Towards vision-based robotic skins: a data-driven, multi-camera tactile sensor

TL;DR

This paper introduces a multi-camera optical tactile sensor that uses particle motion and machine learning to accurately map contact forces, offering a scalable, thin, and large-area solution for robotic skins.

Contribution

It presents a novel, scalable design of a multi-camera tactile sensor that captures contact force distribution without mirrors, suitable for robotic skin applications.

Findings

Larger contact surface compared to existing sensors

Thinner sensor structure without mirrors

Effective machine learning mapping of force distribution

Abstract

This paper describes the design of a multi-camera optical tactile sensor that provides information about the contact force distribution applied to its soft surface. This information is contained in the motion of spherical particles spread within the surface, which deforms when subject to force. The small embedded cameras capture images of the different particle patterns that are then mapped to the three-dimensional contact force distribution through a machine learning architecture. The design proposed in this paper exhibits a larger contact surface and a thinner structure than most of the existing camera-based tactile sensors, without the use of additional reflecting components such as mirrors. A modular implementation of the learning architecture is discussed that facilitates the scalability to larger surfaces such as robotic skins.