IP Library › Granted Patent US 12,646,363
Granted Patent B2
US 12,646,363 · App. 18/467,273 · Granted Jun 2, 2026

Lightweight autonomous system evaluation platform

Inventors: Brian C. Becker (Pittsburgh, PA); Peter VanTuyl Bentley (Seattle, WA); Matthew Thomas Bradley (Pittsburgh, PA); Nathan Falk (San Francisco, CA); Jack Wyatt Harris (Brooklyn, NY); Marion Le Borgne (San Francisco, CA); Timothy Patrick Wojtaszek (Mill Valley, CA); Tashwin Kaur Khurana (Pittsburgh, PA)
Assignee: AURORA OPERATIONS, INC.
G07C5/0841B60W60/001G06F16/901B60W2540/215
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,646,363
App. No.
18/467,273
Granted
Jun 2, 2026
Kind
B2
Abstract

An example method includes (a) generating a request to obtain log data descriptive of operation of an autonomous vehicle control system in a subject scenario, the log data indexed by an indexing parameter; (b) submitting the request to a log repository service, the log repository service configured to receive the request and serve, responsive to the request, log metadata; (c) loading, based on the log metadata and an index value of the indexing parameter, a log data sketch associated with the index value; and (d) loading, based on the log metadata and the index value, and responsive to an inspection indicator, detailed log data associated with the index value.

Claims (51)

1 . A computer-implemented method for autonomous vehicle control system evaluation, comprising:

(a) generating a request to obtain log data descriptive of operation of an autonomous vehicle control system in a subject scenario, the log data indexed by an indexing parameter;

(b) submitting the request to a log repository service, the log repository service configured to receive the request and serve, responsive to the request, log metadata;

(c) loading, based on the log metadata and an index value of the indexing parameter, a log data sketch associated with the index value;

(d) generating, using a machine-learned model, a data tier corresponding to the log data based on the log data sketch, wherein:

the data tier is associated with a priority of the log data based on a predicted indication for further evaluation, and

the data tier corresponds to at least a first latency budget and a second latency budget wherein the first latency budget and the second latency budget are associated with loading the log data at different speeds according to the priority; and

(e) loading, based on the data tier, the log metadata, and the index value, and responsive to an inspection indicator, detailed log data associated with the index value.

2 . The computer-implemented method of claim 1 , wherein:

the log data sketch comprises data at a first fidelity with respect to the log data; and

the detailed log data comprises data at a second fidelity higher than the first fidelity.

3 . The computer-implemented method of claim 1 , wherein loading the log data sketch comprises rendering the log data sketch on a display interface.

4 . The computer-implemented method of claim 1 , wherein a user input sequence comprises a plurality of index values of the indexing parameter, and wherein the inspection indicator corresponds to a selection of a particular index value of the plurality of index values.

5 . The computer-implemented method of claim 1 , wherein a sketch compression value associated with the log data sketch is adjusted based on a communication speed between a log data repository and an evaluation interface.

6 . The computer-implemented method of claim 1 comprising:

(f) modifying, from a default value, one or more parameters of the log metadata to customize contents of the log data sketch.

7 . The computer-implemented method of claim 1 , wherein the detailed log data is dynamically loaded or output on-demand.

8 . The computer-implemented method of claim 1 , wherein the inspection indicator corresponds to a user input.

9 . The computer-implemented method of claim 8 , wherein a user input sequence corresponds to a scrubbing input, and wherein a selection of a particular index value corresponds to a rate change in the scrubbing input associated with the particular index value.

10 . The computer-implemented method of claim 1 , wherein the indexing parameter is time.

11 . The computer-implemented method of claim 1 , wherein:

the log data sketch comprises data at a first resolution; and

the detailed log data comprises data at a second resolution higher than the first resolution.

12 . The computer-implemented method of claim 1 , wherein the log data sketch comprises a downsampled representation of the log data.

13 . The computer-implemented method of claim 1 , wherein the log data sketch comprises a reduced range of log data values from the log data.

14 . The computer-implemented method of claim 1 , wherein the log data sketch is loaded by an evaluation interface that runs in a browser, and wherein the log metadata is retrieved upon loading of an initial set of markup instructions for the evaluation interface.

15 . A computing system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions executable by the one or more processors to cause the computing system to perform operations, the operations comprising:

(a) generating a request to obtain log data descriptive of operation of an autonomous vehicle control system in a subject scenario, the log data indexed by an indexing parameter;

(b) submitting the request to a log repository service, the log repository service configured to receive the request and serve, responsive to the request, log metadata;

(c) loading, based on the log metadata and an index value of the indexing parameter, a log data sketch associated with the index value;

(d) generating, using a machine-learned model, a data tier corresponding to the log data based on the log data sketch, wherein:

the data tier is associated with a priority of the log data based on a predicted indication for further evaluation, and

the data tier corresponds to at least a first latency budget and a second latency budget wherein the first latency budget and the second latency budget are associated with loading the log data at different speeds according to the priority; and

(e) loading, based on the data tier, the log metadata, and the index value, and responsive to an inspection indicator, detailed log data associated with the index value.

16 . The computing system of claim 15 , wherein:

the log data sketch comprises data at a first fidelity with respect to the log data; and

the detailed log data comprises data at a second fidelity higher than the first fidelity.

17 . The computing system of claim 15 , wherein loading the log data sketch comprises rendering the log data sketch on a display interface.

18 . The computing system of claim 15 , wherein a user input sequence comprises a plurality of index values of the indexing parameter, and wherein the inspection indicator corresponds to a selection of a particular index value of the plurality of index values.

19 . The computing system of claim 15 , the operations comprising:

(D) modifying, from a default value, one or more parameters of the log metadata to customize contents of the log data sketch.

20 . One or more non-transitory computer-readable media storing instructions executable by one or more processors to cause a computing system to perform operations, the operations comprising:

(a) generating a request to obtain log data descriptive of operation of an autonomous vehicle control system in a subject scenario, the log data indexed by an indexing parameter;

(b) submitting the request to a log repository service, the log repository service configured to receive the request and serve, responsive to the request, log metadata;

(c) loading, based on the log metadata and an index value of the indexing parameter, a log data sketch associated with the index value;

(d) generating, using a machine-learned model, a data tier corresponding to the log data based on the log data sketch, wherein:

the data tier associated with a priority of the log data based on a predicted indication for further evaluation, and

the data tier corresponds to at least a first latency budget and a second latency budget wherein the first latency budget and the second latency budget are associated with loading the log data at different speeds according to the priority; and

(e) loading, based on the data tier, the log metadata, and the index value, and responsive to an inspection indicator, detailed log data associated with the index value.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 15, 2024
From: KHURANA, TASHWIN KAUR
To: AURORA OPERATIONS, INC.
Reel/Frame 067987/0645 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 28, 2023
From: BECKER, BRIAN C.; BENTLEY, PETER VANTUYL; BRADLEY, MATTHEW THOMAS; FALK, NATHAN; HARRIS, JACK WYATT; LE BORGNE, MARION; WOJTASZEK, TIMOTHY PATRICK
To: AURORA OPERATIONS, INC.
Reel/Frame 065971/0906 →
Continuity (2)
Provisional Application 63406598 · Sep 14, 2022
Related Publication 20240087378A1 · Mar 14, 2024
References Cited (11)
US 20140344622A1 · Huang · 2014 [cited by examiner]
US 20170357320A1 · Chaudhri · 2017 [cited by examiner]
US 20180103348A1 · Malone · 2018 [cited by examiner]
US 20200134077A1 · Tong · 2020 [cited by examiner]
US 20230316816A1 · O'Grady · 2023 [cited by examiner]
Aurora, “The offline executor: Virtual testing and the Aurora Driver”, Aug. 20, 2019, https://blog.aurora.tech/engineering/the-offline-executor, retrieved on Oct. 10, 2023, 9 pages. [cited by applicant]
AVS Auto, “Make a leap with your autonomous and robotics data”, https://avs.auto/#/, retrieved on Oct. 10, 2023, 4 pages. [cited by applicant]
AVS Auto, “Playground”, https://avs.auto/playground/, retrieved on Oct. 12, 2023, 1 page. [cited by applicant]
AVS Auto, “Streetscape.gl”, https://avs.auto/demo/index.html, retrieved on Oct. 12, 2023, 6 pages. [cited by applicant]
Github. “Basic Optimization of the WebGL Rendering Pipeline”, https://rye-terrell.github.io/basic-webgl-optimizations/, retrieved on Oct. 10, 2023, 16 pages. [cited by applicant]
Uber Blog, “Engineering Uber's Self-Driving Car Visualization Platform for the Web”, Aug. 28, 2017, https://www.uber.com/blog/atg-dataviz/, 6 pages. [cited by applicant]