Demonstration Quality-based Teleoperated Learning with Visual and Haptic Data in Bandwidth-Limited Environments

Programming autonomous behavior in machines and robots traditionally requires a specific set of skills and knowledge. On the other hand, human experts can demonstrate the desired task even if they do not know how to program the necessary behavior in a machine or robot. The purpose of Learning from Demonstration (LfD) is to efficiently learn a desired behavior by imitating the teacher. LfD is considered a key technology for applications in manufacturing, elder care, and the service industry. These applications require efficient, intuitive ways to teach robots the motions they need to perform. In recent times there has been a renewed interest in robot teleoperation, since it allows workers to accomplish their tasks remotely from home office or anywhere in the world. Unfortunately, network conditions play a significant role in the stability of teleoperated systems, and factors such as delays or reduced bandwidth can be decisive in the successful completion of even the simplest tasks. In this work, we present a method to teach insertion skills from teleoperated demonstrations that combines visual and haptic information. Both streams of data are decoupled, which allows for easier provision of Quality of Service (QoS) under adverse network conditions. Additionally, a user study of the impact of bandwidth limitation on the visual part of the remote teaching is presented, where the results show that a reduction in bandwidth leads to increased demonstration time and lower accuracy. A weighting strategy to limit the harm of the network conditions is successfully applied, reducing the median error in the demonstrated insertion pose by approximately 20%.