TacEx: GelSight Tactile Simulation in Isaac Sim -- Combining Soft-Body and Visuotactile Simulators

TL;DR

TacEx is a modular tactile simulation framework that integrates soft-body and visuotactile simulators within Isaac Sim, enabling realistic contact-rich manipulation tasks for robot training.

Contribution

It introduces a novel, integrated tactile simulation environment combining GIPC, Taxim, and FOTS for the GelSight sensor in Isaac Sim, facilitating reinforcement learning in contact-rich tasks.

Findings

Stable simulation of visuotactile sensors achieved

High-dimensional tactile data can be used for RL training

Environments include pushing, lifting, and pole balancing

Abstract

Training robot policies in simulation is becoming increasingly popular; nevertheless, a precise, reliable, and easy-to-use tactile simulator for contact-rich manipulation tasks is still missing. To close this gap, we develop TacEx -- a modular tactile simulation framework. We embed a state-of-the-art soft-body simulator for contacts named GIPC and vision-based tactile simulators Taxim and FOTS into Isaac Sim to achieve robust and plausible simulation of the visuotactile sensor GelSight Mini. We implement several Isaac Lab environments for Reinforcement Learning (RL) leveraging our TacEx simulation, including object pushing, lifting, and pole balancing. We validate that the simulation is stable and that the high-dimensional observations, such as the gel deformation and the RGB images from the GelSight camera, can be used for training. The code, videos, and additional results will be released online https://sites.google.com/view/tacex.