Future robotics applications will require complex movement skills that coordinate many degrees of freedom and incorporate sensory feedback of different kinds. Our research targets at devising movement representation, control and learning concepts that enable robots to operate and interact in cluttered and dynamic environments, and in cooperation with humans. We want our robots to learn to work in a team with humans or other systems. Research in whole-body and force interaction control forms a basis for robust movement generation.
Applying new concepts for learning to artificial manipulation allows the efficient and intuitive transfer of complex skills from a human expert to a machine. Bi-manual tasks like the exchange of a light-bulb or tasks that require the direct cooperation between a robot and a human serve as examples to demonstrate the advances in intelligent robotics.