Nvidia patents method to map 3D intersections for self-driving cars
Nvidia describes a system that uses a neural network to turn flat 2D camera images into a 3D map of road intersections. The software is trained to ensure the 3D map follows real-world geometry, helping self-driving vehicles accurately locate where roads meet.
In the filing’s own words
In various examples, a three-dimensional (3D) intersection structure may be predicted using a deep neural network (DNN) based on processing two-dimensional (2D) input data. To train the DNN to accurately predict 3D intersection structures from 2D inputs, the DNN may be trained using a first loss function that compares 3D outputs of the DNN—after conversion to 2D space—to 2D ground truth data and a second loss function that analyzes the 3D predictions of the DNN in view of one or more geometric constraints—e.g., geometric knowledge of intersections may be used to penalize predictions of the DNN that do not align with known intersection and/or road structure geometries. As such, live perception of an autonomous or semi-autonomous vehicle may be used by the DNN to detect 3D locations of intersection structures from 2D inputs.
What exactly they claim (claim 1)
1. A method comprising: applying, to one or more neural networks, image data representative of one or more two-dimensional (2D) images depicting one or more features of an intersection; generating, based at least on the one or more neural networks processing the image data, output data indicating one or more three-dimensional (3D) locations corresponding to the one or more features of the intersection; and causing, based at least on the one or more 3D locations, a machine to perform one or more planning, navigation, or control operations.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- THREE-DIMENSIONAL INTERSECTION STRUCTURE PREDICTION FOR AUTONOMOUS DRIVING APPLICATIONS
- Publication number
- US20260285315A1
- Application number
- 19072741
- Filed
- Mar 6, 2025
- Published
- Sep 24, 2026
- Inventors
- 5
- Claims
- 20
Classified under
B60W 30/18154 Operations & transportG06N 3/04 Physics & computingG06N 3/08 Physics & computingG06T 7/33 Physics & computingG06V 10/764 Physics & computingG06V 10/82 Physics & computingMore from Nvidia in Cars & transport
- Nvidia patents robotaxi system with AI dispatcher and virtual rails Sep 15, 2026
- Nvidia patents car drowsiness check that uses your body clock Oct 13, 2026
- Nvidia patents 3D camera system to measure passengers in vehicles Oct 13, 2026
- Nvidia patents cruise control that predicts driver's next move Oct 20, 2026
- Nvidia patents dual-brain system for self-driving cars Sep 17, 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.