Human-in-the-loop Learning and Control for Robot Teleoperation

Chapter Six: Human–robot interaction in teleoperation systems

Abstract

In this chapter, we have introduced a prediction method for estimating human motion based on an autoregressive model. In this method, human body movement can be predicted by updating the parameters of the autoregressive model, and then the robot's trajectory can be adjusted automatically. Furthermore, techniques such as haptic feedback are used. We also introduce a linear guidance VF based on sEMG signals. The aim is to guide the robot through a trajectory more accurately by providing force feedback to the operator. Experiments including several different tasks were carried out using a Baxter robot. Good performance with a small position error and a low contact force was obtained, ...