Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigation
This addresses bandwidth efficiency and model personalization for autonomous robots in outdoor settings, though it is incremental as it builds on existing federated learning methods.
The paper tackles the problem of federated learning for autonomous robot navigation in diverse environments, where a single global model performs poorly due to non-IID data. It proposes Fed-EC, which reduces communication size by 23x while matching centralized learning performance and outperforming local learning.
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 paper 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.