Intelligent logging

• US 9,805,527 B2
• Filed: 01/13/2016
• Issued: 10/31/2017
• Est. Priority Date: 01/13/2016
• Status: Active Grant

• Current Assignee: Audi AG (Volkswagen AG), Volkswagen AG
• Original Assignee: Audi AG (Volkswagen AG), Volkswagen AG
• Inventors: Gupta, Somudro
• Primary Examiner(s): ARTHUR JEANGLAUDE, GERTRUDE
• Application Number:
  US14/994,897
• Publication Number:
  US 20170200330A1
• Time in Patent Office: 657 Days
• Field of Search: 701 334, 701 36, 701 336, 701 343
• 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: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0634 by changing the state or mode of one or more devices
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G07C 5/085 using electronic data carriers
• CPC Class Codes: G07C 5/0866 the electronic data carrier being a digital video recorder in combination with video camera

Abstract

An on-board computing system for determining an opportune time to log data into a first memory. A sensor system collects data of a vehicle'"'"'s environment. A controller of the on-board computing system logs the data to a first memory when it determines an opportune time to log data to the first memory. The controller holds data in a second memory if it determines it is not an opportune time to log data into the first memory. The controller resumes logging data to the first memory when an opportune time presents itself.

Claims

1. An on-board computer system for logging sensor data for an autonomous vehicle, the on-board computer system comprising:

a plurality of sensors for monitoring sensor data regarding operation of the autonomous vehicle and an environment in which the autonomous vehicle is present;

a processor for analyzing the sensor data; and

a first memory in which the monitored data is stored to log the sensor data received from the plurality of sensors of the autonomous vehicle,

wherein the processor assesses criticality of a current situation for the autonomous vehicle by analyzing the sensor data and determines processing capability of the processor based on the assessment of criticality of the current situation, and

wherein the processor determines whether to log sensor data in the first memory or to, instead, hold sensor data in a second memory until a future time to be determined, wherein the determination to store or hold is based on the determined criticality of the current situation to reduce the load on processing capability of the processor, wherein the first memory is a hard drive and the second memory is a RAM.

2. The on-board computer system of claim 1, wherein the assessment of criticality of the current situation includes analyzing sensor data that indicates a number of objects in a vicinity of the autonomous vehicle.

3. The on-board computer system of claim 2, wherein if the assessment of criticality of the current situation indicates the number of objects in a vicinity of the autonomous vehicle exceed a threshold value of number of objects the processor stops logging data in the first memory and holds sensor data in the second memory until the number of objects fall below the threshold value.

4. The on-board computer system of claim 1, wherein the assessment of criticality of the current situation includes analyzing sensor data that indicates time to collision of the autonomous vehicle.

5. The on-board computer system of claim 4, wherein if the assessment of criticality of the current situation indicates the time to collision of the autonomous vehicle exceeds a threshold value of time to collision the processor will stop logging data in the first memory and begin holding sensor data in the second memory until the time to collision rises above the threshold value.

6. The on-board computer system of claim 1, wherein if the processor determines a collision is imminent the processor will continue to log sensor data in the first memory.

7. The on-board computer system of claim 1, wherein a frequency of the processor logging sensor data varies depending on the assessment of criticality.

8. The on-board computer system of claim 1, wherein the processor determines whether to log sensor data in the first memory or hold sensor data in a second memory until the future time to be determined to log sensor data in the first memory based on an evaluation of the determined criticality of the current situation and the space of the second memory.

9. The on-board computer system of claim 1, wherein the plurality of sensors comprises Lidar technology.

10. The on-board computer system of claim 1, wherein the processor determines whether to log less sensor data if there is a critical amount of space being reached in the second memory.

11. A method of logging sensor data from a plurality of sensors on an autonomous vehicle, the method comprising:

logging sensor data received from the plurality of sensors of the autonomous vehicle, wherein the autonomous vehicle includes a computer coupled to the plurality of sensors to receive the sensor data, and the computer has a first memory, a second memory, and a processor;

assessing of criticality of a current situation for the autonomous vehicle by the processor analyzing the sensor data;

determining processing capability of the processor based on the assessment of criticality of the current situation; and

determining whether to log sensor data in the first memory or to, instead, hold sensor data in the second memory until a future time to be determined, wherein determining to store or hold is based on the determined criticality of the current situation to reduce the load on processing capability of the processor, wherein the first memory is a hard drive and the second memory is a RAM.

12. The method of claim 11, wherein the assessment of criticality of the current situation includes analyzing sensor data that indicates a number of objects in a vicinity of the autonomous vehicle.

13. The method of claim 12, wherein if the assessment of criticality of the current situation indicates the number of objects in a vicinity of the autonomous vehicle exceed a threshold value of number of objects the processor will stop logging data in the first memory and begin holding sensor data in the second memory until the number of objects fall below the threshold value.

14. The method of claim 11, wherein the assessment of criticality of the current situation includes analyzing sensor data that indicates time to collision of the autonomous vehicle.

15. The method of claim 14, wherein if the assessment of criticality of the current situation indicates the time to collision of the autonomous vehicle exceeds a threshold value of time to collision the processor will stop logging data in the first memory and begin holding sensor data in the second memory until the time to collision rises above the threshold value.

16. The method of claim 11, wherein if the processor determines a collision is imminent the processor will continue to log sensor data in the first memory.

17. The method of claim 11, wherein a frequency of the processor logging sensor data varies depending on the assessment of criticality.

18. The method of claim 11, wherein the processor determines whether to log sensor data in the first memory or hold sensor data in a second memory until the future time to log sensor data in the first memory based on an evaluation of the determined criticality of the current situation and the space of the second memory.

19. The method of claim 11, wherein the plurality of sensors comprises Lidar technology.

20. The method of claim 11, wherein the processor determines whether to log less sensor data if there is a critical amount of space being reached in the second memory.