IP Library Granted Patent US 12,422,521
Granted Patent B2
US 12,422,521 · App. 18/093,306 · Granted Sep 23, 2025

Weather station for sensor calibration

Inventor: Luca Castellotto (Oakland, CA)
Assignee: GM Cruise Holdings LLC
G01S7/40G01S13/931G01W1/02B60W2420/00B60W2555/20
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 12,422,521
App. No.
18/093,306
Granted
Sep 23, 2025
Kind
B2
Abstract

The present disclosure generally relates to sensor calibration and more specifically, to sensor calibration using weather data. In some aspects, the present disclosure provides a process for receiving a set of weather data from a weather measurement station disposed within a calibration environment, determining if a predetermined weather condition is indicated by the set of weather data, and collecting, using one or more AV sensors, a set of sensor data within the calibration environment, if the predetermined weather condition is indicated by the set of weather data. Systems and machine-readable media are also provided.

Claims (34)

1. An apparatus, comprising:

at least one memory storing instructions; and

at least one processor coupled to the at least one memory, wherein the instructions, when executed by the at least one processor, cause the at least one processor to:

receive a set of weather data, from a weather measurement station, disposed within a calibration environment;

determine that a predetermined weather condition is indicated by the set of weather data;

collect, using a plurality of autonomous vehicle (AV) sensors, a set of sensor data using one or more sensor calibration targets in the calibration environment;

determine, for each AV sensor of the plurality of AV sensors, based on the set of sensor data, a corresponding confidence score representing a corresponding performance metric of the AV sensor for the predetermined weather condition;

determine, for each AV sensor of the plurality of AV sensors, based on the corresponding confidence scores, a corresponding weighting factor for the AV sensor relative to other AV sensors for the predetermined weather condition; and

configure an AV with the corresponding weighting factors for the predetermined weather condition, wherein the AV is configured to weight, based on the corresponding weighting factors, measurements obtained using each AV sensor of the AV relative to other AV sensors of the AV when the AV detects the predetermined weather condition.

2. The apparatus of claim 1 , wherein the one or more AV sensors comprise one or more of a Light Detection and Ranging (LiDAR) sensor, a camera sensor, or a Radio Detection and Ranging (RADAR) sensor.

3. The apparatus of claim 1 , wherein the predetermined weather condition comprises one or more of rain, fog, snow, sun, hail, lightning, humidity, temperature, cloudiness, tornado, or hurricane.

4. The apparatus of claim 1 , wherein the one or more sensor calibration targets comprise one or more of an optical calibration target, a fiducial, or a reflector.

5. The apparatus of claim 1 , wherein the weather measurement station comprises one or more of a thermometer, a barometer, a hygrometer, an anemometer, a pyranometer, a rain gauge, a windsock, a wind vane, a present weather sensor, a disdrometer, a transmissometer, or a ceilometer.

6. A computer-implemented method, comprising:

receiving a set of weather data, from a weather measurement station, disposed within a calibration environment;

determining that a predetermined weather condition is indicated by the set of weather data;

collecting, using a plurality of autonomous vehicle (AV) sensors, a set of sensor data using one or more sensor calibration targets in the calibration environment;

determining, for each AV sensor of the plurality of AV sensors, based on the set of sensor data, a corresponding confidence score representing a corresponding performance metric of the AV sensor for the predetermined weather condition;

determining, for each AV sensor of the plurality of AV sensors, based on the corresponding confidence scores, a corresponding weighting factor for the AV sensor relative to other AV sensors for the predetermined weather condition; and

configuring an AV with the corresponding weighting factors for the predetermined weather condition, wherein the AV is configured to weight, based on the corresponding weighting factors, measurements obtained using each AV sensor of the AV relative to other AV sensors of the AV when the AV detects the predetermined weather condition.

7. The computer-implemented method of claim 6 , wherein the one or more AV sensors comprise one or more of a Light Detection and Ranging (LiDAR) sensor, a camera sensor, or a Radio Detection and Ranging (RADAR) sensor.

8. The computer-implemented method of claim 6 , wherein the predetermined weather condition comprises one or more of rain, fog, snow, sun, hail, lightning, humidity, temperature, cloudiness, tornado, or hurricane.

9. The computer-implemented method of claim 6 , wherein the one or more sensor calibration targets comprise one or more of an optical calibration target, a fiducial, or a reflector.

10. The computer-implemented method of claim 6 , wherein the weather measurement station comprises one or more of a thermometer, a barometer, a hygrometer, an anemometer, a pyranometer, a rain gauge, a windsock, a wind vane, a present weather sensor, a disdrometer, a transmissometer, or a ceilometer.

11. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to:

receive a set of weather data, from a weather measurement station, disposed within a calibration environment;

determine that a predetermined weather condition is indicated by the set of weather data;

collect, a plurality of autonomous vehicle (AV) sensors, a set of sensor data using one or more sensor calibration targets in the calibration environment;

determine, for each AV sensor of the plurality of AV sensors, based on the set of sensor data, a corresponding confidence score representing a corresponding performance metric of the AV sensor for the predetermined weather condition;

determine, for each AV sensor of the plurality of AV sensors, based on the corresponding confidence scores, a corresponding weighting factor for the AV sensor relative to other AV sensors for the predetermined weather condition; and

configure an AV with the corresponding weighting factors for the predetermined weather condition, wherein the AV is configured to weight, based on the corresponding weighting factors, measurements obtained using each AV sensor of the AV relative to other AV sensors of the AV when the AV detects the predetermined weather condition.

12. The non-transitory computer-readable storage medium of claim 11 , wherein the one or more AV sensors comprise one or more of a Light Detection and Ranging (LiDAR) sensor, a camera sensor, or a Radio Detection and Ranging (RADAR) sensor.

13. The non-transitory computer-readable storage medium of claim 11 , wherein the predetermined weather condition comprises one or more of rain, fog, snow, sun, hail, lightning, humidity, temperature, cloudiness, tornado, or hurricane.

14. The non-transitory computer-readable storage medium of claim 11 , wherein the one or more sensor calibration targets comprise one or more of an optical calibration target, a fiducial, or a reflector.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 4, 2023
From: CASTELLOTTO, LUCA
To: GM CRUISE HOLDINGS LLC
Reel/Frame 062277/0111 →
Continuity (1)
Related Publication 20240219519A1 · Jul 4, 2024
References Cited (6)
US 11567503B1 · Roy · 2023 [cited by examiner]
US 20200019160A1 · McArthur · 2020 [cited by examiner]
US 20210191399A1 · Verghese · 2021 [cited by examiner]
US 20220299446A1 · Tuononen · 2022 [cited by examiner]
US 20230152489A1 · Dormody · 2023 [cited by examiner]
US 20230236317A1 · Fina · 2023 [cited by examiner]