Constraint augmentation in a navigational system

This invention describes a system for self-driving vehicles that uses cameras to understand its surroundings and an artificial intelligence system (reinforcement learning) to decide how to move. Crucially, before acting, the system checks the AI's decision against predefined safety rules, such as maintaining specific buffer zones around objects, and modifies the action if needed to ensure safety. The claims narrow this to a system that specifically augments or adjusts these buffer zone constraints based on identified factors.

Why it matters: Filed when practical, safety-critical reinforcement learning for autonomous vehicles was still in early stages, the integration of robust AI with explicit safety constraints and advanced computer vision has matured significantly, making this hybrid approach more feasible and reliable today.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedReinforcement learning, image processing, control 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