Computer vision for real-time extrusion quality monitoring and control in robotic construction

In this paper, a vision-based real-time extrusion quality monitoring system is developed for robotic construction. Initially, the details related to the extrusion system, data acquisition and processing unit, and the proposed algorithm are discussed. The reliability and responsiveness of the developed system is then evaluated on six determined levels of material variation. To demonstrate its application, the vision algorithm is used to develop an innovative closed-loop extrusion system. This system is able to automatically adjust the extrusion rate based on the vision system feedback. Such self-regulating extrusion system would be able to continuously print layers of acceptable dimensions using any printable mixture, without the need for prior calibration and despite some mixture rheology variations. All in all, the high precision and responsiveness of the developed system demonstrates the great potential for computer vision as a real-time quality monitoring and control tool for robotic construction.