Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems

Abstract

Next-generation autonomous and networked industrial systems (i.e., robots, vehicles, drones) have driven advances in ultra-reliable, low latency communications (URLLC) and computing. These networked multi-agent systems require fast, communication-efficient and distributed machine learning (ML) to provide mission critical control functionalities. Distributed ML techniques, including federated learning (FL), represent a mushrooming multidisciplinary research area weaving in sensing, communication and learning. FL enables continual model training in distributed wireless systems: rather than fusing raw data samples at a centralized server, FL leverages a cooperative fusion approach where networked agents, connected via URLLC, act as distributed learners that periodically exchange their locally trained model parameters. This article explores emerging opportunities of FL for the next-generation networked industrial systems. Open problems are discussed, focusing on cooperative driving in connected automated vehicles and collaborative robotics in smart manufacturing.

The paper has been accepted for publication in the IEEE Communications Magazine. The current arXiv contains an additional Appendix that describes the dataset for the setup of Fig. 5

References in corpus (2)

• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• A Multisensory Edge-Cloud Platform for Opportunistic Radio Sensing in Cobot Environments

Cited by in corpus (23)

• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
• Over-the-Air Computation for 6G: Foundations, Technologies, and Applications
• A Tutorial on 5G Positioning
• An Overview of Federated Learning at the Edge and Distributed Ledger Technologies for Robotic and Autonomous Systems
• Artificial Intelligence in Industry 4.0: A Review of Integration Challenges for Industrial Systems
• Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving
• A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsification
• 6G V2X Technologies and Orchestrated Sensing for Autonomous Driving
• Combining Federated Learning and Control: A Survey
• Enhancing Scalability and Reliability in Semi-Decentralized Federated Learning With Blockchain: Trust Penalization and Asynchronous Functionality
• Channel-driven Decentralized Bayesian Federated Learning for Trustworthy Decision Making in D2D Networks
• Gossiped and Quantized Online Multi-Kernel Learning
• Integrating Sensing and Communication in Cellular Networks via NR Sidelink
• Analog MIMO Communication for One-shot Distributed Principal Component Analysis
• An Energy and Carbon Footprint Analysis of Distributed and Federated Learning
• Cooperation and Federation in Distributed Radar Point Cloud Processing
• A Framework for Energy and Carbon Footprint Analysis of Distributed and Federated Edge Learning
• On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning
• Over-the-Air Decentralized Federated Learning
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
• UAV Aided Over-the-Air Computation
• On Addressing Heterogeneity in Federated Learning for Autonomous Vehicles Connected to a Drone Orchestrator
• Multi-Modal Multi-Task (M3T) Federated Foundation Models for Embodied AI: Potentials and Challenges for Edge Integration