Real-time motion tracking for human and robot in a collaborative assembly task

The human-robot collaboration is combining the extended capabilities of human and robot to create a more inclusive and human-centered production system in the future. However, human safety is the primary concern for manufacturing industries. Therefore, safe human-robot collaboration may require real-time motion tracking and prediction of a robot, a human and an object inside the configured working space. In this work, our task is to investigate a concept for unified real-time motion tracking for human-robot collaboration. A low cost and game-based motion tracking systems are integrated into digital human model using Unity3D environment. In this context, we applied a biomechanical model to realize the joint position and orientation of the digital human model. A unified robot description format describes kinematics of the robot. It is the joint controller that prescribes joint sensor motions. Finally, an assembly operation involving snap joining is applied to analyze the performance of the system in real-time process. The analysis considered the distribution of joint variables in spatial-space and time-space. The results suggest that low cost motion capturing methods are useful to derive a concept, particularly in lab environment. Therefore, by predicting non-naturalistic human movement towards robot joints, human safety can be improved. However, system performance needs further investigation regarding jitter, latency, and occlusion.