DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration

TL;DR

DOT-Sim is a novel differentiable optical tactile sensor simulator that accurately models physical and optical properties, enabling fast calibration and realistic zero-shot sim-to-real transfer for tactile tasks.

Contribution

The paper introduces DOT-Sim, a physically accurate, differentiable optical tactile simulation framework that supports large deformations and optical response learning, with rapid calibration from few demonstrations.

Findings

Accurately replicates DenseTact sensor dynamics in reality.

Generates realistic optical outputs in contact-rich scenarios.

Enables high-accuracy real-world deployment of simulation-trained classifiers.

Abstract

Simulating optical tactile sensors presents significant challenges due to their high deformability and intricate optical properties. To address these issues and enable a physically accurate simulation, we propose DOT-Sim: Differentiable Optical Tactile Simulation. Unlike prior simulators that rely on simplified models of deformable sensors, DOT-Sim accurately captures the physical behavior of soft sensors by modeling them as elastic materials using the Material Point Method (MPM). DOT-Sim enables rapid calibration of optical tactile sensor simulation using a small number of demonstrations within minutes, which is substantially faster than existing methods. Compared to current baselines, our approach supports much larger and non-linear deformations. To handle the optical aspect, we propose a novel approach to simulating optical responses by learning a residual image relative to the real-world idle state. We validate the physical and visual realism of our method through a series of zero-shot sim-to-real tasks. Our experiments show that DOT-Sim (1) accurately replicates the physical dynamics of a DenseTact optical tactile sensor in reality, (2) generates realistic optical outputs in contact-rich scenarios, (3) enables direct deployment of simulation-trained classifiers in the real world, achieving 85% classification accuracy on challenging objects and 90% accuracy in embedded tumor-type detection, and (4) allows precise trajectory following with a policy trained from demonstrations in simulation, with an average error of less than 0.9 mm.