Range-view LIDAR-based object detection

This invention describes a way for self-driving cars to "see" objects around them using LIDAR sensors. It works by taking the raw distance measurements from the LIDAR, organizing them into a special data format, and then feeding this into an AI model. The AI identifies objects and estimates their characteristics, like their size or position, which helps the car understand its surroundings; specifically, it uses 360-degree LIDAR data and processes it into channels representing range and height.

Why it matters: Since 2017, machine learning models for 3D data processing have significantly advanced in efficiency and accuracy, making the "machine-learned model" component of this invention much more performant and accessible. Additionally, LIDAR sensor technology has become more mature and cost-effective, lowering the barrier to implementation for autonomous vehicle applications.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedHeavy software system, machine learning, LIDAR 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