Nvidia patents safety check for self-driving path choices
Nvidia describes a system that combines data from multiple sensors to determine where a vehicle is and which lane it should follow. Before the car acts on this information, the system compares the results against two independent, trusted data sources to ensure they agree.
In the filing’s own words
An architecture can generate lane graphs or path determinations, for devices such as robots or autonomous vehicles, using multiple sources of data while satisfying applicable requirements and regulations for operation. A system can fuse together data from multiple sources useful to determine localization. To ensure safety compliance, this fused data is compared against data from systems where safety is trusted and, as long as at least two comparators agree with the fused localization data, the fused localization data can be used and verified to be safety regulation compliant. This system can also fuse together available information useful for lane perception. This fused data is compared against data from systems where the safety is trusted, and as long as at least two comparators for these safety-compliant systems agree with the fused lane graph data, then the fused lane graph data can be provided for navigation and verified to be regulation compliant.
What exactly they claim (claim 1)
1. A method, comprising generating, using at least two sources of localization data, a fused localization determination, the at least two sources of localization data fused based in part on weightings determined using relative confidence values associated with respective sources; comparing the fused localization determination against at least two trusted and independent sources of localization determinations to verify the fused localization determination; generating a navigation path, based at least on verification of the fused localization determination and using at least two sources of environment perception; comparing the navigation path against at least two trusted and independent sources of navigation path data and the fused localization determination to verify the navigation path; determining that the navigation path is verified upon receiving two or more votes from at least two comparators, each comparator evaluating the navigation path against data from the at least two trusted and independent sources of navigation path data respectively; and providing, based at least on the navigation path being verified, the navigation path to a control system to navigate an object within the environment.
Facts
- Company
- Nvidia (Nvidia Corporation)
- Official title
- Safe path selection
- Patent number
- US12728883B2
- Application number
- 17483019
- Filed
- Sep 23, 2021
- Granted
- Sep 8, 2026
- Inventors
- 4
- Claims
- 20
Classified under
B60W 60/001 Operations & transportG06F 18/25 Physics & computingB60W 2420/403 Operations & transportB60W 2420/408 Operations & transportB60W 2552/53 Operations & transportMore 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.