A vision-based monitoring approach for real-time control of laser origami cybermanufacturing processes

Laser origami processes that use sheet precursors offer considerable advantages over traditional powder based additive manufacturing for fast realization of functional complex shapes for custom manufacturing. An in-process monitoring tool that captures shape transformation in real time is necessary to assure cost and quality parity with mass production. Recent advances in optimal image correlations with Aruco markers and sparse regression formulations can lead to fast and accurate real-time process monitoring and quality assurance. We present a spatial regression approach to combine information from multiple low-resolution cameras for real-time monitoring of a laser-origami processes. Experimental investigations on an origami testbed at Texas A&M University suggest that the present approach can provide fast (delays of around 100 ms) and accurate (error rates NRSME <5%) estimates of geometric features such as the angle of a fold in the laser based origami shape forming process.