Pose determination of a robot manipulator based on monocular vision

Abstract

This paper presents an approach to determine the pose of a robot manipulator by using a single fixed camera. Conventionally, the pose determination is usually achieved by using the encoders to sense the joint angles, and then the pose of the end effector is obtained by using the direct kinematics of the manipulator. However, when the encoders or the manipulators are malfunctioning, the pose may not be accurately determined. This paper presents an approach based on machine vision, where a single camera is fixed away from the base of the manipulator. Besides, based on the kinematics of the manipulator and a calibrated camera, the pose of the manipulator can be determined. Furthermore, a graphical user interface is developed, which is convenient for users to operate the entire system. Two examples are demonstrated, and the estimated results are compared with those from the encoders. The proposed approach does not compete with the encoders. Instead, the approach can be treated as a backup method, which can provide a reference solution.