Scalable Coordinated Learning for H2M/R Applications over Optical Access Networks (Invited)

TL;DR

This paper presents a scalable coordinated learning approach for human-to-machine/robot communications over optical access networks, significantly reducing training time and enabling efficient deployment in Industry 5.0 environments.

Contribution

It introduces a novel global-local coordinated learning framework that enhances scalability and reduces training time for H2M/R applications over optical networks.

Findings

Approximately 72% training time saved

Effective coordination across large geographical areas

Facilitates rapid onboarding of new machines/robots

Abstract

One of the primary research interests adhering to next-generation fiber-wireless access networks is human-to-machine/robot (H2M/R) collaborative communications facilitating Industry 5.0. This paper discusses scalable H2M/R communications across large geographical distances that also allow rapid onboarding of new machines/robots as $\sim72\%$ training time is saved through global-local coordinated learning.