Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913731905060864 |
|---|---|
| author | Gummadi, Shreya Gasparino, Mateus V. Vasisht, Deepak Chowdhary, Girish |
| author_facet | Gummadi, Shreya Gasparino, Mateus V. Vasisht, Deepak Chowdhary, Girish |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04112 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigation Gummadi, Shreya Gasparino, Mateus V. Vasisht, Deepak Chowdhary, Girish Robotics Artificial Intelligence Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing 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. |
| title | Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigation |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2411.04112 |