Robotic control using deep learning

This describes a system that helps robots perform complex tasks even if they haven't been specifically taught how to do them. It works by using one AI system to figure out what's happening in the robot's environment, like understanding its surroundings, and then a separate AI system uses that information to decide what the robot should do next. The claims focus on this specific two-AI-system approach.

Why it matters: Filed before large AI models could generalize across diverse tasks. These models could now significantly enhance the ability of the two neural networks to infer complex logical states and determine actions for untrained scenarios.

Status: Not in forceListed as no longer active.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