Know about MIT’s AI knitting system!

by Apparel Resources News-Desk

05-August-2019  |  3 mins read

Image Courtesy:

MIT Computer Science & Artificial Intelligence Laboratory (CSAIL) has come up with new software that can automate the manufacturing of wovenwears.

These software were revealed in two papers released by MIT’s CSAIL.

The first paper described a term called ‘InverseKnit’ system, which gives instructions for machines to make clothes, using the photos of knitted patterns. What’s notable is that no coding is required in the process and is totally automated.

The system’s neural network can interpret 2D directions from images, e.g., when the system is fed with a photo of a glove, the same output of the design is generated.

Notably, the system is capable enough of generating 94 per cent accurate instructions.

The programme currently works only with a small sample size and specific type of acrylic yarn. However, the researchers are working to expand the sample pool and test different materials to employ Inverseknit on a larger scale.

In a statement, Alexandre Kaspar, CSAIL PhD student and lead author of one of the published papers said, “As far as machines and knitting are concerned, this type of system could change accessibility for people looking to be the designers of their own items. We want to let casual users get access to machines without [needing] programming expertise, so that they can reap the benefits of customisation by making use of machine learning for design and manufacturing.”

The second paper details ‘CADKnit’ – a tool that includes 2D images, CAD software and photo-editing techniques for customised knitting. The non-experts can use templates to adjust pattern and shape, like adding vertical stripes to a sock.

“Whether it’s for the everyday user who wants to mimic a friend’s beanie hat, or a subset of the public who might benefit from using this tool in a manufacturing setting, we’re aiming to make the process more accessible for personal customisation,” Kaspar said.

The system, still in its initial stage, has a lot to work upon like how to connect the trunk and sleeves of sweaters.

“The impact of 3D knitting has the potential to be even bigger than that of 3D printing. Right now, design tools are holding the technology back, which is why this research is so important to the future,” suggested, Jim McCann, Assistant Professor in the Carnegie Mellon Robotics Institute – maker of an automated knitting process for 3D meshes.

Share This Article