Method to dynamically determine vehicle effective sensor coverage for autonomous driving application

Patent metadata

Field	Value
Publication number	US-11016489-B2
Application number	US-201916252154-A
Country	US
Kind code	B2
Filing date	Jan 18, 2019
Priority date	Jan 18, 2019
Publication date	May 25, 2021
Grant date	May 25, 2021

Abstract

Systems and methods are disclosed for dynamically adjusting effective sensor coverage coordinates of a sensor used to assist in navigating an autonomous driving vehicle (ADV) in response to environmental conditions that may affect the ideal operation of the sensor. An ADV includes a navigation system and a safety monitor system that monitors some, or all, of the navigation system, including monitoring: dynamic adjustment of effective sensor coverage coordinates of a sensor and localization of the ADV within a high-definition map. The ADV safety monitor system further determines safety-critical objects surrounding the ADV, determines safe areas to navigate the ADV, and ensures that the ADV navigates only to safe areas. An automated system performance monitor determines whether to pass-through ADV navigation control commands, limit one or more control commands, or perform a fail-operational behavior, based on the ADV safety monitor systems.

First claim

What is claimed is:

1. A computer-implemented method of dynamically adjusting effective sensor coverage coordinates of a first sensor in an autonomous driving vehicle (ADV), the method comprising:
determining a list of one or more objects surrounding the ADV based on a high-definition (HD) map;
identifying a first static object based on first sensor data of the first sensor, the first sensor having coordinates representing an effective coverage area of the first sensor, the coordinates stored in a memory of the ADV, in association with the first sensor;
in response to determining that the identified first static object matches one of the one or more objects in the HD map and determining that the first static object is located outside of the effective sensor coverage coordinates of the first sensor, increasing, by fail-operational logic in a navigation system of the ADV, the effective sensor coverage coordinates of the first sensor to include a location of the first static object and storing the increased effective sensor coverage area coordinates in association with the first sensor, in a storage of the ADV; and
navigating the ADV to avoid the first static object in view of the increased effective sensor coverage coordinates of the first sensor.

2. The method of claim 1 , wherein determining a list of one or more objects surrounding the ADV comprises at least one of:
locating the one or more objects in the HD map surrounding a path of the ADV;
locating the one or more objects using sensor data from a plurality of ADV sensors; or
maintaining a list of one or more objects that comprises objects whose location has been verified and the objects are being tracked, and/or objects whose location verification is pending.

3. The method of claim 1 , further comprising:
in response to determining that the first static object identified by the first sensor does not match any of the one or more objects in the HD map:
identifying the first static object from second sensor data of a second sensor;
in response to determining that the first static object identified from the second sensor data is located inside the effective sensor coverage coordinates of the first sensor, reducing the sensor effective coverage coordinates of the first sensor to exclude the location of the first static object.

4. The method of claim 1 , wherein increasing the effective sensor coverage coordinates of the first sensor to include the location of the first static object comprises: setting the effective sensor coverage coordinates to a default setting of the effective sensor coverage coordinates for the first sensor.

5. The method of claim 1 , wherein the first sensor comprises a camera or a LIDAR system.

6. The method of claim 1 , wherein the increased effective sensor coverage coordinates of the first sensor are stored in a memory in association with the first sensor.

7. The method of claim 1 , wherein the effective sensor coverage coordinates of the first sensor are retrieved from a memory, prior to determining that the first static object is located outside of the effective sensor coverage coordinates of the first sensor.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for dynamically adjusting effective sensor coverage coordinates of a first sensor in an autonomous driving vehicle (ADV), the operations comprising:
determining a list of one or more objects surrounding the ADV based on a high definition (HD) map;
identifying a first static object based on first sensor data of the first sensor, the first sensor having coordinates representing an effective coverage area of the first sensor, the coordinates stored in a memory of the ADV, in association with the first sensor;
in response to determining that the identified first static object matches one of the one or more objects in the HD map, and determining that the first static object is located outside of the effective sensor coverage coordinates of the first sensor, increasing, by fail-operational logic in a navigation system of the ADV, the effective sensor coverage coordinates of the first sensor to include a location of the first static object and storing the increased effective sensor coverage area coordinates in association with the first sensor, in a storage of the ADV; and
navigating the ADV to avoid the first static object in view of the increased sensor coverage of the first sensor.

9. The medium of claim 8 , wherein determining a list of one or more objects surrounding the ADV comprises at least one of:
locating the one or more objects in the HD map surrounding a path of the ADV;
locating the one or more objects using sensor data from a plurality of ADV sensors; or
maintaining a list of one or more objects that comprises objects whose location has been verified and the objects are being tracked, and/or objects whose location verification is pending.

10. The medium of claim 8 , the operations further comprising:
in response to determining that the first static object identified by the first sensor does not match one of the one or more objects in the HD map:
identifying the first static object from second sensor data of a second sensor;
in response to determining that the first static object identified from the second sensor data is located inside the effective sensor coverage coordinates of the first sensor, reducing the sensor effective coverage coordinates of the first sensor to exclude the location of the first static object.

11. The medium of claim 8 , wherein increasing the effective sensor coverage coordinates of the first sensor to include the location of the first static object comprises setting the effective sensor coverage coordinates to a default setting of the effective sensor coverage coordinates.

12. The medium of claim 8 , wherein the first sensor comprises a camera or a LIDAR system.

13. The medium of claim 8 , wherein the increased effective sensor coverage coordinates of the first sensor are stored in association with the first sensor.

14. The medium of claim 8 , wherein the effective sensor coverage coordinates of the first sensor are retrieved from a memory, prior to determining that the first static object is located outside of the effective sensor coverage coordinates of the first sensor.

15. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations for dynamically adjusting effective sensor coverage coordinates of a first sensor in an autonomous driving vehicle (ADV), the operations including:
determining a list of one or more objects surrounding the ADV based on a high-definition (HD) map;
identifying a first static object based on first sensor data of the first sensor, the first sensor having coordinates representing an effective coverage area of the first sensor, the coordinates stored in a memory of the ADV, in association with the first sensor;
in response to determining that the identified first static object matches one of the one or more objects in the HD map and determining that the first static object is located outside of the effective sensor coverage coordinates of the first sensor, increasing, by fail-operational logic in a navigation system of the ADV, the effective sensor coverage coordinates of the first sensor to include a location of the first static object and storing the increased effective sensor coverage area coordinates in association with the first sensor, in a storage of the ADV; a

Assignees

• Baidu Usa Llc

Inventors

• Liu Xiaodong
• Qu Ning

Classifications

• G05D1/0231

  using optical position detecting means (position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16) · CPC title

• G05D2201/0213

  Physics · mapped topic

• G05D1/0276

  using signals provided by a source external to the vehicle (involving a plurality of vehicles G05D1/0287; automatically controlling vehicle speed responsive to externally generated signals B60K31/0058) · CPC title

• G05D1/0212 Primary

  with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287) · CPC title

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title