The realization of autonomous mobile manipulators will enable
a variety of applications with significant societal, scientific, and economical impact.
To enable autonomous manipulation of previously unseen objects,
robots must possess perceptual capabilities for modeling objects
in their environment and for observing their motion during manipulation.
My research focuses on the development of a set of perceptual
in service of manipulation in unstructured environments.
These skills would enable a robot to acquire the information necessary
to interact with a previously unseen object in a purposeful way.
- Interactive Perception of Articulated Objects
- Semi-Autonomous Manipulation of Natural Objects
- Autonomous Manipulation in Clutter