Get the newsletter
Nvidia · Automotive · Filed Jul 22, 2026 · USPTO published Nov 19, 2026 · This week's release

Nvidia Patents a Voting System That Double-Checks Where a Self-Driving Car Thinks It Is

A self-driving car that trusts a single sensor can be fooled by one bad view. Nvidia's patent application has the car blend many sources into one guess, then makes trusted backup systems vote on whether that guess is safe to follow.

A self-driving car fitted with external cameras, radar, lidar, and internal sensors used to track its position on the road. Drawing from patent filing US 2026/0365200 A1.
A self-driving car fitted with external cameras, radar, lidar, and internal sensors used to track its position on the road.All 22 drawings ↓
Publication number
US 2026/0365200 A1(US20260365200A1)
Applicant
Nvidia Corporation
Filed · Published
Jul 22, 2026 · Nov 19, 2026
Inventors
Aidin Ehsanibenafati, Jonas Nilsson, Amir Akbarzadeh, Hae Jong Seo
Status when we published
Waiting for an examiner
Document
20 claims
US classification
701/23
Parent application
Continuation of 17/483,019 (filed Sep 23, 2021)(17483019)

What Nvidia's self-driving voting check does

You're riding in a self-driving car on a rainy highway, and spray from a truck blurs what the front camera can see of the lane lines. The car still has to know exactly where it is and where the road goes. A wrong guess could put it in the wrong lane.

Nvidia's patent application describes a way to blend several sources, such as cameras, radar, lidar (a laser-based sensor) and stored high-detail maps, into one best guess. Then comes the safety check: the blended guess is only used if at least two separate, trusted sources agree with it. Think of it as a small panel of voters.

If the vote fails, the car falls back on one of the individual sources. If a sensor goes dark for a few seconds, the car can estimate its position from its speed and its last good reading. The goal is a ride that is smooth and also meets strict safety rules.

From the filing · CLAIM 1
… one or more arbiter components processing two or more outputs of two or more discrete processing components of the plurality of processing components that independently perform path-related processing for the machine …

Translation: Multiple computer chips independently calculate where the car should go, and a referee chip checks their work.

How the car blends sensors and checks the blend

The claims cover a machine with three kinds of processors (CPUs, GPUs and hardware accelerators) in which an arbiter (a referee component that decides which answer to trust) takes the outputs of two or more separate components that each work out the path on their own. The claims say at least one resulting operation can meet ASIL D, the strictest automotive safety rating.

The description fills in the steps:

  • Each source, such as a camera or radar, makes its own position estimate, and a fusion step blends them.
  • Comparators (the filing calls them "voters") check the blend against the individual estimates, and at least two must agree.
  • The same trick runs on the lane graph, a digital map of lane centers and edges built from stored map data and live sensor views.
  • If confidence falls below a threshold, the car swaps in the most confident individual answer.

The filing splits the safety burden so the blending step can stay flexible, while the simple voting checks carry the strict rating. Dead reckoning (estimating position from the last good reading plus speed and heading) covers short gaps of a few seconds. Other claims add a second, parallel path generator, and the description adds a second control unit fed by satellite data that can take over.

From the filing · THE ABSTRACT
… 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 …

Translation: If at least two independent checks match the car's calculated location, the system confirms it is safe to use.

What this means for smoother self-driving rides

If you ever ride in a self-driving car, you want two things: safety and a ride that doesn't lurch. The filing's background says that proving every individual part meets the top safety rating is costly, and that playing it safe at every step can give a ride that is safe but not pleasant. Blending sources lets the car steer more smoothly, while the vote keeps a safety check in place.

For Nvidia, the pitch is less development and testing effort, since only the simple checking parts need the strictest proof. The filing also covers robots, not only cars, and mentions running on edge devices or in a data center. A patent application is not a product, and nothing here says when a car would use it.

That makes this Nvidia's 116th filing we've tracked since May in our self-driving sensing race watchlist, adding to earlier applications like the radar chip that pre-processes data and blocked sensor detection.

Source: US 2026/0365200 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Nvidia patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 22 sheets

22 drawing sheets from US 2026/0365200 A1 · click any drawing to enlarge

Sensors and controls placed around a self-driving car, drawing sheet 1 from US 2026/0365200 A1
Sheet 1 Sensors and controls placed around a self-driving car
Overlapping camera views scanning around the vehicle, drawing sheet 2 from US 2026/0365200 A1
Sheet 2 Overlapping camera views scanning around the vehicle
Comparing multiple sensors to verify car position and lanes, drawing sheet 3 from US 2026/0365200 A1
Sheet 3 Comparing multiple sensors to verify car position and lanes
Checking radar and camera readings against each other, drawing sheet 4 from US 2026/0365200 A1
Sheet 4 Checking radar and camera readings against each other
Matching live camera views with digital map lanes, drawing sheet 5 from US 2026/0365200 A1
Sheet 5 Matching live camera views with digital map lanes
Backup computers running parallel safety checks, drawing sheet 6 from US 2026/0365200 A1
Sheet 6 Backup computers running parallel safety checks
How the car votes on position before choosing a path, drawing sheet 7 from US 2026/0365200 A1
Sheet 7 How the car votes on position before choosing a path
Estimating location using vehicle motion when sensor views fade, drawing sheet 8 from US 2026/0365200 A1
Sheet 8 Estimating location using vehicle motion when sensor views fade
Show the other 14 sheets
Updating car maps through satellites and the cloud, drawing sheet 9 from US 2026/0365200 A1
Sheet 9 Updating car maps through satellites and the cloud
Internal chip circuits that calculate and store AI decisions, drawing sheet 10 from US 2026/0365200 A1
Sheet 10 Internal chip circuits that calculate and store AI decisions
Custom chips paired with memory to accelerate AI, drawing sheet 11 from US 2026/0365200 A1
Sheet 11 Custom chips paired with memory to accelerate AI
Server clusters organized to run and coordinate large driving software, drawing sheet 12 from US 2026/0365200 A1
Sheet 12 Server clusters organized to run and coordinate large driving software
Computer motherboards that connect vehicle processors with sensors, drawing sheet 13 from US 2026/0365200 A1
Sheet 13 Computer motherboards that connect vehicle processors with sensors
Mobile system components linking cameras, GPS, and sensors together, drawing sheet 14 from US 2026/0365200 A1
Sheet 14 Mobile system components linking cameras, GPS, and sensors together
Graphics chips that process live driving video, drawing sheet 15 from US 2026/0365200 A1
Sheet 15 Graphics chips that process live driving video
Multi-core chips sharing internal memory to speed up navigation tasks, drawing sheet 16 from US 2026/0365200 A1
Sheet 16 Multi-core chips sharing internal memory to speed up navigation tasks
Training and rolling out vision models using medical image data, drawing sheet 17 from US 2026/0365200 A1
Sheet 17 Training and rolling out vision models using medical image data
Computing infrastructure that supports model creation and live services, drawing sheet 18 from US 2026/0365200 A1
Sheet 18 Computing infrastructure that supports model creation and live services
Refining pre-trained models with human feedback and custom datasets, drawing sheet 19 from US 2026/0365200 A1
Sheet 19 Refining pre-trained models with human feedback and custom datasets
Assisting human image labelers with an automated helper server, drawing sheet 20 from US 2026/0365200 A1
Sheet 20 Assisting human image labelers with an automated helper server
Car chips and sensors that guide autonomous driving, drawing sheet 21 from US 2026/0365200 A1
Sheet 21 Car chips and sensors that guide autonomous driving
Cloud servers sending updated maps and AI to cars, drawing sheet 22 from US 2026/0365200 A1
Sheet 22 Cloud servers sending updated maps and AI to cars
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.