A team of researchers from the University of Cambridge has developed a low-cost and energy-efficient robotic hand that uses wrist movement and tactile sensing to grasp and hold a variety of objects.
While this is a simple task for humans, robots face difficulties in grasping objects with varying sizes, shapes, and textures. To overcome this challenge, the researchers utilized 3D printing technology to create a flexible robotic hand that can perform complex movements despite the inability to move its fingers independently. By training the robot hand to recognize different objects and using sensors on its “skin,” it can predict whether it will drop the objects.
The design uses soft components to make the robot more energy-efficient and easier to control. The hand can grasp objects with the correct amount of pressure while using minimal energy, making it a potential solution to the challenge of creating robots that can perform manipulation tasks as easily as humans. The results were reported in the journal Advanced Intelligent Systems.
The robot learned through trial and error how to successfully grasp different objects, including a peach, a computer mouse, and a roll of bubble wrap, using sensors that measure pressure on the object. The robot can estimate where the object has been grasped and with how much force. The hand is simple but customizable and can pick up a lot of objects with the same strategy. The design allows for a range of motion without actuators and can simplify the hand while maintaining a high degree of control.
