Posted on 12/10/2022 10:30:41 AM PST by libh8er
Amazon built a computer vision algorithm from scratch to identify products without barcodes to help robots ship products to you faster.
Robots may be the future, but robotic arms are apparently no good at using an old and steadfast form of technology: the barcode. Barcodes can be hard to find and might be affixed to oddly shaped products, Amazon said in a press release Friday, something robots can't troubleshoot very well.
As a result, the company says it has a plan to kill the barcode.
Using pictures of items in Amazon warehouses and training a computer model, the e-commerce giant has developed a camera system that can monitor items flowing one-by-one down conveyor belts to make sure they match their images. Eventually, Amazon's AI experts and roboticists want to combine the technology with robots that identify items while picking them up and turning them around.
"Solving this problem, so robots can pick up items and process them without needing to find and scan a barcode, is fundamental," said Nontas Antonakos, an applied science manager in Amazon's computer vision group in Berlin. "It will help us get packages to customers more quickly and accurately."
The system, called multi-modal identification, isn't going to fully replace barcodes soon. It's currently in use in facilities in Barcelona, Spain, and Hamburg, Germany, according to Amazon. Still, the company says it's already speeding up the time it takes to process packages there. The technology will be shared across Amazon's businesses, so it's possible you could one day see a version of it at a Whole Foods or another Amazon-owned chain with in-person stores.
The problem that the system eliminates -- incorrect items coming down the line to be sent to customers -- doesn't happen too often, Amazon says. But even infrequent mistakes add up to significant slowdowns when considering just how many items a single warehouse processes in one day.
Amazon's AI experts had to start by building up a library of images of products, something the company hadn't had a reason to create prior to this project. The images themselves as well as data about the products' dimensions fed the earliest versions of the algorithm, and the cameras continually capture new images of items to train the model with.
The algorithm's accuracy rate was between 75% and 80% when first used, which Amazon considered a promising start. The company says the accuracy is now at 99%. The system faced an initial hiccup when it failed to catch color differences. During a Prime Day promotion, the system couldn't distinguish between two different colors of Echo Dots. The only difference between the packages was a small dot that was either blue or gray. With some retooling, the identification system can now assign confidence scores to its ratings that only flag items its very sure are incorrect.
Amazon's AI team says it will be a challenge to fine-tune the multi-modal identification system to assess products that are being handled by people, which is why the ultimate goal is to have robots handle them instead.
Sure. But that’s OK. Any data on the packaging that’s usable by humans is also usable by robots. And what Amazon is figuring out is that once you’ve taught the robot to use the human data it doesn’t necessarily need the not human data (barcodes).
Wow!
They are adding pictures of every inanimate object to a database in addition to the database they already have called “Amazon Photos” (which already includes 17,562 photos that the wife & I have taken since 1960 of the children, grandchildren, and great-grandchildren)...
Very interesting...
“Just have to have people who can fix them”
Eventually, they’ll be able to fix themselves, and AI will run everything. Humans will not be needed and merely be in the way.
Our area McD franchise went to full kiosk also. For substitutions that can’t be done in the app or at the kiosk I just go to the counter where they still are happy to enter on the register. There pretty much has to be a register for customers who order on the kiosk yet need to pay cash.
With folded hands.😵💫
LOL LOL! Someone should hack his Animatronic and have it say “Where are all the little girls? I wanna sniff their hair!”
AI is not intelligent.
AI walks into a McD’s and asks for ice cream.
McD’s says, “We do not have any ice cream.”
AI starts throwning the loose (”or not”) objects around, while trying to:
a) find ice cream
b) find bar code(s)
c) find the Biden-retrained to code, former auto worker (from closed Jeep Cherokee plant in Rockford, Illinois) who gave AI “the notion” that McD’s has ice cream . . .
and to everybody’s amazement, finds a laptop computer in the bottom of a trash bin.
CNN, Facebook, MSNBC suppress that news, and AI is quickly retrained by the Biden Administration, to “Protect Our Borders” and airlifted to the Ukraine.
Thanks!
Whatever they do, they just won’t think of establishing procedures which present the bar codes on the boxes in a uniform fashion. Nah, that would be too easy, and wouldn’t require millions of dollars worth of electronics.
The large boxes are to make it harder for thieves to steal from your porch.
When the Home Depot guy is going to find you a power tool stored on one of the upper shelves, he finds the location on his smart phone app of the pallet of power tools that was scanned into that location by barcode.
“ When the Home Depot guy is going to find you a power tool stored on one of the upper shelves, he finds the location on his smart phone app of the pallet of power tools that was scanned into that location by barcode.”
*****************************************************************
I love how when I need some hardware item I can check the Lowe’s and Home Depot sites to see the price, if the item is in stock at a particular store and its precise location in the store. Now THAT is customer service.
Home Depot guys find things? Last time I bothered to ask them anything they just always said it was on the other side of the store. Sure stores might use barcode scanning while stocking to record where stuff is. That doesn’t counter anything I’ve said.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.