Abstract:
Many animals, such as ravens, (and a fortiori humans) exhibit a great deal of physical intelligence that allows them to solve complex multi-step physical puzzles. This ability indicates an understanding or a faculty to represent causality and mechanisms, understand when something goes wrong, and figure out how to deal with it. As a step towards physical ingenuity in robots, I will propose initial work on a framework to represent knowledge about objects, concepts, and relationships in a causal way. The framework is constructed to (i) generate hypotheses or models to explain observations, (ii) propose and carry out tests to further rule out hypotheses, and (iii) propose a fix (currently from a library of fixes). The domain of application is doors and the many issues they can present, which comprise a number of concepts and mechanisms that are abundant in home (and other) settings.

Committee:
Prof. Chris Atkeson
Prof. Oliver Kroemer
Prof. David Held
Leo Keselman