Trajectory prediction of third-party objects using temporal logic and tree …

This invention describes a system for self-driving cars to predict what other vehicles on the road might do. It uses sensor data to identify objects around it and then generates possible future paths for other cars. To figure out which paths are most likely, it uses a sophisticated search method combined with logical rules to validate or reject these potential movements.

Why it matters: The increasing demand for explainable and formally verifiable AI in safety-critical systems like autonomous vehicles makes logic-based prediction methods, like those using LTL, more relevant today than in 2017, when purely data-driven approaches were gaining primary focus.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedComplex software algorithms, sensor 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