The LearningGripper looks like an abstract form of the human hand. And its actions also have a lot in common with its natural role model: The robot gripper with four fingers automatically learns by means of the machine learning process to rotate a sphere in a raised position into any given orientation.
Only the elementary actions and possible positions of the LearningGripper's fingers, as well as the function for feedback from the environment, are defined in advance so that this complex handling can be carried out. The gripper is only told what it needs to be able to do, not how to do it. The movement strategy required for this is developed independently by the gripper’s learning algorithms – without any further programming.
Theories state that we humans are only so intelligent because our hand can solve so many complex tasks. Babies start to grasp objects very early – for example their mother's finger. As soon as we have learned to grasp an object correctly, we can turn it around and look at it from all sides. This is the only way to reconstruct a three-dimensional image of the object in the head. So the hand also serves us humans for learning.
The learning methods of machines are comparable to those of humans: whether positive or negative – they need feedback on their actions in order to be able to classify them and learn from them. The LearningGripper uses the method of reinforcement learning. The gripper is not given any concrete action that it has to imitate. It optimizes its skills exclusively on the basis of feedback on its previous actions. This increases the probability that it will execute a successful move and will not repeat a less successful move.
The four fingers are driven by a total of twelve pneumatic bellows actuators with low pressure between 2.5 and 3.5 bar. Each of them has three degrees of freedom and the basic functions of the index finger. In the initial state alone, the entire hand thus has a choice of 3¹² total actions to reposition the sphere. Due to the intelligent coordination of the fingers and the flexible bellows structure, the kinematics are freely movable and flexible. It can safely grip, lift and rotate even the most sensitive objects – just like its natural role model.
On the LearningGripper exhibit, a gripper demonstrates how it learns a movement strategy mechanically within an hour how it takes less than an hour for it to learn a mechanical motion strategy – from its first attempt to the reliable execution of the required task. A second gripper shows the learned procedure in the desired target scenario: It lifts the sphere and turns it so that the embossed lettering on the end is visible in the middle on the top.