Method and apparatus for automatically steering a vehicle in an agricultural field using a plurality of fuzzy logic membership functions

• US 20020106108A1
• Filed: 02/02/2001
• Published: 08/08/2002
• Est. Priority Date: 02/02/2001
• Status: Active Grant

• Current Assignee: Board of Trustees of The University of Illinois, Blue Leaf IP Incorporated (CNH Industrial N.V.), CNH Industrial America LLC (CNH Industrial N.V.)
• Original Assignee: Board of Trustees of The University of Alabama (University of Alabama System)
• Inventors: Benson, Eric, Zhang, Qin, Reid, John F.
• Granted Patent: US 6,819,780 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: A01B 69/001 Steering by means of optical assistance, e.g. television cameras steering devices for road marking vehicles E01C23/163
• CPC Class Codes: A01B 69/008 automatic
• CPC Class Codes: B60W 2050/0057 Frequency analysis, spectral techniques or transforms
• CPC Class Codes: B60W 2300/15 Agricultural vehicles
• CPC Class Codes: B60W 2555/00 Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
• CPC Class Codes: B62D 1/28 non-mechanical , e.g. following a line or other known markers
• CPC Class Codes: G01C 11/00 Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means

Abstract

A combine having a camera system is disclosed in which pictures of the ground in front of the vehicle are processed to extract the slope and intercept of a characteristic line indicative of the boundary between the cut and uncut portions of the field. A fuzzy logic algorithm compares the slope and intercept using four input membership functions and a single output membership function. If the slope and intercept extracted from the image are deemed acceptable, they are used to navigate the vehicle through the field. If they are not acceptable, the combine continues to use slope and intercept values previously deemed acceptable to guide the vehicle. This process of image data extraction and quality analysis continues repetitively as the combine traverses the field harvesting crops.

Claims

1. A method of guiding an agricultural vehicle having at least one steerable wheel in an agricultural field having a plurality of rows of crops, the method comprising:

taking a picture of the rows of crops with an electronic camera;

successively processing a plurality of lines of the picture;

extracting from the plurality of processed lines at least one value indicative of a crop line;

extracting another value from the at least one value that is indicative of the lateral displacement of the crop line with respect to the vehicle;

processing the another value in a fuzzy logic input membership function, then a fuzzy logic inference engine and then a fuzzy logic output membership function to develop a signal indicative of the degree the at least one steerable wheel should be turned;

providing the signal indicative of the degree to which the steerable wheel should be turned to a feedback control circuit configured to steer the at least one steerable wheel in a direction that minimizes a difference between the signal indicative of the degree the at least one steerable wheel should be turned and another signal indicative of the degree to which the at least one steerable wheel is actually turned;

generating a valve control signal calculated to reduce the difference;

applying the valve control signal to an electro-hydraulic control valve configured to steer the at least one steerable wheel; and

steering the wheel accordingly.

2. The method of claim 1, wherein the step of extracting another value includes the step of extracting values sufficient to define a line indicative of a row of crops, a gap between a row of crops, or a cut/uncut boundary in a field.

3. The method of claim 2, wherein the step of processing the another value includes the step of processing the another value in the input membership function to produce at least a first input value indicative of a degree of membership in a first input membership function domain and a second input value indicative of a degree of membership in a second input membership domain.

4. The method of claim 3, wherein the step of processing the another value includes the step of processing the first and second input values in the fuzzy logic inference engine.

5. The method of claim 4, wherein the output membership function includes at least three domains symmetric with respect to a steering angle of zero, and further wherein the at least three domains include a center domain wherein a 100% membership causes the at least one steerable wheel to move toward or to remain in a mode of straight line travel.

6. The method of claim 5, wherein two of the at least three domains are symmetrically disposed on either side of a center of the center domain.

7. The method of claim 6, wherein the at least three domains include two additional domains that are also symmetrically disposed on either side of the center of the center domain.

8. A method of guiding an agricultural vehicle having at least one steerable wheel in an agricultural field having a plurality of crop rows, the method comprising:

taking a picture of the crop rows with an electronic camera;

extracting from the pictures row location values indicative of a location of at least one crop row;

determining, based upon at least one previous row location value, whether the row location values are valid;

and for each such row location values that are determined valid;

deriving therefrom a value indicative of a desired direction of travel;

processing the value indicative of a desired direction of travel in a fuzzy logic inference engine to produce a control signal;

providing the control signal to an automatic control loop that uses feedback control based upon the position of the at least one steerable wheel to generate a valve command signal;

applying the valve command signal to an electro-hydraulic steering control valve;

and for each such row location values that is determined invalid;

not using such invalid row location value in the automatic control loop.

9. The method of claim 8, wherein the step of deriving therefrom a value includes the step of processing the row location value in a first fuzzy logic control circuit.

10. The method of claim 9, wherein the value indicative of a desired direction of travel is a value indicative of a desired steering angle.

11. The method of claim 9, wherein the value indicative of a desired direction of travel is a value indicative of a desired steering rate.

12. The method of claim 10, wherein the step of determining whether the row location values are valid includes the step of processing the row location values in a second fuzzy logic control circuit.

13. The method of claim 12, wherein the row location values include values sufficient to define a line having a slope and an intercept in the image frame from which the row location values were extracted.

14. The method of claim 13, wherein the row location values are indicative of a crop row.

15. The method of claim 13, wherein the row location values are indicative of a gap between crop rows.

16. The method of claim 13, wherein the row location values are indicative of a cut/uncut boundary in the field.

17. The method of claim 9, wherein the first fuzzy logic control circuit includes at least one fuzzy logic input membership function to process at least one of the row location values and a second fuzzy logic input membership function to process at least another of the row location values, and further wherein both the at least one and at least another row location values are extracted from a single camera image.