Ask HN: How Does Amazon GO AI Work?

2 points by iluvdata ↗ HN
OPening this as a discussion thread to understand how Amazon GO AI works.

2 comments

[ 5.8 ms ] story [ 22.1 ms ] thread
There isn't much published, but my hypothesis is:

Very accurate weight sensors on each shelf and a knowledge of which products are on each shelf should provide pretty accurate detection of which products a customer has picked up.

Cameras above shelves recognising simple things like t-shirt color detect who picked up that product.

That's probably good enough for a v1 prototype.

I guess now they combine that with per customer profiles (downrank products I'd never normally buy), and special weighing hardware where products are near identical (eg. Spice racks could have a different weight sensor on each column).

Combine all that with a human review system behind the scenes for resolving ambiguities.

Then remember that most people won't care too much if, out of a large grocery shop of 100 items, they were charged 50c for regular carrots when they picked up organic carrots for 65c.

Finally a simple dispute and refund system for cases which aren't caught by any of the above should keep customers happy.

Remember: Retail theft and shrinkage is about 1%. If you can make your system better than 1% while keeping customers happy, Amazon Go is good to go.

It'skept behind the doors but would be interesting to understand from someone who has visited the store.