Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning for Autonomous Visual Robot Navigation

Centralized learning requires data to be aggregated at a central server, which poses significant challenges in terms of data privacy and bandwidth consumption. Federated learning presents a compelling alternative, however, vanilla federated learning methods deployed in robotics aim to learn a single...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 9; H. 12; S. 11841 - 11848
Hauptverfasser: Gummadi, Shreya, Gasparino, Mateus V., Vasisht, Deepak, Chowdhary, Girish
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.12.2024
Schlagworte:
Bandwidth
Computational modeling
Computer vision
Data models
Decentralized control
Distributed robot systems
Federated learning
Navigation
Predictive models
Robot vision systems
robotics in under-resourced settings
Servers
Training
vision-based navigation
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Centralized learning requires data to be aggregated at a central server, which poses significant challenges in terms of data privacy and bandwidth consumption. Federated learning presents a compelling alternative, however, vanilla federated learning methods deployed in robotics aim to learn a single global model across robots that works ideally for all. But in practice one model may not be well suited for robots deployed in various environments. This letter proposes Federated-EmbedCluster (Fed-EC), a clustering-based federated learning framework that is deployed with vision based autonomous robot navigation in diverse outdoor environments. The framework addresses the key federated learning challenge of deteriorating model performance of a single global model due to the presence of non-IID data across real-world robots. Extensive real-world experiments validate that Fed-EC reduces the communication size by 23x for each robot while matching the performance of centralized learning for goal-oriented navigation and outperforms local learning. Fed-EC can transfer previously learnt models to new robots that join the cluster.
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2024.3498778