/Patent Tracker
NvidiaPatent applicationCars & transportInterest 7/10

Nvidia patents dual-brain system for self-driving cars

Nvidia describes a control system that runs two different decision-making processes simultaneously on the same computer chip. One path uses traditional rule-based logic, while the other uses a neural network to predict actions, allowing the system to choose the best result for driving or moving a robot.

Why it mattersThis approach could help self-driving vehicles handle unexpected situations by blending proven safety rules with flexible AI learning.

In the filing’s own words

A hybrid control stack may be implemented with classical and E2E signal paths with independent feature extractors or backbone networks. A classical planner in the classical signal path may be used to generate a first candidate trajectory or control action, a neural planner in the E2E signal path may be used to generate a second, and any suitable technique may be used to determine which to use (e.g., based on an applicable navigational domain). To free up resources to run both signal paths on the same SoC(s), either or both networks may be simplified or downscaled using any suitable technique. The present techniques may be used to transition from a decomposed control stack to an E2E control stack, adapt an existing decomposed control stack into a hybrid control stack, train the hybrid control stack, and/or control navigation of autonomous vehicles, semi-autonomous vehicles, robots, and/or other object or machine types.

What exactly they claim (claim 1)

1. One or more processors comprising processing circuitry to: generate, based at least on applying a first representation of sensor data obtained using one or more sensors of an ego-machine to a first signal path comprising a first encoder network and a heuristic- or rules-based planner, a first candidate action; generate, based at least on applying a second representation of the sensor data to a second signal path comprising a second encoder network and a neural planner, a second candidate action; and control one or more operations of the ego-machine based on at least one of the first candidate action or the second candidate action.

Facts

Company
Nvidia (NVIDIA CORPORATION)
Official title
HYBRID DRIVE STACK WITH INDEPENDENT ENCODERS FOR AUTONOMOUS AND SEMI-AUTONOMOUS MACHINES AND APPLICATIONS
Publication number
US20260274298A1
Application number
19078554
Filed
Mar 13, 2025
Published
Sep 17, 2026
Inventors
8
Claims
20

Classified under

B60W 60/0011 Operations & transportG06N 3/0455 Physics & computingG06V 10/82 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Nvidia in Cars & transport

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.