Orientation Determination in Object Detection and Tracking for Autonomous Vehicles

This invention describes a system for self-driving cars to understand their surroundings. It uses sensor data, like from LIDAR or cameras, to detect objects around the vehicle. Then, it uses a smart computer program (a machine-learned model) to figure out the object's size and how it's oriented, like whether a car is facing towards or away from the autonomous vehicle, and activates vehicle systems accordingly.

Why it matters: Filed when machine learning for real-time 3D object perception in autonomous vehicles was less mature, advancements in deep learning and sensor fusion since 2017 have significantly improved the accuracy and robustness of determining object dimensions and orientations from sensor data. This makes the core "machine learned model" aspect more practical and effective today.

Status: ExpiredProtection ended and was never renewed
How hard to build: SpecializedMachine learning model, sensor integration, autonomous vehicle software.

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