arXiv:2502.20598cs.NIcs.AI2025-02中稿 · publication in 29t…
通过协同学习实现远距离人机协作，训练效率提升72%。
Scalable Coordinated Learning for H2M/R Applications over Optical Access Networks (Invited)
- 采用全局-局部协同学习框架，支持大规模分布式设备
- 实测节省约72%训练时间，显著提升部署速度
- 适合工业5.0中快速接入新机器人或智能设备的场景
下一代光无线接入网络的核心研究方向之一是支持工业5.0的人机/机器人（H2M/R）协同通信。本文探讨了跨大范围地理区域的可扩展H2M/R通信方案，通过全局-局部协同学习，使新设备的快速接入成为可能，实测训练时间减少约72%。
原文摘要 · Abstract (English)
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.
人机协同光接入网工业5.0
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。