Nvidia patents method for self-driving cars to see around corners
Nvidia describes a system that builds a 3D map of a vehicle's surroundings using camera and radar data. It then shoots imaginary lines from the car to different points in the map to figure out which areas are hidden behind obstacles.
In the filing’s own words
In various examples, occlusion detection using occupancy maps for autonomous and/or semi-autonomous systems and applications is described herein. Systems and methods are disclosed that generate an occupancy map—such as a two-dimensional (2D) occupancy grid and/or a 3D occupancy map—of an environment and then use ray tracing with regard to the occupancy map to identify one or more occluded areas of the environment. In some examples, the occupancy map may be generated using 3D occupancy detections that are determined using the fused image data and RADAR data. Additionally, the occluded area(s) of the environment may be identified based at least on projecting rays within the occupancy map to whether points of the occupancy map are occluded. In some examples, the systems and methods may generate a map—such as an occlusion map and/or an occlusion grid-indicating the occluded area(s) of the environment.
What exactly they claim (claim 1)
1. A method comprising: generating, based at least on sensor data obtained using one or more sensors of a machine located within an environment, an occupancy map associated with the environment; determining a first length of a first ray that is projected from a starting point of the occupancy map to a test point of a test area associated with the occupancy map, the starting point of the occupancy map corresponding to a location of the machine within the environment; determining one or more second lengths of one or more second rays that are projected from the starting point of the occupancy map to one or more occupied areas associated with the occupancy map; determining, based at least on the first length of the first ray and the one or more second lengths of the one or more second rays, whether the test area of the occupancy map is occluded; and causing, based at least on whether the test area of the occupancy map is occluded, the machine to perform one or more planning, control, or navigational operations.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- OCCLUSION DETECTION FOR AUTONOMOUS AND SEMI-AUTONOMOUS SYSTEMS AND APPLICATIONS
- Publication number
- US20260278914A1
- Application number
- 19344303
- Filed
- Sep 29, 2025
- Published
- Sep 17, 2026
- Inventors
- 14
- Claims
- 20
Classified under
G06T 15/06 Physics & computingB60W 60/001 Operations & transportG06T 17/05 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.