Nvidia patents robot navigation using simple flat maps
Nvidia describes a method for autonomous machines to find their location using basic two-dimensional maps instead of expensive, detailed 3D models. The system uses cameras to see the environment and projects what it sees onto a flat ground reference to match against the simple map.
In the filing’s own words
Autonomous machines need to know where they are to navigate safely. Traditional systems rely on expensive, detailed high-definition maps that require constant updates. This disclosure describes a more practical approach using simple two-dimensional maps that show where objects are located but that do not include height or elevation data. In particular, the ground plane is used as a reference to register camera images with the simple map. By projecting what the camera sees onto this common reference plane, the machine may match observed features against known map locations. By matching what the camera sees with what the map shows, the machine may figure out its location and navigate accordingly.
What exactly they claim (claim 1)
1. A machine comprising: one or more systems-on-a-chip (SoCs) individually comprising one or more central processing units (CPUs), one or more graphics processing units (GPUs), and one or more hardware accelerators; and one or more sensors having fields of view or sensory fields external to the machine, wherein the machine performs one or more control operations based at least on localizing the machine to a two-dimensional (2D) map of an environment, the localizing being based at least on an analysis between the 2D map and one or more estimated locations in 2D image space corresponding to one or more images of the environment, the one or more estimated locations representing one or more potential intersection points of a portion of an object with one or more ground plane locations.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- MACHINE NAVIGATION
- Publication number
- US20260328587A1
- Application number
- 19654101
- Filed
- Apr 21, 2026
- Published
- Oct 22, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G01C 21/3848 Physics & computingG01C 21/3453 Physics & computingG06T 7/536 Physics & computingG06T 7/75 Physics & computingG06V 20/56 Physics & computingMore from Nvidia in Robots & automation
- Nvidia patents robot control using language models to predict 3D positions Sep 10, 2026
- Nvidia patents method to teach humanoid robots to use hands via simulation Oct 15, 2026
- Nvidia patents 3D scene mapping that lets robots understand objects by name Oct 15, 2026
- Nvidia patents robot system that learns tasks from visual data Sep 29, 2026
- Nvidia patents method for robots to estimate object positions from images Oct 13, 2026
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.
