/Patent Tracker
NvidiaGranted patentCars & transportInterest 6/10

Nvidia patents self-driving tech that swaps sensors based on driving conditions

Nvidia describes a system for autonomous vehicles that automatically switches between different location-finding methods depending on how the car is driving. The system looks at factors like speed and location to pick the best mix of cameras and sensors, changing its approach when the driving situation changes.

Why it mattersThis could make self-driving cars more accurate and efficient by using less computer power when heavy processing isn't needed.

In the filing’s own words

A vehicle, for example, an autonomous vehicle performs localization to determine the current location of the vehicle using different localization techniques as the vehicle drives. The localization technique used by the autonomous vehicle is selected from a localization variant index that stores mapping from a driving context to localization variant, each localization variant identifying a localization technique. The driving context may comprise information including: a geographical region in which the autonomous vehicle is driving, a speed at which the autonomous vehicle is driving, an angular velocity of the autonomous vehicle, or other information. Using an optimal localization technique in each driving context improves the accuracy of localization as well as computing efficiency of the process of localization.

What exactly they claim (claim 1)

1. A method comprising: determining a first operating context of a machine; selecting, for localization of the machine and based at least on the first operating context, a first localization variant that uses first sensor data corresponding to a first sensor modality set that includes one or more vision sensor modalities, the first localization variant corresponding to one or more first parameter values of one or more parameters used for performing the localization, the one or more first parameter values indicating a first manner in which the first sensor data is processed for performing the localization; determining that the first operating context of the machine has changed to a second operating context; and responsive to determining that the first operating context has changed to the second operating context, transitioning, for localization of the machine and based at least on the second operating context, from the first localization variant to a second localization variant that uses second sensor data corresponding to a second sensor modality set that also includes one or more additional or one or more less vision sensor modalities as compared to the first sensor modality set, second localization variant corresponding to one or more second parameter values of the second localization variant indicating a second manner in which the second sensor data is processed for performing the localization.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
High definition map based localization optimization
Patent number
US12729966B2
Application number
17375213
Filed
Jul 14, 2021
Granted
Sep 8, 2026
Inventors
1
Claims
20

Classified under

G01C 21/32 Physics & computingG01C 21/3602 Physics & computingG01C 21/3815 Physics & computingG01C 21/3867 Physics & computingG01C 21/3878 Physics & computingG01C 21/3881 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Nvidia in Cars & transport

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.