Project
SensiCut: Material-Aware Laser Cutting Using Speckle Sensing and Deep Learning
![SensiCut augments standard laser cutters with a speckle sensing add-on that can (a) identify materials often found in workshops, including visually similar ones. (b) SensiCut’s user interface integrates material identification into the laser cutting workflow and also offers suggestions on how to adjust a design’s geometry based on the identified material (e.g., adjusting the size of an earring cut from felt since the kerf for felt is larger than for other materials). (c) Each identified sheet is cut with th](/sites/default/files/styles/primary_image/public/2021-10/SensiCut.png?itok=wz8kpdAX)
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.
Group
HCI Engineering GroupRelated Links
Sponsored By
Contact us
If you would like to contact us about our work, please refer to our members below and reach out to one of the group leads directly.
Last updated Oct 22 '21