High-availability displacement sensing with multi-channel self mixing interferometry

TL;DR

This paper presents a multi-channel self-mixing interferometry system enhanced with neural networks, achieving robust high-availability displacement sensing even with signal loss or noise, advancing nonlinear photonics sensing.

Contribution

It introduces a novel multi-channel self-mixing sensor combined with neural networks for robust displacement measurement under challenging conditions.

Findings

High-availability motion sensing with multi-channel signals

Robustness to measurement noise and signal loss

Potential for multimodal complex photonics sensing

Abstract

Laser self-mixing is in principle a simple and robust general purpose interferometric method, with the additional expressivity which results from nonlinearity. However, it is rather sensitive to unwanted changes in target reflectivity, which often hinders applications with non-cooperative targets. Here we analyze experimentally a multi-channel sensor based on three independent self-mixing signals processed by a small neural network. We show that it provides high-availability motion sensing, robust not only to measurement noise but also to complete loss of signal in some channels. As a form of hybrid sensing based on nonlinear photonics and neural networks, it also opens perspectives for fully multimodal complex photonics sensing.