Get the newsletter
Aurora · Automotive · Filed Jul 27, 2026 · USPTO published Nov 19, 2026 · This week's release

Aurora Files Patent for Scoring Which Mistakes Matter When Self-Driving Vehicles Spot Objects

A 20 centimeter error in where a car is can be harmless at 200 meters and a real problem when that car is beside you. Aurora's new patent covers software that learns that difference when it grades a self-driving system.

A driverless vehicle simulator tracks surrounding cars and cross traffic through an intersection to evaluate driving choices. Drawing from patent filing US 2026/0365201 A1.
A driverless vehicle simulator tracks surrounding cars and cross traffic through an intersection to evaluate driving choices.All 16 drawings ↓
Publication number
US 2026/0365201 A1(US20260365201A1)
Applicant
Aurora Operations, Inc.
Filed · Published
Jul 27, 2026 · Nov 19, 2026
Inventors
Davis Edward King
Status when we published
Waiting for an examiner
Document
20 claims
US classification
701/27
Parent application
Continuation of 18/969,437 (filed Dec 5, 2024)(18969437)

How Aurora decides which detection errors count

Imagine a self-driving truck that misjudges a parked car on the shoulder by a few inches. Nobody would care. Now imagine the same slip for a car in the lane right next to the truck. That one matters a lot.

Aurora's patent is about teaching software to tell those two situations apart. Before a self-driving system goes on the road, engineers test how well it spots objects by comparing what it saw against a human-checked answer key. Demanding a perfect match is impossible, and hand-writing rules for every case is a mess. So Aurora's system measures several kinds of difference (position, direction, speed and more), then uses learned weights to decide how much each one counts, based on things like how far away the object is and which lane it's in.

The output is a single score that says whether the detection was good enough.

From the filing · CLAIM 21
… aggregating, into an aggregate divergence, the plurality of component divergence values based on a plurality of learned parameters that define an influence of the plurality of component divergence values on the aggregate divergence …

Translation: Combining different error measurements using learned weights to figure out how bad a mistake is.

How Aurora's learned weights build one score

The filing describes an evaluation system: software that grades another piece of self-driving software. It takes an object the vehicle's sensors detected (say, a box drawn around a car) and compares it to a label, the human-checked answer for where that object really was.

Instead of one yes-or-no comparison, it computes several component divergence values, each measuring a different kind of miss, such as how the box is rotated or how far off its position is. A small learned model then combines them into one aggregate divergence score. The learned weights set how much each difference counts. They can be constrained so a weight never flips sign (for example, extra rotation error can never be treated as a reward).

Context adjusts the weights. A context metric might capture lane position, distance from the vehicle, or how hidden the object is, so the same rotation error counts more for a car in the next lane than for one parked on the shoulder.

The weights are fit using a bank of test pairs that people marked as good matches, bad matches, or spurious detections. The claims also cover the last step: updating the state of the system being tested, such as recording that it meets a benchmark level of performance.

From the filing · THE ABSTRACT
… obtaining an object detection from a perception system that describes an object in an environment of the autonomous vehicle; (b) obtaining, from a reference dataset, a label that describes a reference position of the object in the environment …

Translation: Comparing what the self driving car sees against a correct reference dataset.

Why faster testing matters for self-driving

Self-driving systems have to be tested on huge numbers of scenes, and the hard part is the borderline cases, where someone must decide whether the system's guess was close enough. Aurora's filing describes automating that judgment, which it says could allow much higher test volume at far greater speed than manual review.

For you, the effect is indirect. Better testing is how a software update that makes things worse gets caught before it reaches the road. The filing also says the same scoring can run live, helping a vehicle decide whether a new detection matches an object it is already tracking or should be thrown out as spurious. That extends the grader from the test lab into the driving software itself.

Source: US 2026/0365201 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 Aurora patent news breaks.

There are more where this came from

We read the new patents from Big Tech, carmakers and more and send you the ones worth knowing. Plain English, free, every week.

The drawings · 16 sheets

16 drawing sheets from US 2026/0365201 A1 · click any drawing to enlarge

A self-driving car tracking traffic to plan its route, drawing sheet 1 from US 2026/0365201 A1
Sheet 1 A self-driving car tracking traffic to plan its route
Key onboard computing parts that steer and brake the vehicle, drawing sheet 2 from US 2026/0365201 A1
Sheet 2 Key onboard computing parts that steer and brake the vehicle
Navigating a driverless passenger car through a crowded city grid, drawing sheet 3 from US 2026/0365201 A1
Sheet 3 Navigating a driverless passenger car through a crowded city grid
Guiding an autonomous semi truck along long highway freight routes, drawing sheet 4 from US 2026/0365201 A1
Sheet 4 Guiding an autonomous semi truck along long highway freight routes
Scoring detection mistakes by measuring their real world driving impact, drawing sheet 5 from US 2026/0365201 A1
Sheet 5 Scoring detection mistakes by measuring their real world driving impact
Measuring how far a car drifts from its lane, drawing sheet 6 from US 2026/0365201 A1
Sheet 6 Measuring how far a car drifts from its lane
Another road scene showing smaller car position errors, drawing sheet 7 from US 2026/0365201 A1
Sheet 7 Another road scene showing smaller car position errors
Sorting spotted objects by road context using simple yes-no questions, drawing sheet 8 from US 2026/0365201 A1
Sheet 8 Sorting spotted objects by road context using simple yes-no questions
Show the other 8 sheets
Combining detection errors with scene context to rate safety impacts, drawing sheet 9 from US 2026/0365201 A1
Sheet 9 Combining detection errors with scene context to rate safety impacts
An AI model scoring how sensor errors affect driving, drawing sheet 10 from US 2026/0365201 A1
Sheet 10 An AI model scoring how sensor errors affect driving
Automated tests checking if the safety scoring works reliably, drawing sheet 11 from US 2026/0365201 A1
Sheet 11 Automated tests checking if the safety scoring works reliably
A replay screen where human reviewers label roadway hazards, drawing sheet 12 from US 2026/0365201 A1
Sheet 12 A replay screen where human reviewers label roadway hazards
Steps for grading how closely detected objects match reality, drawing sheet 13 from US 2026/0365201 A1
Sheet 13 Steps for grading how closely detected objects match reality
Updating the evaluation system when human reviewers correct an assessment, drawing sheet 14 from US 2026/0365201 A1
Sheet 14 Updating the evaluation system when human reviewers correct an assessment
Training vehicle perception models until they pass rigorous validation, drawing sheet 15 from US 2026/0365201 A1
Sheet 15 Training vehicle perception models until they pass rigorous validation
Computer hardware that trains models and evaluates vehicle performance, drawing sheet 16 from US 2026/0365201 A1
Sheet 16 Computer hardware that trains models and evaluates vehicle performance
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.