/Patent Tracker
AmazonPatent applicationRobots & automationInterest 6/10

Amazon patents robot tech to figure out 3D shapes from photos

Amazon describes a system where robots use cameras to take multiple photos of an object and neural networks to guess its 3D shape. The software checks a grid of tiny 3D blocks to see which ones are filled by the object, helping the robot know how to fit it into a box.

Why it mattersThis helps warehouse robots pack boxes more tightly and efficiently without needing expensive 3D scanners.

In the filing’s own words

Systems and methods are disclosed for 3D shape estimation of objects to be placed by a robot. The systems may generate features from images that capture an object from different viewpoints. The systems may use machine learning models (e.g., neural networks) to project from a voxel in a set of voxels to distinct portions within the images. The systems may use the machine learning models to generate second features for the voxel based, at least in part, on first features that correspond to the distinct locations. The systems may use the machine learning models to determine whether the voxel indicates the object based, at least in part, on the second features.

What exactly they claim (claim 1)

1. A method comprising: generating a plurality of images of an object from different perspectives using a plurality of cameras; detecting, using one or more neural networks, a first set of features within the plurality of images, wherein each portion of the plurality of two dimensional (2D) images comprise at least one of the first set of features; mapping, using the one or more neural networks, each voxel in a voxel grid to different portions of the plurality of 2D images based, at least in part, on one or more parameters from the plurality of cameras; detecting, using the one or more neural networks, a second set of features for each voxel based, at least in part, on a subset of the first set of features that are within the different portions of the plurality of 2D images; estimating a shape of the object, using the one or more neural networks, by at least determining whether each voxel of the voxel grid is occupied based, at least in part, on the second set of features; and identifying a space within a container to cause a robot to place the object based, at least in part, on the shape of the object.

Facts

Company
Amazon (Amazon Technologies, Inc.)
Official title
USING MACHINE LEARNING TO ESTIMATE A 3D SHAPE OF OBJECTS
Publication number
US20260284891A1
Application number
19082949
Filed
Mar 18, 2025
Published
Sep 24, 2026
Inventors
2
Claims
20

Classified under

B25J 9/1697 Operations & transportB25J 9/161 Operations & transportG06V 10/82 Physics & computingB25J 19/023 Operations & transport
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Amazon in Robots & automation

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.