Graph neural networks for parsing roads

This invention describes a system that uses artificial intelligence, specifically a type called a graph neural network, to analyze detailed elevation and terrain information about roads. It figures out the best paths a vehicle can drive on those roads. This information is then saved into a map, which can be sent to self-driving or assisted-driving cars to help them navigate.

Why it matters: The underlying graph neural network technology was established in 2023. However, the increased availability of diverse topographical datasets and more efficient AI training infrastructure since then could simplify development and improve model performance.

Status: Under examinationA pending application. It has not been granted, and it has not been abandoned.
How hard to build: SpecializedGraph neural networks, data processing, vehicle integration

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