AutoInvent
Turn abandoned patents
into your own filing
Get Started
Patent drawing for Object localization and recognition using fractional occlusion frustum
US 11,467,599 B2
Control systems US 11,467,599 B2 Not in force

Object localization and recognition using fractional occlusion frustum

This invention describes a mobile cleaning robot that can find and identify objects in its environment, even if they are partly hidden. As the robot moves and takes pictures of an object from different angles, it calculates how likely it is that the object is visible at various points on its internal map. By combining these probabilities, the robot can pinpoint the object's location and recognize what it is, even when obstacles block parts of its view.

Why it matters: Since 2020, significant advancements in deep learning and 3D scene reconstruction have made robust object recognition and localization under partial occlusion more feasible. Modern AI models are better at inferring object presence and location from incomplete visual data, which was a major challenge when this was filed.

Status
Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build
SpecializedRobot hardware, advanced computer vision software

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.