Description

This PhD addresses the problem of understanding, recognizing, and learning of manipulation of garments for robot monitoring. We hypothesize that the perception of deformable garments heavily relies on the semantic state representation describing a unique deformation on the object. Revealing the quantity of object deformation to estimate the semantic state is a non-trivial and challenging problem due to its extreme high dimensionality and complexity. Lack of data and benchmarks is another challenge impeding progress in robot manipulation.

The work is under the scope of the following projects:

• SOCRATES: Social cognitive robotics in the European society (web)
• MdM: Unit of Excellence María de Maeztu (web)
• CLOTHILDE: Cloth manipulation learning from demonstration (web)