Description

There has been a growing awareness of the necessity of providing replicable results in the robotic grasping research community. However, benchmarking for manipulation is particularly challenging and passes necessarily through the definition of a standardized data experimental testbed. Garment manipulation is receiving increasing attention and thus, a dedicated benchmark is necessary.

We propose to study and develop alternatives to propose a generic benchmark, that can be used by the community to compare and foster new developments to the garment manipulation task. In this theses, practical applications of the proposed measurements will be developed and tested in a real robotic system.

The work is under the scope of the following projects:

• CLOTHILDE: Cloth manipulation learning from demonstration (web)