-efficient.
The robot’s hand was also able to predict whether it could drop objects it grabbed using information provided by sensors placed on it.
Experts said their findings, published in the journal Advanced Intelligent Systems, could be used in the development of low-cost robotics in which mechanical hands can learn to grip a wide range of objects while still being capable of natural movements.
Scientists have said that the human hand is very complex, which means that recreating all of its capabilities in a robot can be a huge research challenge.
For example, experts said, humans instinctively know how much force to use to pick up an egg, but for a robot, that’s a challenge.
If the robot applies too much force, the egg may break, and if there is not enough pressure, it may drop the egg.
Scientists have created a 3D printed robotic hand implanted with sensors that could allow the hand to “feel” what it’s touching.
This hand was only capable of passive wrist-based movements, and the individual fingers were not fully motorized.
More than 1,200 tests have been carried out using the robotic hand.
The hand was initially trained using small 3D printed plastic spheres, after which it attempted to grip several objects, including a peach, a computer mouse and a roll of bubble wrap.
The robotic hand was able to successfully grasp 11 of the 14 objects, the researchers said.
Dr Thomas George-Thuruthel, formerly of the University of Cambridge and now a lecturer in robotics and artificial intelligence in the Department of Computer Science at University College London, said: ‘The sensors, which are a bit like the skin on the robot , measure the pressure that is applied to the object.
“We can’t tell exactly what information the robot is getting, but it can theoretically estimate where the object was grabbed and how hard.
“The hand is very simple, but it can pick up many items with the same strategy.”
Fumiya Iida, professor of robotics in the Department of Engineering at Cambridge University, added: “The big advantage of this design is the range of motion we can achieve without using any actuators.
“We want to make the hand as simple as possible.
“We can get a lot of good information and a high degree of control without actuators, so when we add them, we’ll get more complex behavior in a more efficient package.”
The research was funded by UK Research and Innovation (UKRI) and software design firm Arm Ltd.