Virtual Reality Study of Human Adaptability in Industrial Human-Robot Collaboration

Abstract

Modern industrial automation may benefit from humans and robots collaborating with each other in a shared workspace. Even though collaborative robots are often designed to be physically safe, mental and emotional well-being of humans working with industrial robots, as well as the fluency of collaboration, are rarely considered. This study uses Pimax 5k+ Virtual Reality headset to study human behaviours in a potential collaborative task, where a human and a robot work at the same time on the same workpiece. The human's motion and physiological responses were collected from the VR equipment, wearable Zephyr Biomodule sensor and a subjective questionnaire. The results show that some people can easily adapt to the robot and work fluently even when it speeds up, while others fail to keep up with it and give up any attempts to collaborate. It was shown that participants, who fail to keep up with the robot can often be detected before they give up. This study shows not only the need to adapt the robot's behaviour (especially its speed) to each worker individually, but also the possibility to use human motion and physiological data to predict which worker is going to require additional support to improve the collaboration.