Warehouse picking just crossed the reliability line
warehouse picking just crossed the reliability line: ai-trained manipulation models now succeed on 90-98% of mixed-sku picks, up from 70-85% for rule-based vision, and amazon’s robot fleet passed 750,000 units with proteus now taking spoken commands from workers. locus array, shipping since april, runs the whole pick-putaway-replenish loop with no human in it.
the payback math changed before the job titles did.
Context
Amazon (Jun 4, 2026) unveiled a next-generation Proteus robot that uses natural language commands, and its robotics page says 750,000 Amazon robots work in its facilities. Locus Robotics launched Locus Array on Apr 13, 2026, a physical AI system for fully autonomous picking.
Brightpick (Jul 2, 2026) describes a two-stage AI picking stack where a lightweight neural network handles the first pick attempt on the robot.
The 750,000 robots, Proteus taking natural language commands and the April Locus Array launch match the sources. Whether Proteus takes spoken commands from workers specifically, the 90 to 98 percent mixed-SKU success versus 70 to 85 percent for rule-based vision, and 'no human in it' for the whole loop were not seen in the sources read, so unsupported here, not refuted. Locus describes Array as fully autonomous picking, not the whole pick, putaway and replenish loop. 'The payback math changed' is the author's.
Related work
- Amazon: how Amazon deploys robots ↗750,000 robots.
- Locus Robotics: Locus Array ↗Product page.
- Amazon: new robots, faster delivery and 25,000 jobs in Europe ↗Jun 4, 2026.
Watch next
- Find the success-rate figures for AI manipulation versus rule-based vision.
Sources
- Amazon: new Proteus robot in European investmentaboutamazon.com
- Locus Robotics: launches Locus Arraylocusrobotics.com
- Brightpick: our multimodal AI picking stackbrightpick.ai
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 1 October 2026 at 21:43 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →