Xing Li, Oliver Brock
We will develop a novel approach to Learning from Demonstration for teaching a robot complex, contact-rich manipulation tasks. This approach will enable the robots to physically operate complex locks and other mechanisms. The scientific challenge consists of reliably operating such multi-degree-of-freedom mechanisms that require transitions between different multi-contact situations. Rather than programming these manipulation actions directly, we will have a human demonstrate motions to the robot. We will use our knowledge about the problem and a clever way to elicit demonstration behavior to produce robust and transferable manipulation strategies. These strategies will form an important building block for the one of the SCIoI demonstrators in which a mobile manipulator has to escape from an escape room. To develop and validate the proposed approach to Learning from Demonstration, we will construct escape rooms of increasing mechanical complexity, matching the newly posed challenges to further advances in our approach.
This project is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy - EXC 2002/1 "Science of Intelligence" - project number 390523135.