Researchers at MIT developed a smart laser cutter system called SensiCut that can differentiate between 30 materials commonly found in makerspaces and workshops.

Laser cutters can quickly and precisely cut metals, woods, papers, and plastics to create all kind of products. However, with the naked eye, it is not always easy to differentiate between visually similar materials, with the danger of creating messes, bad odours or even harmful chemicals if the wrong material is laser cut.

The SensiCut system has a smart material-sensing platform for laser cutters. Rather than using cameras that can easily misidentify materials, the system uses deep learning and an optical method called speckle sensing. This method uses a laser to sense a surface’s microstructure, enabled by just one image-sensing add-on.

Aside from potentially protecting users from hazardous waste, the system also provides material-specific knowledge, suggests subtle cutting adjustments for better results and even engrave various items that consist of multiple materials.

The speckle imaging technique was used inside a laser cutter, with low-cost, off-the shelf-components, like a Raspberry Pi Zero microprocessor board. To make it compact, the team designed and 3D printed a lightweight mechanical housing.

Photo: MIT CSAIL