Robotics continues to advance to create devices that can do almost anything like humans, the most recent being a robotic hand that can grab objects and not drop them.
Researchers have designed a low-cost, low-power robotic hand that can grasp a variety of objects -and not drop them- using only the movement of your wrist and the sensitivity of your “skin”.
Grasping objects of different sizes, shapes, and textures is an easy problem for a human being, but a difficult one for a robot. Researchers at the University of Cambridge designed a 3D-printed soft robotic hand that he cannot move his fingers independently, but can perform a series of complex movements.
robotic hand trained to grasp different objects and was able to predict if he would drop them thanks to the information provided by the sensors placed on his “skin”.
This type of passive movement makes the robot much easier to control and much more energy efficient than fully motorized finger robots. The researchers claim that their adaptable design could be used in the development of low-cost robots. able to make more natural movements and learn to grasp a wide range of objects.
The human hand is highly complex, and recreating all of its dexterity and adaptability in a robot is a huge research challenge. Most of the Current advanced robots are not capable of manipulative tasks that small children can easily perform..
For example, a human being instinctively knows how much force to use to pick up an egg, but for a robot it is quite a challenge: too much force, and the egg could break; too little, and the robot might drop it. Plus, a fully powered robotic hand, with motors for each joint of each fingerrequires a significant amount of energy.
In Professor Fumiya Iida’s Bioinspired Robotics Laboratory, Cambridge Department of Engineering, researchers have been developing possible solutions to both problems: a robotic hand that can grasp a variety of objects with the right amount of pressure and using a minimal amount of energy.
“In previous experiments, our lab has shown that it is possible to achieve significant range of motion in a robotic hand just by moving the wrist,” explains co-author Dr Thomas George-Thuruthel, who is now at University College London (UCL). ) East. “We wanted to see if a robotic hand based on passive movement could not only grasp objectsbut to be able to predict if they were going to fall or not, and adapt accordingly.
The researchers used a 3D-printed anthropomorphic hand implanted with tactile sensors, so that the hand could perceive what it touched. The hand was only capable of passive movements with the wrist.
He team conducted more than 1,200 tests with the robotic hand, looking at its ability to grasp small objects without dropping them. The robot was initially trained using small 3D-printed plastic balls, grasping them using a predefined action obtained through human demonstrations.
The robot used trial and error to learn what type of grip would work for it. After finishing the training with the balls, he tried to catch different objects, such as a peach, a computer mouse and a roll of bubble wrap. In these tests, the hand was able to successfully grasp 11 out of 14 objects.
• Children believe that assistants like Alexa should be treated well and not yelled at
• Can humans regain trust when a robot lies? scientists explain
• Will they be replaced by technology? AI is more accurate than sonographers
Source: La Opinion