DenseTact: Optical Tactile Sensor for Dense Shape Reconstruction

TL;DR

DenseTact is a cost-effective, scalable optical tactile sensor that uses deep learning to achieve real-time, high-resolution 3D surface reconstruction, enhancing robotic manipulation capabilities.

Contribution

The paper introduces a novel inexpensive and scalable tactile sensor with high-resolution surface deformation modeling using deep neural networks for real-time shape reconstruction.

Findings

Successfully estimates surface deformation in 1.8ms

Enables high-resolution 3D shape reconstruction

Improves in-hand object localization and classification

Abstract

Increasing the performance of tactile sensing in robots enables versatile, in-hand manipulation. Vision-based tactile sensors have been widely used as rich tactile feedback has been shown to be correlated with increased performance in manipulation tasks. Existing tactile sensor solutions with high resolution have limitations that include low accuracy, expensive components, or lack of scalability. In this paper, an inexpensive, scalable, and compact tactile sensor with high-resolution surface deformation modeling for surface reconstruction of the 3D sensor surface is proposed. By measuring the image from the fisheye camera, it is shown that the sensor can successfully estimate the surface deformation in real-time (1.8ms) by using deep convolutional neural networks. This sensor in its design and sensing abilities represents a significant step toward better object in-hand localization, classification, and surface estimation all enabled by high-resolution shape reconstruction.