Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data
This addresses the challenge of collaborative learning for robots in cloud systems with privacy and data heterogeneity, but it appears incremental as it builds on existing imitation and federated learning concepts.
The paper tackles the problem of enabling robots to learn more efficiently from each other while preserving privacy and handling heterogeneous sensor data, by proposing Federated Imitation Learning (FIL), which increases imitation learning performance in cloud robotic systems as demonstrated in a self-driving task.
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.