System and method for autonomous vehicle system planning

Patent metadata

Field	Value
Publication number	US-10649457-B2
Application number	US-201715585002-A
Country	US
Kind code	B2
Filing date	May 2, 2017
Priority date	May 2, 2017
Publication date	May 12, 2020
Grant date	May 12, 2020

Abstract

A system includes a processor. The processor is configured to derive one or more partitions of a field based on a vehicle system data via a learning system. The processor is further configured to derive one or more turn features representative of vehicle turns in the field based on the vehicle system via the learning system. The processor is also configured to derive an autonomous vehicle plan based on the partitions of the field and the turn features via a planning system, wherein the autonomous vehicle plan comprises a planned route of the autonomous vehicle in the field.

First claim

The invention claimed is:

1. A system, comprising:
a processor configured to:
derive one or more partitions of a field based on a vehicle system data via a learning system;
derive one or more turn features representative of vehicle turns in the field based on the vehicle system via the learning system;
derive an autonomous vehicle plan based on the partitions of the field and the turn features via a planning system, wherein the autonomous vehicle plan comprises a planned route of the autonomous vehicle in the field, wherein the learning system comprises a forward-chained expert system, a backward-chained expert system, a neural network, a data mining system, a state vector machine (SVM), a decision tree learning system, an association rule learning system, a deep learning system, an inductive logic programming system, a genetic algorithm, or a combination thereof.

2. The system of claim 1 , wherein the vehicle system comprises an agricultural vehicle towing an agricultural implement and the agricultural implement is configured for agricultural operations on the field, and wherein the autonomous vehicle is configured to apply the autonomous vehicle plan for performing the agricultural operations.

3. The system of claim 1 , comprising, deriving an order of operations for the one or more partitions of the field.

4. The system of claim 1 , wherein the one or more partitions of the field comprise one or more headland partitions in the field, one or more interior field partitions, or a combination thereof, and wherein each of the one or more interior field partitions comprise an orientation of rows within each of the one or more field partitions.

5. The system of claim 1 , wherein the processor is configured to derive one or more operational features, one or more driving features, one or more operating patterns, or a combination thereof, via the learning system based on the vehicle system data.

6. The system of claim 5 , wherein the operational features comprise agricultural equipment settings for each of the one or more partitions, wherein the driving features comprise a plurality of rows for each of the one or more partitions, a direction of travel for each of the plurality of rows, a spacing between each of the plurality of rows, a preferred route around an obstacle in the field, or a combination thereof, and wherein the operating patterns comprise a one-way pattern, a gathering pattern, a casting pattern, a spiral pattern, a zig zag pattern, or a combination thereof.

7. The system of claim 1 , comprising a user interface system configured to receive a drawing input from a user, wherein the processor is configured to derive the one or more partitions of a field based on the drawing input via the learning system; and to derive the one or more turn features representative of vehicle turns in the field based on the drawing input via the learning system.

8. The system of claim 1 , comprising a communications system communicatively coupled to the processor, wherein the processor is configured to receive the vehicle system data transmitted during operations of a vehicle in the field.

9. A method, comprising:
deriving one or more partitions of a field based on a vehicle system data via a learning system;
deriving one or more turn features representative of vehicle turns in the field based on the vehicle system via the learning system;
deriving an autonomous vehicle plan based on the partitions of the field and the turn features via a planning system, wherein the autonomous vehicle plan comprises a planned route of the autonomous vehicle in the field, wherein the learning system comprises a forward-chained expert system, a backward-chained expert system, a neural network, a data mining system, a state vector machine (SVM), a decision tree learning system, an association rule learning system, a deep learning system, an inductive logic programming system, a genetic algorithm, or a combination thereof.

10. The method of claim 9 , wherein the vehicle system comprises an agricultural vehicle towing an agricultural implement and the agricultural implement is configured for agricultural operations on the field, and wherein the autonomous vehicle is configured to apply the autonomous vehicle plan for performing the agricultural operations.

11. The method of claim 9 comprising, transmitting, from a vehicle in the field, the vehicle system data during operations of the vehicle in the field.

12. The method of claim 9 , comprising deriving an order of operations for the one or more partitions of the field, wherein the one or more partitions of the field comprise one or more headland partitions in the field, one or more interior field partitions, or a combination thereof, and wherein each of the one or more interior field partitions comprise an orientation of rows within each of the one or more field partitions.

13. The method of claim 9 , comprising deriving one or more operational features, one or more driving features, one or more operating patterns, or a combination thereof, via the learning system based on the vehicle system data.

14. The method of claim 13 , wherein the operational features comprise agricultural equipment settings for each of the one or more partitions, wherein the driving features comprise a plurality of rows for each of the one or more partitions, a direction of travel for each of the plurality of rows, a spacing between each of the plurality of rows, a preferred route around an obstacle in the field, or a combination thereof, and wherein the operating patterns comprise a one-way pattern, a gathering pattern, a casting pattern, a spiral pattern, a zig zag pattern, or a combination thereof.

15. A non-transitory, computer readable medium comprising instructions that when executed by a processor cause the processor to:
derive one or more partitions of a field based on a vehicle system data via a learning system;
derive one or more turn features representative of vehicle turns in the field based on the vehicle system via the learning system;
derive an autonomous vehicle plan based on the partitions of the field and the turn features via a planning system, wherein the autonomous vehicle plan comprises a planned route of the autonomous vehicle in the field, wherein the learning system comprises a forward-chained expert system, a backward-chained expert system, a neural network, a data mining system, a state vector machine (SVM), a decision tree learning system, an association rule learning system, a deep learning system, an inductive logic programming system, a genetic algorithm, or a combination thereof.

16. The non-transitory, computer readable medium of claim 15 , wherein the vehicle system comprises an agricultural vehicle towing an agricultural implement and the agricultural implement is configured for agricultural operations on the field, and wherein the autonomous vehicle is configured to apply the autonomous vehicle plan for performing the agricultural operations.

17. The non-transitory, computer readable medium of claim 15 , comprising instructions that when executed by the processor, cause the processor to receive, from a vehicle in the field, the vehicle system data during operations of the vehicle in the field.

18. The non-transitory, computer readable medium of claim 15 , comprising instructions that when executed by the processor, cause the processor to derived one or more operational features, one or more driving features, one or more operating patterns, or a combination thereof, via the learning system based on the vehicle system data.

Assignees

• Cnh Ind America Llc
• Autonomous Solutions Inc

Inventors

• Foster Christopher Alan
• Posselius John Henry
• Turpin Bret Todd
• Morwood Daniel John
• Bunderson Nathan Eric

Classifications

• G06N20/00

  Machine learning · CPC title

• A01B69/008

  automatic · CPC title

• G01C21/32

  Structuring or formatting of map data · CPC title

• G05D1/0221 Primary

  involving a learning process · CPC title

• G05D2201/0201

  Physics · mapped topic