SensiCut: Material-Aware Laser Cutting Using Speckle Sensing and Deep Learning

Video

DOI

Laser cutter users face difficulties distinguishing between visually similar materials. This can lead to problems, such as using the wrong power/speed settings or accidentally cutting hazardous materials. To support users, we present SensiCut, an integrated material sensing platform for laser cutters.SensiCut enables material awareness beyond what users are able to see and reliably differentiates among similar-looking types. It achieves this by detecting materials' surface structures using speckle sensing and deep learning. SensiCut consists of a compact hardware add-on for laser cutters and a user interface that integrates material sensing into the laser cutting workflow. In addition to improving the traditional workflow and its safety, SensiCut enables new applications, such as automatically partitioning designs when engraving on multi-material objects or adjusting their geometry based on the kerf of the identified material. We evaluate SensiCut's accuracy for different types of materials under different sheet orientations and illumination conditions.