Abstract:
Tactile sensing has seen a rapid adoption with the advent of vision-based tactile sensors. Vision-based tactile sensors provide high resolution, compact and inexpensive data to perform precise in-hand manipulation and human-robot interaction. However, the simulation of tactile sensors is still a challenge. Simulation is a critical tool in the development of robotic systems. In this work, we develop an optical simulation system using physics-based rendering(PBR) techniques for simulation of vision-based tactile sensors with the objective to design new tactile sensors. The simulation system generates realistic simulation together with the ability to control light parameterization, surface coating material and sensing surface geometry.

Second part of the work will focus on posing the tactile sensor design as an optimization problem with automated sensor design generation, optical simulation and sensor evaluation steps. We show changes in a) sensor shapes, b) illumination shape design and c)illumination location to come up with a new tactile sensor to improve the sensor design.

Committee:
Prof. Wenzhen Yuan (Chair)
Prof. Matthew P. O’Toole
Prof. Oliver Kroemer
Jacky Liang