Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data
Uloženo v:
| Název: | Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data |
|---|---|
| Autoři: | Boyi Liu, Lujia Wang, Ming Liu, Cheng-Zhong Xu |
| Zdroj: | IEEE Robotics and Automation Letters. 5:3509-3516 |
| Publication Status: | Preprint |
| Informace o vydavateli: | Institute of Electrical and Electronics Engineers (IEEE), 2020. |
| Rok vydání: | 2020 |
| Témata: | FOS: Computer and information sciences, Computer Science - Machine Learning, 0209 industrial biotechnology, Big data in robotics and automation, Computer Science - Artificial Intelligence, Computational modeling, 02 engineering and technology, Microstrip, Machine Learning (cs.LG), Computer Science - Robotics, Artificial Intelligence (cs.AI), Deep learning in robotics and automation, Motion and path planning, Robot sensing systems, Task analysis, Fuses, Cloud computing, Robotics (cs.RO) |
| Popis: | Humans are capable of learning a new behavior by observing others to perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So, how can robots achieve this? To address the issue, we present a novel framework named FIL. It provides a heterogeneous knowledge fusion mechanism for cloud robotic systems. Then, a knowledge fusion algorithm in FIL is proposed. It enables the cloud to fuse heterogeneous knowledge from local robots and generate guide models for robots with service requests. After that, we introduce a knowledge transfer scheme to facilitate local robots acquiring knowledge from the cloud. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning in accuracy and efficiency. Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a self-driving task for robots (cars). The experimental results demonstrate that the shared model generated by FIL increases imitation learning efficiency of local robots in cloud robotic systems. arXiv admin note: substantial text overlap with arXiv:1909.00895 |
| Druh dokumentu: | Article |
| ISSN: | 2377-3774 |
| DOI: | 10.1109/lra.2020.2976321 |
| DOI: | 10.48550/arxiv.1912.12204 |
| Přístupová URL adresa: | http://arxiv.org/pdf/1912.12204 http://arxiv.org/abs/1912.12204 http://ieeexplore.ieee.org/document/9013081/ https://dblp.uni-trier.de/db/journals/corr/corr1912.html#abs-1912-12204 https://ieeexplore.ieee.org/document/9013081/ https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002274053393025 http://dblp.uni-trier.de/db/journals/ral/ral5.html#LiuWLX20 |
| Rights: | IEEE Copyright arXiv Non-Exclusive Distribution |
| Přístupové číslo: | edsair.doi.dedup.....8ef9e33390e0b51cc8cac7cf4e5f9f36 |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science Buďte první, kdo okomentuje tento záznam!