Dual path ethernet-based sensor device fault monitoring

Patent metadata

Field	Value
Publication number	US-12552406-B2
Application number	US-202218000206-A
Country	US
Kind code	B2
Filing date	Sep 5, 2022
Priority date	Sep 5, 2022
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

In an embodiment, an autonomous driving vehicle (ADV) processes a set of sensor data concurrently by both a first computing unit and a second computing unit, wherein the set of sensor data is generated by a sensor. The first computing unit formats the set of sensor data into a set of message data. The second computing unit determines whether the set of sensor data indicates a control path fault. The second computing unit reports the control path fault responsive to determining that the set of sensor data indicates the control path fault.

First claim

What is claimed is:

1 . A computer-implemented method for operating an autonomous driving vehicle, the method comprising:
receiving, at both a first computing unit and a second computing unit, a set of sensor data generated by a sensor, wherein the set of sensor data comprises raw data; formatting, by the first computing unit, the raw data into a set of message data; determining, by the second computing unit, whether the set of sensor data indicates a control path fault, the control path fault being independent from the raw data; and reporting, by the second computing unit, the control path fault responsive to determining that the set of sensor data indicates the control path fault.

2 . The method of claim 1 , further comprising:
receiving, at an Ethernet switch, the set of sensor data from the sensor; and transmitting, from the Ethernet switch, the set of sensor data to both the first computing unit and the second computing unit over a dedicated virtual LAN.

3 . The method of claim 2 wherein the autonomous driving vehicle comprises an autonomous driving system that includes the first computing unit, the second computing unit, and the Ethernet switch.

4 . The method of claim 1 , further comprising:
determining, by the first computing unit, whether the set of sensor data indicates a data path fault; and reporting, by the first computing unit, the data path fault based determining that the set of sensor data indicates the data path fault.

5 . The method of claim 4 , wherein the first computing unit reports the data path fault to a central system monitor, and wherein the second computing unit reports the control path fault to the central system monitor.

6 . The method claim 1 , further comprising:
determining, by the second computing unit, whether the set of sensor data indicates a link layer fault; and reporting, by the second computing unit, the link layer fault based determining that the set of sensor data indicates the link layer fault.

7 . The method of claim 1 , further comprising:
generating, by the second computing unit, a set of sensor data statistics in response to evaluating the set of sensor data.

8 . A non-transitory machine-readable medium having instructions stored therein, which when executed by at least one processor comprised in a system, cause the system to:
receive, at both a first computing unit and a second computing unit, a set of sensor data generated by a sensor, wherein the at least one processor comprises the first computing unit and the second computing unit, and wherein the set of sensor data comprises raw data; format, by the first computing unit, the raw data into a set of message data; determine, by the second computing unit, whether the set of sensor data indicates a control path fault, the control path fault being independent from the raw data; and report, by the second computing unit, the control path fault responsive to determining that the set of sensor data indicates the control path fault.

9 . The non-transitory machine-readable medium of claim 8 , wherein the system is further to:
receive, at an Ethernet switch, the set of sensor data from the sensor; and transmit, from the Ethernet switch, the set of sensor data to both the first computing unit and the second computing unit over a dedicated virtual LAN.

10 . The non-transitory machine-readable medium of claim 9 , wherein an autonomous driving system comprises the first computing unit, the second computing unit, and the Ethernet switch.

11 . The non-transitory machine-readable medium of claim 8 , wherein the system is further to:
determine, by the first computing unit, whether the set of sensor data indicates a data path fault; and report, by the first computing unit, the data path fault based determining that the set of sensor data indicates the data path fault.

12 . The non-transitory machine-readable medium of claim 11 , wherein the first computing unit reports the data path fault to a central system monitor, and wherein the second computing unit reports the control path fault to the central system monitor.

13 . The non-transitory machine-readable medium of claim 8 , wherein the system is further to:
determine, by the second computing unit, whether the set of sensor data indicates a link layer fault; and report, by the second computing unit, the link layer fault based determining that the set of sensor data indicates the link layer fault.

14 . The non-transitory machine-readable medium of claim 8 , wherein the system is further to:
generate, by the second computing unit, a set of sensor data statistics in response to evaluating the set of sensor data.

15 . A system comprising:
at least one processing device, comprising:
a first computing unit; and
a second computing unit; and
a memory to store instructions that, when executed by the at least one processing device cause the at least one processing device to:
receive, at both the first computing unit and the second computing unit, a set of sensor data generated by a sensor, wherein the set of sensor data comprises raw data;
format, by the first computing unit, the raw data into a set of message data;
determine, by the second computing unit, whether the set of sensor data indicates a control path fault, the control path fault being independent from the raw data; and
report, by the second computing unit, the control path fault responsive to determining that the set of sensor data indicates the control path fault.

16 . The system of claim 15 , wherein the at least one processing device is further to:
receive, at an Ethernet switch, the set of sensor data from the sensor; and transmit, from the Ethernet switch, the set of sensor data to both the first computing unit and the second computing unit over a dedicated virtual LAN.

17 . The system of claim 16 wherein an autonomous driving system comprises the first computing unit, the second computing unit, and the Ethernet switch.

18 . The system of claim 15 , wherein the at least one processing device is further to:
determine, by the first computing unit, whether the set of sensor data indicates a data path fault; and report, by the first computing unit, the data path fault based determining that the set of sensor data indicates the data path fault.

19 . The system of claim 18 , wherein the first computing unit reports the data path fault to a central system monitor, and wherein the second computing unit reports the control path fault to the central system monitor.

20 . The system of claim 15 , wherein the at least one processing device is further to:
determine, by the second computing unit, whether the set of sensor data indicates a link layer fault; and report, by the second computing unit, the link layer fault based determining that the set of sensor data indicates the link layer fault.

Assignees

• Baidu Usa Llc
• Apollo Intelligent Driving Technology Beijing Co Ltd

Inventors

• Shu Guoli
• Xu Kedong

Classifications

• H04L49/351

  for local area network [LAN], e.g. Ethernet switches · CPC title

• B60W60/001 Primary

  Planning or execution of driving tasks · CPC title

• B60W50/0205 Primary

  Diagnosing or detecting failures; Failure detection models · CPC title