Systems and methods for predicting the trajectory of a road agent external to a vehicle

This invention describes a system for self-driving vehicles to predict where other road users, like cars or pedestrians, are going. It uses at least two different methods to guess their paths and then calculates how sure it is about each guess, using an advanced AI system. The vehicle then uses these predictions and confidence levels to decide how to drive safely.

Why it matters: Since 2019, deep learning models have become significantly more efficient and accurate, especially for real-time prediction tasks in autonomous systems. Advances in automotive-grade AI hardware and data collection for training complex neural networks could make this multi-predictor, confidence-aware approach more robust and deployable now.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedDeep neural networks, software logic, 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