Tracking Additive Manufacturing Using Machine Vision

Midshipman Researcher(s): 1/C Lenny Davis

Adviser(s): Associate Professor Michael D.M. Kutzer and Assistant Professor John Donnal

Poster #100

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 retrofitted cameras. A feature-based Visual Odometry (VO) algorithm is used to estimate the relative motion of the extruder. Preliminary results in simulation demonstrate feasibility of the proposed VO method and identify factors that may limit performance. Further, alternative methods of VO with potential applications to this project are presented to include machine learning, H.264 motion vector extraction, and template matching.

Full Size Robotics and Controls Engineering #100