Search
Menu

Laser Cutter Differentiates Among Materials

Facebook X LinkedIn Email
A laser cutting system developed by researchers at MIT can detect and differentiate materials, to make informed cutting decisions. The system, called SensiCut, could increase the capabilities of laser cutting systems in applications that involve objects composed of multiple materials.

Conventional approaches to material identification in this context often involve cameras, which can make mistakes with visually similar materials, or sticker tags such as QR codes, which could be cut or fall off, or even misidentify a material. Incorrect identification can result in damaged products and potentially the release of harmful chemicals.
The SensiCut system is able to distinguish material types using a laser speckle imaging technique. Courtesy of Mustafa Doga Dogan, MIT.
The SensiCut system is able to distinguish material types using a laser speckle imaging technique. Courtesy of Mustafa Doga Dogan, MIT.

The device developed by researchers in the Computer Science and Artificial Intelligence Laboratory (CSAIL) uses deep learning and an optical method called speckle sensing, which identifies materials using a laser to sense a surface’s microstructure, enabled by just one image-sensing add-on.

“By augmenting standard laser cutters with lensless image sensors, we can easily identify visually similar materials commonly found in workshops and reduce overall waste,” said Mustafa Doga Dogan, a 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.”
A phone case comprised of two different materials engraved using the SensiCut system. Courtesy of Mustafa Doga Dogan, MIT.
A phone case composed of two different materials engraved using the SensiCut system. Courtesy of Mustafa Doga Dogan, MIT.


The researchers trained the device’s deep neural network on 38,000 images of 30 different materials. The machine was then able to differentiate between things such as acrylic, foamboard, and styrene, and provide further guidance on power and speed settings.

To test the device, the researchers decided to build a face shield, which would require SensiCut to distinguish transparent materials in a workshop. The user first selects a design file in the interface, and then uses the pinpoint function to get the laser moving to identify the material type at a point on the sheet. The laser then interacts with the tiny features of the surface, and the rays are reflected off it, arriving at the pixels of the image sensor and producing a unique 2D image. The system could then alert the user that their sheet is polycarbonate, meaning that it could produce potentially highly toxic flames if cut by a laser.

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

Apart from laser cutters, the team envisions deploying SensiCut’s sensing technology for integration into other fabrication tools, such as 3D printers. To capture additional nuance, the team plans to incorporate thickness detection, an important variable in material makeup.

The research will be presented at the ACM Symposium on User Interface Software and Technology (UIST).

Published: August 2021
Glossary
machine vision
Machine vision, also known as computer vision or computer sight, refers to the technology that enables machines, typically computers, to interpret and understand visual information from the world, much like the human visual system. It involves the development and application of algorithms and systems that allow machines to acquire, process, analyze, and make decisions based on visual data. Key aspects of machine vision include: Image acquisition: Machine vision systems use various...
neural network
A computing paradigm that attempts to process information in a manner similar to that of the brain; it differs from artificial intelligence in that it relies not on pre-programming but on the acquisition and evolution of interconnections between nodes. These computational models have shown extensive usage in applications that involve pattern recognition as well as machine learning as the interconnections between nodes continue to compute updated values from previous inputs.
surface
1. In optics, one of the exterior faces of an optical element. 2. The process of grinding or generating the face of an optical element.
Research & TechnologyLasersImagingSensors & DetectorsMaterialsmachine visionlaser cuttingneural networkfabricationindustrialMITCSAILsurfaceTech Pulse

We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.