Face Tracking Strategy of 7-DOF Manipulator Using Optimization Algorithm Based on Velocity Analysis

Patients' facial expressions can reflect their condition, but expressions cannot be captured like ECG or EEG monitor. Long-term monitoring will increase the workload of nurses. To tackle this issue, we develop a face tracking strategy using a 7-DOF robot manipulator with a camera mounted on the end-effector. First, we analyze the relationship between the manipulator's workspace and optimal tracking pose and design an optimization function to initialize the head position. By comparing the speed of the head and manipulator, knowledge of the maximum tracking limit of the head and the manipulator in the tracking process is given. Moreover, a configuration-based optimization algorithm is proposed to minimize the error with theoretical optimal pose by converting radian to arc length. We calculate the optimal configuration of the camera with the feedback of the head configuration while minimizing the difference between theoretical optimal pose. Simulation experimental results verified that the proposed face tracking strategy outperforms the visual servoing control strategy only based on the pseudo-inverse of the Jacobian matrix.