Deep Learning

Synthetic image data for segmentation tasks has proved beneficial in scenarios with data scarcity. However, most of these methods fail to capture the physics of the components involved, thus generating unrealistic image data. With the aid of physics simulators, we explore different avenues for generating physics-informed synthetic images.

Compliant or deformable objects are challenging to manipulate due to their inherent physical properties. However, the majority of the objects humans interact with are deformable. This work focuses on enabling robots to handle such objects with greater efficiency and flexibility and to be able to adapt to changes in the objects or their surroundings.