Systems and methods to determine risk distribution based on sensor coverages of a sensor system for an autonomous driving vehicle

Patent metadata

Field	Value
Publication number	US-11702104-B2
Application number	US-202016855283-A
Country	US
Kind code	B2
Filing date	Apr 22, 2020
Priority date	Apr 22, 2020
Publication date	Jul 18, 2023
Grant date	Jul 18, 2023

Abstract

Systems and methods of determining a risk distribution associated with a multiplicity of coverage zones covered by a multiplicity of sensors of an autonomous driving vehicle (ADV) are disclosed. The method includes for each coverage zone covered by at least one sensor of the ADV, obtaining MTBF data of the sensor(s) covering the coverage zone. The method further includes determining a mean time between failure (MTBF) of the coverage zone based on the MTBF data of the sensor(s). The method further includes computing a performance risk associated with the coverage zone based on the determined MTBF of the coverage zone. The method further includes determining a risk distribution based on the computed performance risks associated with the multiplicity of coverage zones.

First claim

What is claimed is:

1. A computer-implemented method of operating an autonomous driving vehicle (ADV) having a plurality of sensors, the method comprising:
for each coverage zone covered by at least one sensor of the plurality of sensors of the ADV, wherein the at least one sensor comprises at least one of: a primary sensor communicating with a primary autonomous driving system (ADS) of the ADV, a redundant sensor communicating with a secondary ADS of the ADV, or a shared sensor communicating with the primary ADS and the secondary ADS,
obtaining mean time between failure (MTBF) data of the at least one sensor covering the coverage zone, wherein the MTBF data of the at least one sensor includes information of an elapsed time between failures of the at least one sensor,
determining an MTBF for the coverage zone based on the MTBF data of the at least one sensor, wherein the MTBF for the coverage zone represents the elapsed time between failures of the at least one sensor covering the coverage zone, and
computing a performance risk associated with the coverage zone based on the determined MTBF for the coverage zone;

determining risk distributions based on the computed performance risks associated with the plurality of coverage zones;
controlling the ADV to move along a route in autonomous driving (AD) mode; and
while controlling the ADV to move along the route in AD mode, for each coverage zone covered by the at least one sensor,
starting an AD mode timer, and
determining whether the AD mode timer reaches the MTBF for the coverage zone.

2. The method of claim 1 , further comprising:
determining whether the MTBF for the coverage zone has timed out; and
in response to determining that the MTBF for the coverage zone has timed out, monitoring performance limitation of the at least one sensor within the coverage zone.

3. The method of claim 2 , further comprising:
determining whether the performance limitation of the at least one sensor is detected;
in response to determining that the performance limitation of the at least one sensor is detected, determining whether the performance limitation is permanent;
in response to determining that the performance limitation is permanent, marking the coverage zone as invalid;
otherwise, in response to determining that the performance limitation is not permanent, marking the coverage zone as valid.

4. The method of claim 1 , wherein the performance risk associated with the coverage zone is a reciprocal of the MTBF for the coverage zone.

5. The method of claim 1 , wherein the at least one sensor comprises a first sensor and a second sensor, and the MTBF for the coverage zone is a product of a MTBF of the first sensor and a MTBF of the second sensor.

6. The method of claim 1 , wherein
the at least one sensor comprises a 360-degree light detection and range (LIDAR) unit, a plurality of cameras, a plurality of side LIDAR units, a forward facing radar unit, a rear facing radar unit, and a redundant forward facing LIDAR unit,
the plurality of cameras and the 360-degree LIDAR unit are only used by a primary autonomous driving system (ADS) of the ADV,
the plurality of side LIDAR units and the forward and rear facing radar units are shared between the primary ADS and a secondary ADS of the ADV, and
the redundant forward facing LIDAR unit is only used by the secondary ADS.

7. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
in a plurality of coverage zones covered by a plurality of sensors of an autonomous driving vehicle (ADV), for each coverage zone covered by at least one sensor of the plurality of sensors of the ADV, wherein the at least one sensor comprises at least one of: a primary sensor communicating with a primary autonomous driving system (ADS) of the ADV, a redundant sensor communicating with a secondary ADS of the ADV, or a shared sensor communicating with the primary ADS and the secondary ADS,
obtaining mean time between failure (MTBF) data of the at least one sensor covering the coverage zone, wherein the MTBF data of the at least one sensor includes information of an elapsed time between failures of the at least one sensor,
determining an MTBF for the coverage zone based on the MTBF data of the at least one sensor, wherein the MTBF for the coverage zone represents the elapsed time between failures of the at least one sensor covering the coverage zone, and
computing a performance risk associated with the coverage zone based on the determined MTBF for the coverage zone;

determining risk distributions based on the computed performance risks associated with the plurality of coverage zones;
controlling the ADV to move along a route in autonomous driving (AD) mode; and
while controlling the ADV to move along the route in AD mode, for each coverage zone covered by the at least one sensor,
starting an AD mode timer, and
determining whether the AD mode timer reaches the MTBF for the coverage zone.

8. The non-transitory machine-readable medium of claim 7 , wherein the operations further comprise:
determining whether the MTBF for the coverage zone has timed out; and
in response to determining that the MTBF for the coverage zone has timed out, monitoring performance limitation of the at least one sensor within the coverage zone.

9. The non-transitory machine-readable medium of claim 8 , wherein the operations further comprise:
determining whether the performance limitation of the at least one sensor is detected;
in response to determining that the performance limitation of the at least one sensor is detected, determining whether the performance limitation is permanent;
in response to determining that the performance limitation is permanent, marking the coverage zone as invalid;
otherwise, in response to determining that the performance limitation is not permanent, marking the coverage zone as valid.

10. The non-transitory machine-readable medium of claim 7 , wherein the performance risk associated with the coverage zone is a reciprocal of the MTBF for the coverage zone.

11. The non-transitory machine-readable medium of claim 7 , wherein the at least one sensor comprises a first sensor and a second sensor, and the MTBF for the coverage zone is a product of a MTBF of the first sensor and a MTBF of the second sensor.

12. The non-transitory machine-readable medium of claim 7 , wherein
the at least one sensor comprises a 360-degree light detection and range (LIDAR) unit, a plurality of cameras, a plurality of side LIDAR units, a forward facing radar unit, a rear facing radar unit, and a redundant forward facing LIDAR unit,
the plurality of cameras and the 360-degree LIDAR unit are only used by a primary autonomous driving system (ADS) of the ADV,
the plurality of side LIDAR units and the forward and rear facing radar units are shared between the primary ADS and a secondary ADS of the ADV, and
the redundant forward facing LIDAR unit is only used by the secondary ADS.

13. 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, the operations including:
in a plurality of coverage zones covered by a plurality of sensors of an autonomous driving vehicle (ADV), for each coverage zone covered by at least one sensor of the plurality of sensors of the ADV, wherein the at least one sensor comprises at least one of: a primary sensor communicating with a primary autonomous driving system (ADS) of the ADV, a redundant sensor c

Assignees

• Baidu Usa Llc

Inventors

• Liu Xiaodong
• Qu Ning

Classifications

• B60W60/0015 Primary

  specially adapted for safety · CPC title

• B60W60/0011

  involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles · CPC title

• B60W60/0025

  specially adapted for specific operations · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G01S7/497 Primary

  Means for monitoring or calibrating · CPC title