ABSTRACT
Due to the COVID-19 epidemic, there has been a high demand for non-contact diagnostic equipment that can reduce exposure and cross-infection. A non-contact medical detection robot is a type of diagnostic equipment and medical service robot with a wide application prospect. However, few non-contact medical detection robots have been designed to collect patients' physiological parameters when they are in inconvenient situations, such as bedridden, during clinical usage. A six-degree-of-freedom (six-DOF) face tracking method based on a six-DOF robot is proposed in this paper. In the proposed system, a face detector equipped with a camera attached to the robot's wrist is used to obtain the real-time face depth and attitude information. The optimal target attitude of the camera is calculated according to the constraints in the base coordinate system. A closed-loop controller is designed to control the robot to reach the target position and posture smoothly. The experiment with a six-DOF robot has verified that the proposed system can achieve the real-time tracking of human faces by a camera. The proposed method can also be used in many other scenarios where six-DOF face tracking is required by robots.