© Festo

The learning methods of machines are comparable to those of humans: Just like humans, they need feedback on their actions in order to classify them and learn from them. The 'BionicSoftHand' uses the reinforcement learning method - learning through reinforcement. This means that instead of a specific action that it has to imitate, the hand is simply given a goal. It tries to achieve this by trial and error. Based on the feedback it receives, it gradually optimizes its actions until it finally successfully solves the task set. Specifically, the 'BionicSoftHand' ...