# US 2023/0266147 A1 · Sensor calibration

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0266147 A1
- Document ID: US20230266147A1
- Status: Published application
- Kind: A1
- Application number: 17/675,725
- Filed: 2022-02-18
- Published: 2023-08-24
- Earliest claimed: 2022-02-18
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Diyan TENG; Junsheng HAN; Victor KULIK; Mehul SOMAN; Rashmi KULKARNI
- Web page: https://patentgrep.com/patent/US20230266147A1

## CPC

- G01C 25/00: Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass (testing, calibrating or compensating compasses G01C17/38)
- G01C 25/005: {initial alignment, calibration or starting-up of inertial devices}
- G01P 21/00: Testing or calibrating of apparatus or devices covered by the preceding groups
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- G01P: MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT (measuring or recording blood flow A61B5/02, A61B8/06; monitoring speed or deceleration of electrically-propelled vehicles B60L3/00; vehicle lighting systems adapted to indicate speed B60Q1/54; determining position or course in navigation, measuring ground distance in geodesy or surveying G01C; combined measuring devices for measuring two or more variables of movement G01C23/00; measuring velocity of sound G01H; measuring velocity of light G01J7/00; measuring direction or velocity of solid objects by reception or emission of radiowaves or other waves and based on propagation effects, e.g. Doppler effect, propagation time, direction of propagation, G01S; measuring speed of nuclear radiation G01T; measuring acceleration of gravity G01V; {measuring or recording the speed of trains B61L23/00; speed indicators incorporated in motor vehicles B60K35/00; measuring frequency or phase G01R; traffic control G08G})

## Abstract

Systems and techniques are described herein. For example, a process can include obtaining first sensor measurement data associated with a and second sensor measurement from one or more sensors. In some cases, the first measurement data can be associated with a first time and the second sensor measurement data can be associated with a second time occurring after the first time. In some aspects, the process includes determining that the first sensor measurement data and the second sensor measurement data satisfy at least one batching condition. In some examples, the process includes, based on determining that the first sensor measurement data and the second sensor measurement data satisfy the at least one batching condition, generating a sensor measurement data batch including the first sensor measurement data, the second sensor measurement data, and at least one target sensor measurement data. Ins examples the process includes outputting the sensor measurement data batch.

## Claims

### Claim 1

A method comprising:
obtaining first sensor measurement data associated with a first time from one or more sensors of a device;
obtaining second sensor measurement data associated with a second time from the one or more sensors of the device, the second time occurring after the first time;
determining, by a data batching engine, that the first sensor measurement data and the second sensor measurement data satisfy at least one batching condition;
based on determining that the first sensor measurement data and the second sensor measurement data satisfy the at least one batching condition, generating, the data batching engine, a sensor measurement data batch including the first sensor measurement data and the second sensor measurement data, wherein the data batch is associated with at least one target sensor measurement data from a target sensor of the device, the at least one target sensor measurement data occurring between the first time and the second time;
selecting by a calibration policy engine based on the data batch, a calibration model for calibrating the at least one target sensor measurement data; and
generating, by the calibration model, calibrated target sensor data based on the at least one tar et sensor measurement data.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
comparing the calibrated target sensor data with an expected target sensor data, wherein the expected target sensor data is determined based on the data batch; and
adjusting, by a training engine based on comparing the calibrated target sensor data with the expected target sensor data, one or more parameters of the calibration policy engine.

### Claim 3 (depends on 2)

The method of claim 2, further comprising
determining an estimated orientation based on the calibrated target sensor data;
comparing the estimated orientation with a known orientation associated with the data batch; and
based on comparing the estimated orientation with the known orientation, adjusting the one or more parameters of the calibration policy engine.

### Claim 4 (depends on 3)

The method of claim 3, wherein the known orientation comprises a relative orientation change between the first time and the second time determined based on the first sensor measurement data and the second sensor measurement data and the estimated orientation comprises a relative orientation change determined based on the at least one target sensor measurement data.

### Claim 5 (depends on 4)

The method of claim 4, wherein the known orientation is determined at least in part based on at least one of a first angle of arrival and a first time of flight of a first radio frequency signal at the first time with at least one of a second angle of arrival and a second time of flight of a second radio frequency signal at the second time.

### Claim 6 (depends on 3)

The method of claim 3, wherein the known orientation is determined based on at least one of a charging station status, a computer vision algorithm, an angle of arrival of a radio frequency signal, a time of flight of a radio frequency signal, and a Global Navigation Satellite System (GNSS) status.

### Claim 7 (depends on 1)

The method of claim 1, wherein determining that the first sensor measurement data and the second sensor measurement data satisfy the at least one batching condition comprises determining a known orientation based on the first sensor measurement data and the second sensor measurement data.

### Claim 8 (depends on 6)

The method of claim 6, wherein the first sensor measurement data and the second sensor measurement data correspond to a same sensor orientation.

### Claim 9 (depends on 8)

The method of claim 8, wherein the known orientation is determined based on a relative orientation change between the first time and the second time.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
obtaining third sensor measurement data associated with a third time from the one or more sensors of the device, the third time occurring after the second time;
obtaining fourth sensor measurement data associated with a fourth time from the one or more sensors of the device, the fourth time occurring after the third time;
determining h that the third sensor measurement data and the fourth sensor measurement data satisfy an additional batching condition;
based on determining that the third sensor measurement data and the fourth sensor measurement data satisfy the additional batching condition, generating an additional sensor measurement batch including the third sensor measurement data, the fourth sensor measurement data, and at least an additional target sensor measurement data between the third time and the fourth time; and
outputting the additional sensor measurement batch.

### Claim 11

An apparatus for processing sensor measurement data, comprising:
one or more processors operably configured to:
obtain first sensor measurement data associated with a first time from one or more sensors of a device;
obtain second sensor measurement data associated with a second time from the one or more sensors of the device, the second time occurring after the first time;
determine, by a data batching engine, that the first sensor measurement data and the second sensor measurement data satisfy at least one batching condition;
based on determining that the first sensor measurement data and the second sensor measurement data satisfy the at least one batching condition, generate, by the data batching engine, a sensor measurement data batch including the first sensor measurement data, the second sensor measurement data, wherein the data batch is associated with at least one target sensor measurement data from a target sensor of the device, the at least one target sensor measurement data occurring between the first time and the second time;
select, by a calibration policy engine based on the data batch a calibration model for calibrating at least one_target sensor measurement data; and
generate, by the calibration model, calibrated target sensor data based on the at least one target sensor measurement data.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the one or more processors are configured to:
compare the calibrated target sensor data with an expected target sensor data determined based on the data batch; and
adjust, by a training engine based on comparing the calibrated target sensor data with the expected target sensor data, one or more parameters of the calibration policy engine.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the one or more processors are configured to:
determine an estimated orientation based on the calibrated target sensor data;
compare the estimated orientation with a known orientation associated with the data batch; and
based on compare the estimated orientation with the known orientation, adjust the one or more parameters of the calibration policy engine.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the known orientation comprises a relative orientation change between the first time and the second time determined based on the first sensor measurement data and the second sensor measurement data and the estimated orientation comprises a relative orientation change determined based on the at least one target sensor measurement data.

### Claim 15 (depends on 14)

The apparatus of claim 14, wherein the known orientation is determined at least in part based on at least one of a first angle of arrival and a first time of flight of a first radio frequency signal at the first time with at least one of a second angle of arrival and a second time of flight of a second radio frequency signal at the second time.

### Claim 16 (depends on 13)

The apparatus of claim 13, wherein the known orientation is determined based on at least one of a charging station status, a computer vision algorithm, an angle of arrival of a radio frequency signal, a time of flight of a radio frequency signal, and a Global Navigation Satellite System (GNSS) status.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein the first sensor measurement data and the second sensor measurement data correspond to a same sensor orientation.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the known orientation is determined based on a relative orientation change between the first time and the second time.

### Claim 19 (depends on 11)

The apparatus of claim 11, wherein, to determine that the first sensor measurement data and the second sensor measurement data satisfy the at least one batching condition, the one or more processors are operably configured to determine a known orientation based on the first sensor measurement data and the second sensor measurement data.

### Claim 20 (depends on 11)

The apparatus of claim 11, wherein the one or more processors are configured to:
obtain third sensor measurement data associated with a third time from the one or more sensors of the device, the third time occur after the second time;
obtain fourth sensor measurement data associated with a fourth time from the one or more sensors of the device, the fourth time occur after the third time;
determine, by the data batching engine, that the third sensor measurement data and the fourth sensor measurement data satisfy an additional batching condition;
based on determine that the third sensor measurement data and the fourth sensor measurement data satisfy the additional batching condition, generate an additional sensor measurement batch including the third sensor measurement data, the fourth sensor measurement data, and at least an additional target sensor measurement data between the third time and the fourth time; and
output the additional sensor measurement batch.

### Claim 21

A non-transitory computer-readable medium having stored thereon instructions that, when executed by one or more processors, cause the one or more processors to:
obtain first sensor measurement data associated with a first time from one or more sensors of a device;
obtain second sensor measurement data associated with a second time from the one or more sensors of the device, the second time occurring after the first time;
determine, by a data batching engine, that the first sensor measurement data and the second sensor measurement data satisfy at least one batching condition;
based on determining that the first sensor measurement data and the second sensor measurement data satisfy the at least one batching condition, generate, by the data batching engine, a sensor measurement data batch including the first sensor measurement data, the second sensor measurement data, wherein the data batch is associated with at least one target sensor measurement data from a target sensor of the device, the at least one target sensor measurement data occurring between the first time and the second time;
select, by a calibration policy engine based on the data batch, a calibration model for calibrating at least one target sensor measurement data, and
generate, by the calibration model, calibrated target sensor data based on the at least one tar et sensor measurement data.

### Claim 22 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising instructions that, when executed by the one or more processors, cause the one or more processors to:
compare the calibrated target sensor data with an expected target sensor data determined based on the data batch; and
adust, by a training engine based on comparing the calibrated target sensor data with the expected tar et sensor data, one or more parameters of the calibration policy engine.

### Claim 23 (depends on 22)

The non-transitory computer-readable medium of claim 22, further comprising instructions that, when executed by the one or more processors, cause the one or more processors to:
determine an estimated orientation based on the calibrated target sensor data;
compare the estimated orientation with a known orientation associated with the data batch; and
based on compare the estimated orientation with the known orientation, adjust the one or more parameters of the calibration policy engine.

### Claim 24 (depends on 23)

The non-transitory computer-readable medium of claim 23, wherein the known orientation comprises a relative orientation change between the first time and the second time determined based on the first sensor measurement data and the second sensor measurement data and the estimated orientation comprises a relative orientation change determined based on the at least one target sensor measurement data.

### Claim 25 (depends on 24)

The non-transitory computer-readable medium of claim 24, wherein the known orientation is determined at least in part based on at least one of a first angle of arrival and a first time of flight of a first radio frequency signal at the first time with at least one of a second angle of arrival and a second time of flight of a second radio frequency signal at the second time.

### Claim 26 (depends on 23)

The non-transitory computer-readable medium of claim 23, wherein the known orientation is determined based on at least one of a charging station status, a computer vision algorithm, an angle of arrival of a radio frequency signal, a time of flight of a radio frequency signal, and a Global Navigation Satellite System (GNSS) status.

### Claim 27 (depends on 26)

The non-transitory computer-readable medium of claim 26, wherein the first sensor measurement data and the second sensor measurement data correspond to a same sensor orientation.

### Claim 28 (depends on 27)

The non-transitory computer-readable medium of claim 27, wherein the known orientation is determined based on a relative orientation change between the first time and the second time.

### Claim 29 (depends on 21)

The non-transitory computer-readable medium of claim 21, wherein, to determine that the first sensor measurement data and the second sensor measurement data satisfy the at least one batching condition, the instructions, when executed by the one or more processors, cause the one or more processors to determine a known orientation based on the first sensor measurement data and the second sensor measurement data.

### Claim 30 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising instructions that, when executed by the one or more processors, cause the one or more processors to:
obtain third sensor measurement data associated with a third time from the one or more sensors of the device, the third time occur after the second time;
obtain fourth sensor measurement data associated with a fourth time from the one or more sensors of the device, the fourth time occur after the third time;
determine, by the data batching engine, that the third sensor measurement data and the fourth sensor measurement data satisfy an additional batching condition;
based on determine that the third sensor measurement data and the fourth sensor measurement data satisfy the additional batching condition, generate an additional sensor measurement data batch including the third sensor measurement data, the fourth sensor measurement data, and at least an additional target sensor measurement data between the third time and the fourth time; and
output the additional sensor measurement data batch.
