Examining Tactile Feature Extraction for Shape Recconstruction in Robotic Grippers

Shubhan Parag Patni, Matej Hoffmann

Keywords: Tactile Sensing, Shape Reconstruction

TL;DR: We define and examine a set of tactile features that can help in describing objects to a lot of different robotic setups.

Abstract:

Different robotic setups provide tactile feedback about the objects they interact with in different manners. This makes it difficult to transfer the information gained from haptic exploration to different setups and to humans as well. We introduce “touch primitives”, a set of object features for haptic shape representation which aim to reconstruct the shape of objects independent from the robot morphology. We investigate
how precisely the primitives can be extracted from household objects by a commonly used gripper, on a set of objects that vary in size, shape and stiffness.

Confirmation: I am a student and I would like to be considered for the funding award.