Systems and methods for dynamic data mining during data collection missions

Patent metadata

Field	Value
Publication number	US-12195031-B2
Application number	US-202217654247-A
Country	US
Kind code	B2
Filing date	Mar 10, 2022
Priority date	Mar 10, 2022
Publication date	Jan 14, 2025
Grant date	Jan 14, 2025

Abstract

Disclosed herein are systems, methods, and computer program products for controlling data collection by resources. The methods comprise: receiving real-world data collected by the resources in accordance with data collection mission (DCM) parameters; receiving user defined DCM goal(s); updating goal(s) for DCM mission(s) based on the real-world data and the user defined DCM goal(s); modifying the data DCM parameter(s) based on the updated goal(s) and which ones of the resources are still available for DCMs; and causing data collection operations (which are currently being performed by the resource(s)) to change in accordance with the modified DCM parameter(s).

First claim

What is claimed is:

1. A method for controlling data collection by a plurality of resources, comprising:
receiving, by a computing device, real-world data collected by the plurality of resources in accordance with data collection mission parameters, the data collection mission parameters comprising at least one of a first parameter being a target object type and a second parameter being a number of target objects for the target object type for which data is to be collected;
receiving, by the computing device, a user defined data collection mission goal;
updating, by the computing device, a goal for a data collection mission based on the real-world data and the user defined data collection mission goal, the goal being collection of data associated with a particular target object type of a plurality of different target object types;
modifying, by the computing device, at least one of the first and second parameters of the data collection mission parameters based on the updated goal for the data collection mission and which ones of the plurality of resources are still available for data collection missions; and
causing, by the computing device, data collection operations which are currently being performed by at least one of the plurality of resources to change in accordance with the at least one parameter of the data collection mission parameters which was modified.

2. The method according to claim 1 , further comprising using the real-world data collected by the plurality of resources to (i) train a machine learning model to detect objects in perception data or (ii) generate a map.

3. The method according to claim 2 , further comprising using at least one of the machine learning model or map to control movement of an autonomous vehicle.

4. The method according to claim 1 , wherein the goal for the data collection mission is updated by generating at least one value representing a difference between one of the first and second parameters of the data collection mission parameters and a third parameter specified in the user defined data collection mission goals.

5. The method according to claim 4 , further comprising generating a score based on the at least one value.

6. The method according to claim 5 , wherein the at least one value is weighted relative to at least one other value representing a difference between a fourth parameter of the data collection mission parameters and a fifth parameter specified in the user defined data collection mission goals.

7. The method according to claim 5 , further comprising generating a prioritization of the plurality of different target object types based on the score.

8. The method according to claim 7 , further comprising dividing target objects between the plurality of resources based on at least the prioritization.

9. The method according to claim 8 , wherein the at least one of the first and second parameters of the data collection mission parameters is modified in accordance with the dividing.

10. A system, comprising:
a processor;
a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for controlling data collection by a plurality of resources, wherein the programming instructions comprise instructions to:
receive real-world data collected by the plurality of resources in accordance with data collection mission parameters, the data collection mission parameters comprising at least one of a first parameter being a target object type and a second parameter being a number of target objects for the target object type for which data is to be collected;
receive a user defined data collection mission goal;
update a goal for a data collection mission based on the real-world data and the user defined data collection mission goal, the goal being collection of data associated with a particular target object type of a plurality of different target object types;
modify at least one of the first and second parameters of the data collection mission parameters based on the updated goal for the data collection mission and which ones of the plurality of resources are still available for data collection missions; and
cause data collection operations which are currently being performed by at least one of the plurality of resources to change in accordance with the at least one parameter of the data collection mission parameters which was modified.

11. The system according to claim 10 , wherein the goal for the data collection mission is updated by generating at least one value representing a difference between one of the first and second parameters of the data collection mission parameters and a third parameter specified in the user defined data collection mission goals.

12. The system according to claim 11 , wherein the programming instructions comprise instructions to generate a score based on at least one of the at least one value and a total number of targets for all target object types for which data is be collected.

13. The system according to claim 12 , wherein the at least one value is weighted relative to at least one other value representing a difference between a fourth parameter of the data collection mission parameters and a fifth parameter specified in the user defined data collection mission goals.

14. The system according to claim 12 , wherein the programming instructions comprise instructions to:
generate a prioritization of a plurality of different target object types based on the score;
divide target objects between the plurality of resources based on at least the prioritization; and
modify at least one of the first and second parameters of the data collection mission parameters in accordance with how the target objects are divided between the plurality of resources.

15. The system according to claim 10 , wherein the programming instructions comprise instructions to use the real-world data collected by the plurality of resources to (i) train a machine learning model to detect objects in perception data or (ii) generate a map.

16. The system according to claim 15 , wherein the programming instructions comprise instructions to use at least one of the machine learning model or map to control movement of an autonomous vehicle.

17. A non-transitory computer-readable medium that stores instructions that is configured to, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
receiving real-world data collected by the plurality of resources in accordance with data collection mission parameters, the data collection mission parameters comprising at least one of a first parameter being a target object type and a second parameter being a number of target objects for the target object type for which data is to be collected;
receiving a user defined data collection mission goal;
updating a goal for a data collection mission based on the real-world data and the user defined data collection mission goal, the goal being collection of data associated with a particular target object type of a plurality of different target object types;
modifying at least one of the first and second parameters of the data collection mission parameters based on the updated goal for the data collection mission and which ones of the plurality of resources are still available for data collection missions; and
causing data collection operations which are currently being performed by at least one of the plurality of resources to change in accordance with the at least one parameter of the data collection mis

Assignees

• Argo Ai Llc
• Volkswagen Group Of America Invest Llc

Inventors

• Swanson Kevin
• Attard Christopher
• Puchalski Matthew
• Swartz Daniel

Classifications

• G06F16/26

  Visual data mining; Browsing structured data · CPC title

• G06N20/00

  Machine learning · CPC title

• B60W50/06

  Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot · CPC title

• B60W60/00 Primary

  Drive control systems specially adapted for autonomous road vehicles · CPC title

• G06V20/58 Primary

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title