Semantic mapping of environments for autonomous devices

This invention describes a system for robots to find lost items. It works by keeping a map of the robot's environment that tracks where different objects are likely to be, and how those probabilities change over time since the object was last seen. When asked to find something, the system uses this map to figure out the most probable location and then guides the robot there.

Why it matters: Filed before widespread adoption of advanced computer vision and foundation models, which now make robust semantic understanding of environments and objects significantly more feasible and accurate. This directly enhances the system's ability to build and maintain the detailed semantic maps it relies on.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedComplex software logic, robot integration, semantic understanding.

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.

This one

+10