An MIT team develops 3D-printed tags to classify and store data on physical objects.
If you download music online, you can get accompanying information embedded into the digital file that might tell you the name of the song, its genre, the featured artists on a given track, the composer, and the producer. Similarly, if you download a digital photo, you can obtain information that may include the time, date, and location at which the picture was taken. That led Mustafa Doga Dogan to wonder whether engineers could do something similar for physical objects. “That way,” he mused, “we could inform ourselves faster and more reliably while walking around in a store or museum or library.”
The idea, at first, was a bit abstract for Dogan, a 4th-year PhD student in the MIT Department of Electrical Engineering and Computer Science. But his thinking solidified in the latter part of 2020 when he heard about a new smartphone model with a camera that utilizes the infrared (IR) range of the electromagnetic spectrum that the naked eye can’t perceive. IR light, moreover, has a unique ability to see through certain materials that are opaque to visible light. It occurred to Dogan that this feature, in particular, could be useful.
The concept he has since come up with — while working with colleagues at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) and a research scientist at Facebook — is called InfraredTags. In place of the standard barcodes affixed to products, which may be removed or detached or become otherwise unreadable over time, these tags are unobtrusive (due to the fact that they are invisible) and far more durable, given that they’re embedded within the interior of objects fabricated on standard 3D printers.
Final yr, Dogan spent a few months looking for an appropriate number of plastic that IR gentle can move by way of. It must come within the type of a filament spool particularly designed for 3D printers. After an in depth search, he got here throughout custom-made plastic filaments made by a small German firm that appeared promising. He then used a spectrophotometer at an MIT supplies science lab to research a pattern, the place he found that it was opaque to seen gentle however clear or translucent to IR gentle — simply the properties he was in search of.
The subsequent step was to experiment with strategies for making tags on a printer. One choice was to provide the code by carving out tiny air gaps — proxies for zeroes and ones — in a layer of plastic. An alternative choice, assuming an obtainable printer may deal with it, could be to make use of two sorts of plastic, one which transmits IR gentle and the opposite — upon which the code is inscribed — that’s opaque. The twin materials strategy is preferable, when potential, as a result of it could possibly present a clearer distinction and thus may very well be extra simply learn with an IR digital camera.
The tags themselves may encompass acquainted barcodes, which current data in a linear, one-dimensional format. Two-dimensional choices — corresponding to sq. QR codes (generally used, as an illustration, on return labels) and so-called ArUco (fiducial) markers — can doubtlessly pack extra data into the identical space. The MIT workforce has developed a software program “consumer interface” that specifies precisely what the tag ought to appear to be and the place it ought to seem inside a specific object. A number of tags may very well be positioned all through the identical object, in actual fact, making it simple to entry data within the occasion that views from sure angles are obstructed.
“InfraredTags is a extremely intelligent, helpful, and accessible strategy to embedding data into objects,” feedback Fraser Anderson, a senior principal analysis scientist on the Autodesk Know-how Heart in Toronto, Ontario. “I can simply think about a future the place you possibly can level a normal digital camera at any object and it will provide you with details about that object — the place it was manufactured, the supplies used, or restore directions — and also you wouldn’t even need to seek for a barcode.”
Dogan and his collaborators have created a number of prototypes alongside these traces, together with mugs with bar codes engraved contained in the container partitions, beneath a 1-millimeter plastic shell, which could be learn by IR cameras. They’ve additionally fabricated a Wi-Fi router prototype with invisible tags that reveal the community identify or password, relying on the attitude it’s considered from. They’ve made an inexpensive online game controller, formed like a wheel, that’s fully passive, with no digital parts in any respect. It simply has a barcode (ArUco marker) inside. A participant merely turns the wheel, clockwise or counterclockwise, and a cheap ($20) IR digital camera can then decide its orientation in house.
Sooner or later, if tags like these turn out to be widespread, individuals may use their cellphones to show lights on and off, management the quantity of a speaker, or regulate the temperature on a thermostat. Dogan and his colleagues are trying into the potential for including IR cameras to augmented actuality headsets. He imagines strolling round a grocery store, sometime, sporting such headsets and immediately getting details about the merchandise round him — what number of energy are in a person serving, and what are some recipes for getting ready it?
Kaan Aksit, an affiliate professor of laptop science at College School London, sees nice potential for this expertise. “The labeling and tagging trade is an unlimited a part of our day-to-day lives,” Aksit says. “The whole lot we purchase from grocery shops to items to get replaced in our gadgets (e.g., batteries, circuits, computer systems, automobile components) should be recognized and tracked appropriately. Doga’s work addresses these points by offering an invisible tagging system that’s principally protected towards the sands of time.” And as futuristic notions just like the metaverse turn out to be a part of our actuality, Aksit provides, “Doga’s tagging and labeling mechanism may also help us carry a digital copy of things with us as we discover three-dimensional digital environments.”
The paper, “InfraredTags: Embedding Invisible AR Markers and Barcodes into Objects Utilizing Low-Price Infrared-Primarily based 3D Printing and Imaging Instruments,” (DOI: 10.1145/3491102.3501951) is being offered on the ACM CHI Convention on Human Components in Computing Techniques, in New Orleans this spring, and will probably be printed within the convention proceedings.
Dogan’s coauthors on this paper are Ahmad Taka, Michael Lu, Yunyi Zhu, Akshat Kumar, and Stefanie Mueller of MIT CSAIL; and Aakar Gupta of Fb Actuality Labs in Redmond, Washington.
This work was supported by an Alfred P. Sloan Basis Analysis Fellowship. The Dynamsoft Corp. supplied a free software program license that facilitated this analysis.