IP Library › Granted Patent US 12,420,825
Granted Patent B2
US 12,420,825 · App. 18/483,841 · Granted Sep 23, 2025

Periodically mapping calibration scene for calibrating autonomous vehicle sensors

Inventors: Daniel Chou (San Diego, CA); Nigel Rodrigues (Palo Alto, CA); Jordan Michael Croom (San Francisco, CA)
Assignee: GM Cruise Holdings LLC
B60W60/00G01C21/3804G01C21/3885G06V20/56G06V40/10B60W2050/0083B60W2420/00B60W2556/40B60W2556/45
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 12,420,825
App. No.
18/483,841
Granted
Sep 23, 2025
Kind
B2
Abstract

A sensor calibration system periodically receives scene data from a detector in a calibration scene. The calibration scene includes calibration targets. The sensor calibration system generates a calibration map based on the scene data. The calibration map is a virtual representation of the calibration scene and includes features of the calibration targets that can be used as ground truth features for calibrating AV sensors. The sensor calibration system can periodically update the calibration map. For instance, the sensor calibration system receives the scene data at a predetermined frequency and updates the calibration map every time it receives new scene data. The predetermined frequency may be a frequency of the detector completing a full scan of the calibration scene. The sensor calibration system provides a latest version of the calibration map for being used by an AV to calibrate a sensor on the AV 110.

Claims (40)

1. A method, comprising:

receiving, by a sensor calibration system, scene data from a detector in a calibration scene, the calibration scene comprising a calibration target for calibrating a sensor on a vehicle, the detector separate from the vehicle;

generating, by the sensor calibration system, a calibration map based on the scene data from the detector, the calibration map being a virtual representation of the calibration scene and including a ground truth feature of the calibration target;

receiving, by the sensor calibration system from the vehicle, a request for the calibration map;

determining, by the sensor calibration system, whether the calibration scene is ready for the vehicle based on a latest version of the calibration map by detecting objects other than the calibration target in the latest version of the calibration map; and

subsequent to receiving the request and in response to determining that the calibration scene is ready for the vehicle, providing, by the sensor calibration system, the calibration map to calibrate the sensor on the vehicle.

2. The method of claim 1 , wherein a distance of the sensor from a ground of the calibration scene is equal to a distance of the detector from the ground of the calibration scene.

3. The method of claim 1 , wherein the scene data comprises a point cloud including a plurality of points, and at least some of the points represent features of the calibration target.

4. The method of claim 1 , wherein the scene data from the detector comprises one or more images of the calibration scene, and the one or more images are captured by the detector.

5. The method of claim 1 , wherein determining whether the calibration scene is ready for the vehicle comprises:

detecting whether a person is present in the calibration scene based on the latest version of the calibration map; and

in response to determining that a person is present in the calibration scene, determining that the calibration scene is not ready for the vehicle.

6. The method of claim 1 , wherein determining whether the calibration scene is ready for the vehicle comprises:

detecting whether the calibration target is at a predetermined location based on the latest version of the calibration map; and

in response to determining that the calibration target is not at the predetermined location, determining that the calibration scene is not ready for the vehicle.

7. The method of claim 6 , further comprising:

in response to determining that the calibration target is not at the predetermined location, moving the calibration target to the predetermined location.

8. The method of claim 1 , further comprises:

instructing the vehicle to navigate to a predetermined location inside the calibration scene; and

causing the vehicle to move relative to the calibration target.

9. One or more non-transitory computer-readable media storing instructions executable to perform operations, the operations comprising:

receiving, by a sensor calibration system, scene data from a detector in a calibration scene, the calibration scene comprising a calibration target for calibrating a sensor on a vehicle, the detector separate from the vehicle;

generating, by the sensor calibration system, a calibration map based on the scene data from the detector, the calibration map being a virtual representation of the calibration scene and including a ground truth feature of the calibration target;

receiving, by the sensor calibration system from the vehicle, a request for the calibration map;

determining, by the sensor calibration system, whether the calibration scene is ready for the vehicle based on a latest version of the calibration map by detecting objects other than the calibration target in the latest version of the calibration map; and

subsequent to receiving the request and in response to determining that the calibration scene is ready for the vehicle, providing, by the sensor calibration system, the calibration map to calibrate the sensor on the vehicle.

10. The one or more non-transitory computer-readable media of claim 9 , wherein a distance of the sensor from a ground of the calibration scene is equal to a distance of the detector from the ground of the calibration scene.

11. The one or more non-transitory computer-readable media of claim 9 , wherein the scene data comprises a point cloud including a plurality of points, and at least some of the points represent features of the calibration target.

12. The one or more non-transitory computer-readable media of claim 9 , wherein the scene data from the detector comprises one or more images of the calibration scene, and the one or more images are captured by the detector.

13. The one or more non-transitory computer-readable media of claim 9 , wherein determining whether the calibration scene is ready for the vehicle comprises:

detecting whether the calibration target is at a predetermined location based on the latest version of the calibration map; and

in response to determining that the calibration target is not at the predetermined location, determining that the calibration scene is not ready for the vehicle.

14. A computer system, the comprising:

a computer processor for executing computer program instructions; and

one or more non-transitory computer-readable media storing computer program instructions executable by the computer processor to perform operations comprising:

receiving, by a sensor calibration system, scene data from a detector in a calibration scene, the calibration scene comprising a calibration target for calibrating a sensor on a vehicle, the detector separate from the vehicle;

generating, by the sensor calibration system, a calibration map based on the scene data from the detector, the calibration map being a virtual representation of the calibration scene and including a ground truth feature of the calibration target;

receiving, by the sensor calibration system from the vehicle, a request for the calibration map;

determining, by the sensor calibration system, whether the calibration scene is ready for the vehicle based on a latest version of the calibration map by detecting objects other than the calibration target in the latest version of the calibration map; and

subsequent to receiving the request and in response to determining that the calibration scene is ready for the vehicle, providing, by the sensor calibration system, the calibration map to calibrate the sensor on the vehicle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 10, 2023
From: CHOU, DANIEL; RODRIGUES, NIGEL; CROOM, JORDAN MICHAEL
To: GM CRUISE HOLDINGS LLC
Reel/Frame 065170/0030 →
Continuity (2)
Continuation 17550239 · Dec 14, 2021
Related Publication 20240034347A1 · Feb 1, 2024
References Cited (17)
US 11594037B1 · Grossman · 2023 [cited by examiner]
US 20170132934A1 · Kentley · 2017 [cited by examiner]
US 20170248426A1 · Jesudason · 2017 [cited by examiner]
US 20170343654A1 · Valois · 2017 [cited by examiner]
US 20180299533A1 · Pliefke · 2018 [cited by examiner]
US 20190056484A1 · Bradley · 2019 [cited by examiner]
US 20190204427A1 · Abari · 2019 [cited by examiner]
US 20200200566A1 · Kim · 2020 [cited by examiner]
US 20210197854A1 · Grabe · 2021 [cited by examiner]
US 20210215505A1 · Castorena Martinez · 2021 [cited by examiner]
US 20210239793A1 · Yu · 2021 [cited by examiner]
US 20220194412A1 · Zhang · 2022 [cited by examiner]
US 20220204019A1 · Lauterbach · 2022 [cited by examiner]
US 20220244395A1 · Chen · 2022 [cited by examiner]
US 20230076693A1 · Braun · 2023 [cited by examiner]
US 20230088398A1 · Brühlmeier · 2023 [cited by examiner]
WO WO2017189361A1 · 2017 [cited by examiner]