SAFETY INFERENCE ENGINE FOR AUTONOMOUS SYSTEMS

• US 20190047580A1
• Filed: 12/27/2017
• Published: 02/14/2019
• Est. Priority Date: 12/27/2017
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Kwasnick, Robert F., Le, Huy
• Granted Patent: US 10,513,272 B2
• Time in Patent Office: Days
• CPC Class Codes: B60W 2050/0215 Sensor drifts or sensor failures
• CPC Class Codes: B60W 2050/0292 Fail-safe or redundant systems, e.g. limp-home or backup systems
• CPC Class Codes: B60W 50/0205 Diagnosing or detecting failures; Failure detection models
• CPC Class Codes: G05D 1/00 Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots drive control systems specially adapted for autonomous road vehicles B60W60/00
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction

Abstract

Various systems and methods for monitoring integrate circuits for failure are described herein. A system to monitor for potential component failure includes a sensor array interface to obtain a first safety level from a first sensor and a second safety level from a second sensor, the first and second sensors installed in a machine, the first and second safety levels indicating how safe the machine is to operate; and a processor to: obtain configuration parameters from a rule data store; combine the first and second safety levels using the configuration parameters to produce a composite safety level; and initiate a responsive action based on the composite safety level.

Claims

1. A system to monitor for potential component failure, the system comprising:

a sensor array interface to obtain a first safety level from a first sensor and a second safety level from a second sensor, the first and second sensors installed in a machine, the first and second safety levels indicating how safe the machine is to operate; and

a processor to;

obtain configuration parameters from a rule data store;

combine the first and second safety levels using the configuration parameters to produce a composite safety level; and

initiate a responsive action based on the composite safety level.

2. The system of claim 1, wherein the machine comprises an autonomous vehicle.

3. The system of claim 1, wherein the first sensor is a visible light camera, an acoustic sensor, a laser scanner, or a radar.

4. The system of claim 1, wherein the first sensor comprises a system monitor to monitor a component of the machine, and wherein the first safety level is based on a deviation from normal operation of the component.

5. The system of claim 1, wherein the first safety level is an enumerated value within a range of values.

6. The system of claim 3, wherein the range of values is from 1 to 5, where lower numbers indicate safer operation and higher numbers indicate more unsafe operation of the machine.

7. The system of claim 1, wherein the first safety level is based on a measure of stress or wear of an integrated circuit that the first sensor is monitoring.

8. The system of claim 1, wherein the first safety level is based on a calculation drift of an integrated circuit that the first sensor is monitoring.

9. The system of claim 1, wherein the first safety level is based on an error rate of an integrated circuit that the first sensor is monitoring.

10. The system of claim 1, wherein the configuration parameters include a first weight and a second weight, the first and second weights for use in a weighted formula with the respective first and second safety levels.

11. The system of claim 1, wherein the configuration parameters include a set of thresholds to use in a decision tree.

12. The system of claim 1, wherein the configuration parameters include a set of weights to use as artificial neuron values in a machine-learning technique.

13. The system of claim 1, wherein to combine the first and second safety levels, the processor is to:

use a maximum function to set the composite safety level equal to the highest safety level of the first and second safety levels.

14. The system of claim 1, wherein to combine the first and second safety levels, the processor is to:

use a weighted function to set the composite safety level, each of the first and second safety levels weighted by a respective first and second weight.

15. The system of claim 1, wherein to initiate the response action, the processor is to:

determine that the composite safety level indicates a warning level; and

initiate the presentation of a warning to an operator of the machine.

16. The system of claim 1, wherein to initiate the response action, the processor is to:

determine that the composite safety level indicates a high safety impact level; and

initiate a safe operation mode of the machine.

17. The system of claim 1, wherein to initiate the response action, the processor is to:

determine that the composite safety level indicates a critical safety impact level; and

initiate an autonomous operation mode of the machine.

18. The system of claim 17, wherein to initiate the autonomous operation mode, the processor is to:

designate a destination of the machine; and

cause the machine to autonomously navigate to the destination for service.

19. The system of claim 18, wherein the destination comprises a service station.

20. The system of claim 18, wherein the destination comprises a shoulder of a road, and wherein to cause the machine to autonomously navigate to the destination, the processor is to:

cause the machine to pull over to the shoulder; and

cause the machine to initiate a call for assistance.

21. A method for monitoring for potential component failure, the method comprising:

obtaining a first safety level from a first sensor and a second safety level from a second sensor, the first and second sensors installed in a machine, the first and second safety levels indicating how safe the machine is to operate;

obtaining configuration parameters from a rule data store;

combining the first and second safety levels using the configuration parameters to produce a composite safety level; and

initiating a responsive action based on the composite safety level.

22. The method of claim 21, wherein initiating the response action comprises:

determining that the composite safety level indicates a high safety act level; and

initiating a safe operation mode of the machine.

23. The method of claim 21, wherein initiating the response action comprises:

determining that the composite safety level indicates a critical safety impact level; and

initiating an autonomous operation mode of the machine.

24. At least one machine-readable medium including instructions for monitoring for potential component failure, the instructions when executed by a machine, cause the machine to perform operations comprising:

obtaining a first safety level from a first sensor and a second safety level from a second sensor, the first and second sensors installed in a machine, the first and second safety levels indicating how safe the machine is to operate;

obtaining configuration parameters from a rule data store;

combining the first and second safety levels using the configuration parameters to produce a composite safety level; and

initiating a responsive action based on the composite safety level.

25. The machine-readable medium of claim 24, wherein the configuration parameters include a set of thresholds to use in a decision tree.