Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data
Humans are capable of learning a new behavior by observing others perform the skill. Robots can also implement this by imitation learning. Furthermore, if with external guidance, humans will master the new behavior more efficiently. So how can robots implement this? To address the issue, we present Federated Imitation Learning (FIL) in the paper. Firstly, a knowledge fusion algorithm deployed on the cloud for fusing knowledge from local robots is presented. Then, effective transfer learning methods in FIL are introduced. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning. FIL considers information privacy and data heterogeneity when robots share knowledge. It is suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a simplified self-driving task for robots (cars). The experimental results demonstrate that FIL is capable of increasing imitation learning of local robots in cloud robotic systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Imitation LearningTransfer LearningSimilar Papers 제목 키워드 기반
Prompt-enhanced Federated Content Representation Learning for Cross-domain Recommendation
Cross-domain Recommendation (CDR) as one of the effective techniques in alleviating the data sparsity issues has been widely studied in recent years. However, previous works may cause domain privacy leakage since they ne…
Federated LearningPrivacy PreservingRepresentation LearningTransfer LearningFederated Dynamic Spectrum Access
Due to the growing volume of data traffic produced by the surge of Internet of Things (IoT) devices, the demand for radio spectrum resources is approaching their limitation defined by Federal Communications Commission (F…
Federated LearningMulti-agent Reinforcement LearningPrinciples and Components of Federated Learning Architectures
Federated Learning (FL) is a machine learning framework where multiple clients, from mobiles to enterprises, collaboratively construct a model under the orchestration of a central server but still retain the decentralize…
Federated LearningFederated nnU-Net for Privacy-Preserving Medical Image Segmentation
The nnU-Net framework has played a crucial role in medical image segmentation and has become the gold standard in multitudes of applications targeting different diseases, organs, and modalities. However, so far it has be…
Federated LearningImage SegmentationMedical Image SegmentationPrivacy Preserving+2Survey of Privacy Threats and Countermeasures in Federated Learning
Federated learning is widely considered to be as a privacy-aware learning method because no training data is exchanged directly between clients. Nevertheless, there are threats to privacy in federated learning, and priva…
Federated LearningSurveyVertical Federated Learning