Tactile Neural De-rendering

TL;DR

This paper introduces Tactile Neural De-rendering, a generative model that reconstructs 3D object representations from tactile data, improving pose estimation and uncertainty quantification in robotic perception.

Contribution

It presents a novel generative approach to tactile data interpretation, moving beyond traditional deterministic models for better 3D reconstruction and pose estimation.

Findings

Effective 3D reconstruction from tactile signatures

Enhanced pose estimation accuracy

Quantification of tactile perception uncertainty

Abstract

Tactile sensing has proven to be an invaluable tool for enhancing robotic perception, particularly in scenarios where visual data is limited or unavailable. However, traditional methods for pose estimation using tactile data often rely on intricate modeling of sensor mechanics or estimation of contact patches, which can be cumbersome and inherently deterministic. In this work, we introduce Tactile Neural De-rendering, a novel approach that leverages a generative model to reconstruct a local 3D representation of an object based solely on its tactile signature. By rendering the object as though perceived by a virtual camera embedded at the fingertip, our method provides a more intuitive and flexible representation of the tactile data. This 3D reconstruction not only facilitates precise pose estimation but also allows for the quantification of uncertainty, providing a robust framework for tactile-based perception in robotics.