Simulation of Vision-based Tactile Sensors using Physics based Rendering
This work provides a valuable simulation tool for researchers and developers working with vision-based tactile sensors, enabling more efficient development and testing of robotic manipulation and human-robot interaction applications.
This paper addresses the challenge of simulating vision-based tactile sensors, specifically the GelSight sensor, by developing the first fully general optical tactile simulation system using physics-based rendering. The system incorporates physically accurate light models and demonstrates qualitative and quantitative improvements over previous simulation techniques in image similarity metrics.
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. In this paper, we built the first fully general optical tactile simulation system for a GelSight sensor using physics-based rendering techniques. We propose physically accurate light models and show in-depth analysis of individual components of our simulation pipeline. Our system outperforms previous simulation techniques qualitatively and quantitative on image similarity metrics. Our code and experimental data is open-sourced at https://labs.ri.cmu.edu/robotouch/tactile-optical-simulation/