The envisioned smart industrial systems rely on networked machines with increasing level of intelligence and autonomy, moving far beyond traditional low-cost, low-power sensors. Networked and cooperative intelligent machines have recently opened new research opportunities that target the integration of distributed learning tools with sensing, communication and decision operations. Cross-fertilization of these components is crucial to enable challenging collaborative tasks in terms of safety, reliability, scalability and latency. Among distributed learning techniques, federated learning (FL) has been emerging for privacy-preserving model training in decentralized wireless systems.

For further reading see: https://arxiv.org/abs/2101.03367

Distributed FL for cooperative perception by real-time fusion of imaging data at different vehicles.