Systems and methods for selectively capturing sensor data of an autonomous vehicle using a sensor guide rail
US-10782689-B2 · Sep 22, 2020 · US
US11422246B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11422246-B2 |
| Application number | US-201916407062-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 8, 2019 |
| Priority date | May 8, 2019 |
| Publication date | Aug 23, 2022 |
| Grant date | Aug 23, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Provided herein is a system and method for determining whether a sensor is calibrated and error handling of an uncalibrated sensor. The system comprises a sensor system comprising a sensor and an analysis engine configured to determine whether the sensor is uncalibrated. The system further comprises an error handling system configured to perform an error handling in response to the sensor system determining that the sensor is uncalibrated. The method comprises determining, by a sensor system, whether the sensor is uncalibrated, and performing, by an error handling system, an error handling in response to the sensor system determining that the sensor is uncalibrated.
Opening claim text (preview).
What is claimed is: 1. A system comprising: a sensor; and one or more processors configured to: determine whether the sensor is uncalibrated based on sensor parameters or a comparison of a proportion of features from data captured by the sensor and historical data at a same location, wherein the sensor parameters comprising any of a skew, a depth of field, an angle of view, a beam angle, an aspect ratio, and a pixel number; perform a first recalibration in response to determining that the sensor is uncalibrated; determine whether the sensor is validated after the first recalibration; in response to determining that the sensor is not validated after the first recalibration: determine whether to perform a second recalibration based on an amount of sensor error before the first recalibration, an amount of sensor error after the first recalibration, or a difference between the amount of sensor error before the first recalibration and the amount of sensor error after the first recalibration; selectively perform the second recalibration based on the determination of whether to perform the second recalibration; upon determining that the sensor is validated after the first recalibration or the second recalibration, capture sensor data using the sensor after the first recalibration or the second recalibration; and navigate a vehicle using the sensor data. 2. The system of claim 1 , wherein: the one or more processors are further configured to perform: eliminating data determined to be erroneous from the sensor, initiating a backup sensor, or issuing an alert to a user; and saving a result of the first recalibration or the second recalibration of the sensor in a memory. 3. The system of claim 1 , wherein the one or more processors are further configured to select an error handling procedure from one of eliminating data determined to be erroneous, initiating a backup sensor, and issuing an alert to a user, based on a load consumption of the error handling procedure, an amount of availability of a system load, a history of the sensor, an availability of a backup sensor, a density of moving objects detected at the same location, a weather condition at the same location, or an environment condition at the same location. 4. The system of claim 3 , further comprising a memory accessible by the one or more processors, the memory storing one or more results of previous error handling of the sensor, and wherein the selecting of the error handling procedure is based on the one or more results of the previous error handling of the sensor. 5. The system of claim 1 , wherein in response to the one or more processors determining that the sensor is uncalibrated: the one or more processors are further configured to: determine whether the sensor requires immediate recalibration based on an availability of a backup sensor; in response to determining that the sensor does not require immediate recalibration, refrain from recalibrating the sensor until a second sensor is determined to be uncalibrated; and recalibrate the sensor and the second sensor together. 6. The system of claim 1 , wherein the one or more processors are further configured to: determine a probability of the sensor being uncalibrated; and select an error handling procedure from one of eliminating data determined to be erroneous, initiating a backup sensor, and issuing an alert to a user based on the probability of the sensor being uncalibrated. 7. The system of claim 1 , wherein in response to the one or more processors determining that the sensor is not validated after the second recalibration, the one or more processors further perform an error handling procedure. 8. The system of claim 1 , wherein the determining of whether the sensor is validated is based on a known parameter of the sensor or of historical data or second data captured at a different time or from a second sensor. 9. An error handling method for a sensor of a system, performed by one or more processors, the error handling method comprising: determining whether the sensor is uncalibrated based on sensor parameters or a comparison of a proportion of features from data captured by the sensor and historical data at a same location, wherein the sensor parameters comprising any of a skew, a depth of field, an angle of view, a beam angle, an aspect ratio, and a pixel number; and performing a first recalibration in response to determining that the sensor is uncalibrated; determining whether the sensor is validated after the first recalibration; in response to determining that the sensor is not validated after the first recalibration: determining whether to perform a second recalibration based on an amount of sensor error before the first recalibration, an amount of sensor error after the first recalibration, or a difference between the amount of sensor error before the first recalibration and the amount of sensor error after the first recalibration; selectively performing the second recalibration based on the determination of whether to perform the second recalibration; upon determining that the sensor is validated after the first recalibration or the second recalibration, capturing sensor data using the sensor after the first recalibration or the second recalibration; and navigating a vehicle using the sensor data. 10. The method of claim 9 , further comprising performing: eliminating data determined to be erroneous from the sensor, initiating a backup sensor to operate, or issuing an alert to a user; and saving a result of the first recalibration or the second recalibration of the sensor in a memory. 11. The method of claim 9 , further comprising: selecting an error handling procedure from one of eliminating data determined to be erroneous, initiating a backup sensor, and issuing an alert to a user based on a load consumption of the error handling procedure, an amount of availability of a system load, a history of the sensor, an availability of a backup sensor, a density of moving objects detected at the same location, a weather condition at the same location, or an environment condition at the same location. 12. The method of claim 9 , further comprising: accessing a memory storing one or more results of a previous error handling of the sensor and selecting an error handling procedure based on the one or more results of the previous error handling of the sensor. 13. The method of claim 9 , further comprising: in response to determining that the sensor is uncalibrated: determining whether the sensor requires immediate recalibration based on an availability of a backup sensor; in response to determining that the sensor does not require immediate recalibration, refraining from recalibrating the sensor until a second sensor is determined to require recalibration; and recalibrating the sensor and the second sensor together. 14. The method of claim 9 , further comprising: determining a probability of the sensor being uncalibrated; and selecting an error handling procedure from one of eliminating data determined to be erroneous, initiating a backup sensor, and issuing an alert to a user based on the probability of the sensor being uncalibrated. 15. The method of claim 9 , further comprising, in response to determining that the sensor is not validated after the second recalibration, performing an error handling procedure. 16. The method of claim 9 , wherein the determining of whether the sensor is validated is based on a known parameter of the sensor or of historical data or second data captured at a different time or from a second sensor.
specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title
of land vehicles · CPC title
Means for monitoring or calibrating · CPC title
Means for monitoring or calibrating (short-range imaging G01S7/5205) · CPC title
Alignment of sensor · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.