Detecting anomalies online using histograms of controller processing activity

• US 10,545,814 B2
• Filed: 02/19/2019
• Issued: 01/28/2020
• Est. Priority Date: 07/25/2017
• Status: Active Grant

• Current Assignee: Aurora Labs Limited
• Original Assignee: Aurora Labs Limited
• Inventors: Fox, Zohar
• Primary Examiner(s): Dao, Thuy
• Application Number:
  US16/279,213
• Publication Number:
  US 20190179626A1
• Time in Patent Office: 343 Days
• CPC Class Codes: B60W 2050/021 Means for detecting failure or malfunction
• CPC Class Codes: B60W 50/02 Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
• CPC Class Codes: B60W 50/0205 Diagnosing or detecting failures; Failure detection models
• CPC Class Codes: B60W 50/0225 Failure correction strategy
• CPC Class Codes: B60W 50/04 Monitoring the functioning of the control system
• CPC Class Codes: B60W 50/045 Monitoring control system parameters
• CPC Class Codes: G06F 11/0721 within a central processing unit [CPU]
• CPC Class Codes: G06F 11/0751 Error or fault detection not based on redundancy power supply failures G06F1/30; network fault management H04L41/06
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06F 11/1433 during software upgrading
• CPC Class Codes: G06F 11/1629 Error detection by comparing the output of redundant processing systems
• CPC Class Codes: G06F 11/3612 by runtime analysis performance monitoring G06F11/3466
• CPC Class Codes: G06F 12/0284 Multiple user address space allocation, e.g. using different base addresses interprocessor communication G06F15/163
• CPC Class Codes: G06F 12/0646 Configuration or reconfiguration
• CPC Class Codes: G06F 16/188 Virtual file systems
• CPC Class Codes: G06F 21/57 Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
• CPC Class Codes: G06F 21/572 Secure firmware programming, e.g. of basic input output system [BIOS]
• CPC Class Codes: G06F 21/577 Assessing vulnerabilities and evaluating computer system security
• CPC Class Codes: G06F 2212/1008 Correctness of operation, e.g. memory ordering
• CPC Class Codes: G06F 2212/1044 : Space efficiency improvement
• CPC Class Codes: G06F 2212/1056 : Simplification
• CPC Class Codes: G06F 2221/033 : Test or assess software
• CPC Class Codes: G06F 8/60 : Software deployment
• CPC Class Codes: G06F 8/65 : Updates security arrangements therefor G06F21/57
• CPC Class Codes: G06F 8/654 : using techniques specially adapted for alterable solid state memories, e.g. for EEPROM or flash memories
• CPC Class Codes: G06F 8/656 : while running
• CPC Class Codes: G06F 8/658 : Incremental updates; Differential updates
• CPC Class Codes: G06F 8/66 : of program code stored in read-only memory [ROM]
• CPC Class Codes: G06F 8/71 : Version control security arrangements therefor G06F21/57; Configuration management
• CPC Class Codes: G06F 9/4401 : Bootstrapping security arrangements therefor G06F21/57
• CPC Class Codes: G06F 9/445 : Program loading or initiating bootstrapping G06F9/4401; security arrangements for program loading or initiating G06F21/57
• CPC Class Codes: G06F 9/44521 : Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
• CPC Class Codes: G06N 20/00 : Machine learning
• CPC Class Codes: Y02D 10/00 : Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Disclosed embodiments relate to identifying Electronic Control Unit (ECU) anomalies in a vehicle. Operations may include monitoring, in the vehicle, data representing real-time processing activity of the ECU; accessing, in the vehicle, historical data relating to processing activity of the ECU, the historical data representing expected processing activity of the ECU; comparing, in the vehicle, the real-time processing activity data with the historical data, to identify at least one anomaly in the real-time processing activity of the ECU; and implementing a control action for the ECU when the at least one anomaly is identified.

Claims

1. A non-transitory computer readable medium including instructions that, when executed by at least one processor, cause the at least one processor to perform operations for identifying controller anomalies, comprising:

monitoring data representing real-time processing activity of a first controller;

accessing historical data relating to processing activity of the first controller, the historical data representing expected processing activity of the first controller;

comparing the real-time processing activity data with the historical data, to identify at least one anomaly in the real-time processing activity of the first controller; and

implementing a control action for the first controller when the at least one anomaly is identified, wherein the control action includes issuing a prompt to adjust the first controller from executing a first version of controller software to a second version of controller software;

wherein the historical data comprises data from a second controller different from the first controller, and

wherein the first version of controller software includes position-independent code, and the first controller is configured to utilize the position-independent code without requiring modification to the first version of controller software.

2. The non-transitory computer readable medium of claim 1, wherein the first version of controller software is mapped to a plurality of functional units, and the first controller is configured to utilize a virtual file system (VFS) to manage and track one or more versions of each of the plurality of functional units.

3. The non-transitory computer readable medium of claim 2, wherein adjusting the first controller from executing the first version of controller software to the second version of controller software comprises:

updating memory addresses of one or more functional units managed by the VFS based on a delta file corresponding to the second version of controller software.

4. The non-transitory computer readable medium of claim 1, wherein the second controller is comparable to the first controller.

5. The non-transitory computer readable medium of claim 4, wherein the second controller is comparable based on control functions of the first and second controllers.

6. The non-transitory computer readable medium of claim 4, wherein the second controller is comparable based on rules associated with the first version of controller software and rules associated with the second version of controller software.

7. The non-transitory computer readable medium of claim 1, wherein the historical data comprises a machine-learning model or map.

8. The non-transitory computer readable medium of claim 1, wherein the control action comprises activating a safe mode for the first controller.

9. The non-transitory computer readable medium of claim 1, the operations further comprising:

determining a controller operation to have run more than a threshold number of times within a pre-determined time interval.

10. A system for identifying controller anomalies, the system comprising:

one or more processors; and

one or more memories having instructions that, when executed by the one or more processors, cause the one or more processors to perform the operations of;

monitoring data representing real-time processing activity of a first controller;

accessing historical data relating to processing activity of the first controller, the historical data representing expected processing activity of the first controller;

comparing the real-time processing activity data with the historical data, to identify at least one anomaly in the real-time processing activity of the first controller; and

implementing a control action for the first controller when the at least one anomaly is identified, wherein the control action includes issuing a prompt to adjust the first controller from executing a first version of controller software to a second version of controller software;

wherein the historical data comprises data from a second controller different from the first controller, and

wherein the first version of controller software includes position-independent code, and the first controller is configured to utilize the position-independent code without requiring modification to the first version of controller software.

11. The system of claim 10, wherein the first version of controller software is mapped to a plurality of functional units, and the first controller is configured to utilize a virtual file system (VFS) to manage and track one or more versions of each of the plurality of functional units.

12. The system of claim 11, wherein adjusting the first controller from executing the first version of controller software to the second version of controller software comprises:

updating memory addresses of one or more functional units managed by the VFS based on a delta file corresponding to the second version of controller software.

13. The system of claim 10, wherein the second controller is comparable to the first controller.

14. The system of claim 13, wherein the second controller is comparable based on control functions of the first and second controllers.

15. The system of claim 13, wherein the second controller is comparable based on rules associated with the first version of controller software and rules associated with the second version of controller software.

16. The system of claim 10, wherein the historical data comprises a machine-learning model or map.

17. The system of claim 10, the operations further comprising:

determining a controller operation to have run more than a threshold number of times within a pre-determined time interval.

18. A computer-implemented method for identifying controller anomalies, the method comprising:

monitoring data representing real-time processing activity of a first controller;

accessing historical data relating to processing activity of the first controller, the historical data representing expected processing activity of the first controller;

comparing the real-time processing activity data with the historical data to identify at least one anomaly in the real-time processing activity of the first controller; and

implementing a control action for the first controller when the at least one anomaly is identified, wherein the control action includes issuing a prompt to adjust the first controller from executing a first version of controller software to a second version of controller software;

wherein the historical data comprises data from a second controller different from the first controller, and

wherein the first version of controller software includes position-independent code, and the first controller is configured to utilize the position-independent code without requiring modification to the first version of controller software.