Nvidia patents neural network to help self-driving cars see 3D surroundings
Nvidia describes a system that uses deep neural networks to analyze sensor data from a 3D environment. It processes different views, such as a standard perspective and a top-down map, to identify objects and their shapes. This information creates 3D bounding boxes to help an autonomous vehicle plan its path safely.
In the filing’s own words
A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional ( 3 D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3 D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3 D bounding boxes and class labels for detected objects in the 3 D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.
What exactly they claim (claim 1)
1. An autonomous or semi-autonomous 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 autonomous or semi-autonomous machine, wherein the one or more SoCs are to: generate a representation of one or more detected elements in an environment based at least on a neural network processing a representation of classification data transformed into a bird's eye view; and cause performance of one or more operations of the autonomous or semi-autonomous machine based at least on the representation of the one or more detected elements.
Facts
- Company
- Nvidia (NVIDIA CORPORATION)
- Official title
- MACHINE PERCEPTION
- Publication number
- US20260260498A1
- Application number
- 19655093
- Filed
- Apr 22, 2026
- Published
- Sep 3, 2026
- Inventors
- 10
- Claims
- 21
Classified under
G06V 20/584 Physics & computingB60W 60/0011 Operations & transportB60W 60/0016 Operations & transportB60W 60/0027 Operations & transportG01S 7/4802 Physics & computingG01S 17/89 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 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.