Vehicle data health monitoring and recording system for multi-layer control software architecture

Patent metadata

Field	Value
Publication number	US-12304511-B2
Application number	US-202218063250-A
Country	US
Kind code	B2
Filing date	Dec 8, 2022
Priority date	Dec 8, 2022
Publication date	May 20, 2025
Grant date	May 20, 2025

Abstract

A data health monitoring and recording system for a vehicle includes a data recording infrastructure and one or more controllers. The one or more controllers include a multi-layer control software architecture including two or more software layers. The one or more controllers execute instructions to monitor, by a health monitoring structure that is part of the multi-layer control software architecture, one or more parameters calculated by each of the two or more software layers. The one or more controllers compare a respective parameter of a respective software layer with a predetermined corresponding performance metric for a required time horizon. In response to determining the respective parameter of the respective software layer does not meet the predetermined corresponding performance metric for the required time horizon, a trigger that instructs the data recording infrastructure to record the parameters calculated by each of the two or more software layers is generated.

First claim

What is claimed is:

1. A data health monitoring and recording system for a vehicle, the data health monitoring and recording system comprising:
a data recording infrastructure; and
one or more controllers in electronic communication with the data recording infrastructure, wherein the one or more controllers include a multi-layer control software architecture including two or more software layers, wherein each of the two or more software layers includes a respective control layer and a respective estimator layer, the one or more controllers executing instructions to:
monitor, by a health monitoring structure that is part of the multi-layer control software architecture, one or more parameters calculated by each of the two or more software layers, wherein the health monitoring structure includes a control health monitoring layer corresponding to each of the respective control layers and an estimator health monitoring layer corresponding to each of the respective estimator layers;
compare a respective parameter calculated by a respective software layer with a predetermined corresponding performance metric for a required time horizon;
in response to determining the respective parameter of the respective software layer does not meet the predetermined corresponding performance metric for the required time horizon, generate a trigger that instructs the data recording infrastructure to record the parameters calculated by each of the two or more software layers, wherein the trigger corresponding to the control health monitoring layer is determined based on a type of control system that receives the one or more parameters calculated by each of the two or more software layers; and
record, by the data recording infrastructure, the parameters calculated by each of the two or more software layers that are part of the multi-layer control software architecture to trace a fault that propagates though the multi-layer control software architecture;

wherein each of the respective control layers calculates a target action based on data indicative of a dynamic state of the vehicle;
wherein a global control layer of the two or more software layers calculates one or more parameters that indicate the target action that the vehicle executes at a global control point.

2. The data health monitoring and recording system of claim 1 , wherein the type of the control system that receives the one or more parameters is a feedback system.

3. The data health monitoring and recording system of claim 2 , wherein the trigger is determined based on one of a target response and a reference signal.

4. The data health monitoring and recording system of claim 3 , wherein the target response indicates a target vehicle state and the reference signal indicates a reference command.

5. The data health monitoring and recording system of claim 1 , wherein the type of the control system that receives the one or more parameters is a feedforward system.

6. The data health monitoring and recording system of claim 5 , wherein the trigger is determined based on an expected behavior.

7. The data health monitoring and recording system of claim 6 , wherein the expected behavior is determined based on one or more of the following: a vehicle state estimate, a wheel state estimate, and one or more environmental parameters.

8. The data health monitoring and recording system of claim 1 , wherein the trigger corresponding to the estimator health monitoring layer is determined based on a physics-based model including one or more equations that solves for the one or more parameters estimated by the respective estimator layer.

9. The data health monitoring and recording system of claim 8 , wherein the physics-based model is a lateral velocity estimation model that combines a drift-type fault detection model and a bias-type fault detection model together.

10. The data health monitoring and recording system of claim 1 , wherein the trigger corresponding to the estimator health monitoring layer is determined based on a machine learning model.

11. The data health monitoring and recording system of claim 10 , wherein the machine learning model receives a plurality of inputs and a reference signal, and wherein the plurality of inputs are employed by the machine learning model to calculate the reference signal and the reference signal represents one of the one or more parameters estimated by the respective estimator layer.

12. The data health monitoring and recording system of claim 1 , wherein the trigger corresponding to the estimator health monitoring layer is determined based on a combination of a physics-based model and a machine learning model together, wherein the physics-based model is employed as a constraint on a reference signal received by the machine learning model.

13. The data health monitoring and recording system of claim 1 , wherein the one or more parameters that indicate the target action at the global control point include one or more of the following: target longitudinal acceleration, target longitudinal velocity, target slip tracking, target lateral acceleration, target velocity, and target yaw rate tracking.

14. A method for monitoring a multi-layer control software architecture of one or more controllers that are part of a monitoring and recording system for a vehicle, the method comprising:
monitoring, by a health monitoring structure that is part of the multi-layer control software architecture, one or more parameters calculated by each of two or more software layers that are part of the multi-layer control software architecture of the one or more controllers, wherein each of the two or more software layers includes a respective control layer and a respective estimator layer, and wherein the health monitoring structure includes a control health monitoring layer corresponding to each of the respective control layers and an estimator health monitoring layer corresponding to each of the respective estimator layers;
comparing a respective parameter of a respective software layer with a predetermined corresponding performance metric for a required time horizon; and
in response to determining the respective parameter of the respective software layer does not meet the predetermined corresponding performance metric for the required time horizon, generating a trigger that instructs a data recording infrastructure to record the parameters calculated by each of the two or more software layers, wherein the trigger corresponding to the control health monitoring layer is determined based on a type of control system that receives the one or more parameters calculated by each of the two or more software layers; and
recording, by the data recording infrastructure, the parameters calculated by each of the two or more software layers that are part of the multi-layer control software architecture to trace a fault that propagates though the multi-layer control software architecture;
wherein each of the respective control layers calculates a target action based on data indicative of a dynamic state of the vehicle;
wherein a global control layer of the two or more software layers calculates one or more parameters that indicate the target action that the vehicle executes at a global control point.

15. A data health monitoring and recording system for a vehicle, the data health monitoring and recording system comprising:
a data recording infrastructure; and
one or more controllers in electronic communication with the data recording infrastructure, wherein the one or more controllers include a multi-layer control software architecture including two or more software layers, and wherein eac

Assignees

• Gm Global Tech Operations Llc

Inventors

• Kasaiezadeh Mahabadi SeyedAlireza
• Long Ruixing
• Askari Hassan
• Mashrouteh Shamim
• Kapoor Saurabh
• Mehrabi Naser
• Abolhassani Amir
• Ataei Mansour

Classifications

• B60W40/02

  related to ambient conditions · CPC title

• G07C5/0808 Primary

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• B60W2556/45

  External transmission of data to or from the vehicle · CPC title

• B60W50/0205

  Diagnosing or detecting failures; Failure detection models · CPC title

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title