Binocular vision-based guidance for robotic assembly of prefabricated components

Abstract

A robot-assisted installation method, which uses a crane to bear the component's weight and two robots to control the lifted component for precise horizontal positioning, was proposed in a previous study. To enhance the capability to operate large prefabricated components, this paper designs a binocular vision-based technique for real-time localization of the end-tool during the component-pushing process. Each robot is continuously commanded to rotate and translate the end tool based on the measured difference between its current and target poses, until this difference is within an acceptable threshold. The principles and implementation details of the visual method are described in this paper. Even if the robot deforms or slips, accurate measurement and adjustment of the end tool's pose allow effective pushing of the component to the target area. Test results demonstrate that the binocular vision guidance technology is feasible and effective, improving the flexibility and practicability of the installation-assisted robot.