April/May 2019

INTEGRATED SYSTEMS 46 HYDRAULICS & PNEUMATICS April/May 2019 www.hpmag.co.uk Whether it’s grabbing, holding or turning, touching, typing or pressing - we use our hands for the most diverse tasks. The human hand, with its unique combination of power, dexterity and fine motor skills, is a true miracle tool of nature. So, what could be more natural than equipping robots in collaborative workspaces with a gripper that is modelled on the human hand, and which solves various tasks by learning through artificial intelligence? Festo showed its pneumatic BionicSoftHand at Hanover Fair 2019. Combined with the BionicSoftArm, a pneumatic lightweight robot, the Future Concepts are suitable for human-robot collaboration. The BionicSoftHand is pneumatically operated, so that it can interact safely and directly with people. Unlike the human hand, the BionicSoftHand has no bones. Its fingers consist of flexible bellows structures with air chambers. The bellows are enclosed in the fingers by a special 3D textile coat knitted from elastic, high-strength threads. With the help of the textile, it is possible to determine exactly where the structure expands and generates power, and where it is prevented from expanding. This makes it light, flexible, adaptable and sensitive, yet capable of exerting strong forces. Artificial Intelligence The learning methods of machines are comparable to those of humans: they require a positive or negative feedback following their actions in order to classify and learn from them. BionicSoftHand uses the method of reinforcement learning. This means that instead of imitating a specific action, the hand is merely given a goal. It uses trial and error to achieve its goal. Based on received feedback, it gradually optimises its actions until the task is finally solved successfully. Specifically, the BionicSoftHand is required to rotate a 12-sided cube so Festo pneumatic robotics get to grips with artificial intelligence that a previously defined side points upwards at the end. The necessary movement strategy is taught in a virtual environment with the aid of a digital twin, which is created with the help of data from a depth-sensing camera via computer vision and the ABOVE: The BionicSoftHand should rotate a 12-sided cube so that a previously defined side points upwards at the end. LEFT: The BionicSoftHand is operated pneumatically for the safe and direct interaction with people.