BionicSoftHand: Pneumatic robot hand with artificial intelligence

BionicSoftHand

Pneumatic robot hand with artificial intelligence  

Whether grasping, holding or turning, touching, typing or pressing – in everyday life, we use our hands as a matter of course for the most diverse tasks. The human hand is a true miracle tool of nature. What could be more logical than equipping robots in collaborative working spaces with a gripper that is modelled on this natural model and can learn through artificial intelligence to solve a wide variety of gripping and turning tasks?

 

Reinforcement learning: the principle of reward

BionicSoftHand uses the method of reinforcement learning – learning by strengthening. This means that instead of having to imitate a concrete action, the hand is merely given a goal. It tries to achieve this through trial and error. Based on the positive and negative feedback received, the hand gradually optimises its actions until it finally solves the task successfully.

Digital twin of the real robot hand 

Specifically, the BionicSoftHand should rotate a 12-sided cube so 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 and the algorithms of artificial intelligence.

Digital twin: the real robot hand and its virtual image in the simulation model
Digital twin: the real robot hand and its virtual image in the simulation model

Fast knowledge transfer through massively parallel learning

The digital simulation model accelerates the training considerably, especially if you multiply it. In so-called massively parallel learning, the acquired knowledge is shared with all virtual hands, which then continue to work with the new state of knowledge; so every mistake is made only once. Successful actions are immediately available to all models.

After the control has been trained in the simulation, it is transferred to the real BionicSoftHand. With the virtually learned movement strategy, it can turn the cube to the desired side and orient other objects accordingly in the future. This was how knowledge building blocks and new skills, once learned, could be limitlessly shared and made available on a global scale.

Sophisticated functional integration: numerous components, technologies and materials are combined in the tightest of spaces
Click on the image to open the graphic with label in a new window.

Pneumatic kinematics with 3D textile knitted fabric 

Unlike the human hand, the BionicSoftHand has no bones. It controls its movements via the pneumatic bellows structures in its gripper fingers. When the chambers are filled with air, the gripper fingers bend. If the air chambers are empty, the gripper fingers remain stretched. The thumb and index finger are additionally equipped with a swivel module, which allows these two gripper fingers to be moved laterally. This gives the bionic robot hand a total of twelve degrees of freedom.

The bellows in the gripper fingers are enclosed in a special 3D textile cover which is knitted from both elastic and high-strength fibres. This means that the textile can be used to exactly determine at which points the structure expands, thereby generating force, and where it is prevented from expanding.

Proportional piezo valves for precise control

In order to keep the effort of tubing the BionicSoftHand as low as possible, the developers have specially designed a small, digitally controlled valve terminal, which is mounted directly below the hand. This means that the tubes for controlling the gripper fingers do not have to be pulled through the entire robot arm. Thus, the BionicSoftHand can be quickly and easily connected and operated with only one tube each for supply air and exhaust air. With the proportional piezo valves used, the movements of the gripper fingers can be precisely controlled.

  • BionicSoftHand

    Complete safe system: the BionicSoftHand on the BionicSoftArm

  • BionicSoftHand

    Machine vision: computer vision to collect the necessary data for a virtual image

  • BionicSoftHand

    Massively parallel learning: fast learning through the duplication of the digital twin

  • BionicSoftHand

    Easy commissioning: quick connection to various lightweight robots, such as the BionicSoftArm

  • BionicSoftHand

    Helping hand: predestined for direct collaboration in collaborative spaces

  • BionicSoftHand

    Conceivable future scenario: working from a safe distance by means of gesture imitation

  • BionicSoftHand

    Versatile usage: four BionicSoftHand pneumatic gripper fingers in an adaptive pincer gripper

Potential for human–robot collaboration

Its flexible, pneumatic kinematics and the use of elastic materials and lightweight components distinguish the BionicSoftHand from electric or cable-operated robot hands and make inexpensive production possible. Thanks to their modular design, gripper variants with three or four gripper fingers are also possible.

Combined with pneumatic lightweight robots, such as the BionicCobot or the BionicSoftArm, direct and safe human–robot collaboration is possible. Both robots are completely compliant and do not have to be shielded from the worker like conventional factory robots.

The BionicSoftHand is therefore predestined for applications in the collaborative working spaces of tomorrow’s factories. Since the flexible robot hand can grip both strongly and sensitively, it can conceivably be used in assembly as a helping third hand and also in service robotics.