Tracking Additive Manufacturing Using Machine Vision

This paper presents a method of vision-based trajectory reconstruction for additive manufacturing (AM). With the rise in popularity of AM comes severe cyber-physical risks. Towards addressing this issue, this paper presents a method of reconstructing printhead motion with a minimally invasive camera module retrofit. A feature based Visual Odometry (VO) algorithm is used to estimate the relative motion of the extruder, leveraging expanded methods from the MATLAB Computer Vision Toolbox. Preliminary results in simulation demonstrate feasibility of the proposed VO method and identify factors that may limit performance. Further, a hardware implementation is demonstrated on a retrofitted LulzBot TAZ6, as well as novel methods to improve feature-based VO performance.