Deep neural network based smart material sensing platform that can identify materials, and protect users from hazardous stuff.
Laser cutters have rapidly become a relatively simple and powerful tool equipped with smart controllers and machinery that can chop metals, woods, papers, and plastics. But users often face difficulties distinguishing between stockpiles of visually similar materials, where the wrong material selection can emit odors and spew harmful chemicals.
To address this issue, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) developed “SensiCut,” a smart material-sensing platform for laser cutters. Conventional camera-based approaches can easily misidentify materials. The newly developed method uses deep learning and an optical method called “speckle sensing,” a technique that uses a laser to sense a surface’s microstructure, enabled by just one image-sensing add-on.
SensiCut could potentially protect users from hazardous waste, provide material-specific knowledge, suggest subtle cutting adjustments for better results, and even engrave various items like garments or phone cases that consist of multiple materials.
“By augmenting standard laser cutters with lensless image sensors, we can easily identify visually similar materials commonly found in workshops and reduce overall waste,” says Mustafa Doga Dogan, Ph.D. candidate at MIT CSAIL. “We do this by leveraging a material’s micron-level surface structure, which is a unique characteristic even when visually similar to another type. Without that, you’d likely have to make an educated guess on the correct material name from a large database.”
The team trained SensiCut’s deep neural network on images of 30 different material types of over 38,000 images, where it could then differentiate between materials like acrylic, foamboard, and styrene, and even provide further guidance on power and speed settings.
Researchers say that SensiCut’s sensing technology could eventually be integrated into other fabrication tools like 3D printers.
