Perception uncertainty

This invention describes a computer system that processes sensor data to understand its surroundings, like identifying objects or their depth. Crucially, it also figures out how uncertain its own perception is by learning from past experiences. Specifically, it focuses on generating probabilistic estimates for things like depth and object detection, and then calculating how reliable those estimates are.

Why it matters: Filed before the rapid advancements in deep learning for computer vision and uncertainty quantification. Modern AI models and increased computational power make learning robust uncertainty estimates for perception tasks significantly more feasible and accurate than in 2020.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedMachine learning algorithms, data processing

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