Method for autonomous detection of crop location based on tool depth and location

1. A method comprising, at an autonomous machine:

capturing a first image of a ground area of a plant bed surface via a ground-facing camera arranged on the autonomous machine;

detecting a first target plant in the first image;

accessing a lateral pixel location of the first target plant in the first image;

via a depth sensor arranged on the autonomous machine, estimating a depth of a subregion of the ground area;

for each tool module in a set of tool modules in contact with the plant bed surface and arranged behind the ground-facing camera relative to a direction of forward motion of the autonomous machine:

capturing an extension distance of the tool module; and

capturing a lateral position of the tool module relative to the ground-facing camera;

estimating a surface profile of the plant bed surface based on the extension distance of each tool module in the set of tool modules and the lateral position of each tool module in the set of tool modules;

estimating a depth profile based on the surface profile and the depth of the subregion of the ground area, comprising:

identifying a coincident section of the surface profile laterally coincident with the subregion of the ground area; and

defining the depth profile as a shifted version of the surface profile comprising the coincident section with an average depth equal to the depth of the subregion of the ground area;

estimating a real lateral location of the first target plant relative to the autonomous machine based on the lateral pixel location of the first target plant and the depth profile of the plant bed surface; and

driving a first tool module in the set of tool modules to a lateral position laterally aligned with the real lateral location of the first target plant.

2. The method of claim 1 , wherein detecting the depth of the subregion of the ground area comprises:

at the depth sensor, capturing a depth image of the subregion of the ground area;

identifying a ground region of the depth image; and

calculating an average depth of the ground region based on the ground region of the depth image.

3. The method of claim 2 , further comprising:

identifying a plant-occupying region of the depth image; and

calculating a plant height based on the plant-occupying region of the depth image.

4. The method of claim 3 , wherein estimating the real lateral location of the first target plant relative to the ground-facing camera comprises:

accessing a projection in three-dimensional space relative to the ground-facing camera corresponding to the lateral pixel location of the first target plant;

subtracting the plant height from the depth profile to calculate an approximate depth of the first target plant; and

estimating the real lateral location along the projection, the real lateral location corresponding to the approximate depth of the first target plant.

5. The method of claim 1 , further comprising:

at the second time, capturing an extension distance of a first weeding module in the set of tool modules; and

estimating a first depth of blades of the first weeding module based on a difference between the depth of the subregion of the ground area and the extension distance of the first weeding module.

6. The method of claim 5 , further comprising:

receiving a set depth for the blades of the first weeding module; and

actuating a suspension of the first weeding module according to feedback control based on the first depth of the blades of the first weeding module and the set depth of the blades of the first weeding module.

7. The method of claim 6 , further comprising:

estimating a maturity of the first target plant based on the first image; and

modifying the set depth for the blades of the first weeding module based on the maturity of the first target plant.

8. The method of claim 5 , further comprising:

in response to the difference between the depth of the subregion of the ground area and the extension distance of the first weeding module exceeding a threshold difference:

identifying malfunction of the depth sensor;

estimating a second depth profile of the plant bed surface proximal the first target plant based on the first extension distance of each tool module in the set of tool modules and the first lateral position of each tool module in the set of tool modules; and

updating the real lateral location of the first target plant relative to the ground-facing camera based on the lateral pixel location of the first target plant and the second depth profile.

9. The method of claim 8 , wherein estimating the second depth profile comprises:

for each tool module in the set of tool modules, defining a contact point of the tool module at an intersection of the first extension distance of the tool module and the first lateral position of the tool module to generate a set of contact points; and

interpolating between the set of contact points to generate the second depth profile.

10. A method comprising, at an autonomous machine:

capturing a first image of a ground area of a plant bed surface via a ground-facing camera arranged on the autonomous machine;

detecting a first target plant in the first image;

accessing a lateral pixel location of the first target plant in the first image;

via a depth sensor arranged on the autonomous machine, estimating a depth of a subregion of the ground area, comprising:

at the depth sensor, capturing a depth image of the subregion of the ground area;

identifying a ground region of the depth image; and

calculating an average depth of the ground region based on the ground region of the depth image;

for each tool module in a set of tool modules in contact with the plant bed surface and arranged behind the ground-facing camera relative to a direction of forward motion of the autonomous machine:

capturing an extension distance of the tool module; and

capturing a lateral position of the tool module relative to the ground-facing camera;

estimating a surface profile of the plant bed surface based on the extension distance of each tool module in the set of tool modules and the lateral position of each tool module in the set of tool modules;

estimating a depth profile based on the surface profile and the depth of the subregion of the ground area;

estimating a real lateral location of the first target plant relative to the autonomous machine based on the lateral pixel location of the first target plant and the depth profile of the plant bed surface; and

driving a first tool module in the set of tool modules to a lateral position laterally aligned with the real lateral location of the first target plant.

11. The method of claim 10 , further comprising:

identifying a plant-occupying region of the depth image; and

calculating a plant height based on the plant-occupying region of the depth image.

12. The method of claim 11 , wherein estimating the real lateral location of the first target plant relative to the ground-facing camera comprises:

accessing a projection in three-dimensional space relative to the ground-facing camera corresponding to the lateral pixel location of the first target plant;

subtracting the plant height from the depth profile to calculate an approximate depth of the first target plant; and

estimating the real lateral location along the projection, the real lateral location corresponding to the approximate depth of the first target plant.

13. A method comprising, at an autonomous machine:

capturing a first image of a ground area of a plant bed surface via a ground-facing camera arranged on the autonomous machine;

detecting a first target plant in the first image;

accessing a lateral pixel location of the first target plant in the first image;

via a depth sensor arranged on the autonomous machine, estimating a depth of a subregion of the ground area;

for each tool module in a set of tool modules in contact with the plant bed surface and arranged behind the ground-facing camera relative to a direction of forward motion of the autonomous machine:

capturing an extension distance of the tool module; and

capturing a lateral position of the tool module relative to the ground-facing camera;

estimating a surface profile of the plant bed surface based on the extension distance of each tool module in the set of tool modules and the lateral position of each tool module in the set of tool modules;

estimating a depth profile based on the surface profile and the depth of the subregion of the ground area;

estimating a real lateral location of the first target plant relative to the autonomous machine based on the lateral pixel location of the first target plant and the depth profile of the plant bed surface; and

driving a first tool module in the set of tool modules to a lateral position laterally aligned with the real lateral location of the first target plant;

at a second time, capturing an extension distance of a first weeding module in the set of tool modules; and

estimating a first depth of blades of the first weeding module based on a difference between the depth of the subregion of the ground area and the extension distance of the first weeding module.

14. The method of claim 13 , further comprising:

receiving a set depth for the blades of the first weeding module; and

actuating a suspension of the first weeding module according to feedback control based on the first depth of the blades of the first weeding module and the set depth of the blades of the first weeding module.

15. The method of claim 14 , further comprising:

estimating a maturity of the first target plant based on the first image; and

modifying the set depth for the blades of the first weeding module based on the maturity of the first target plant.

16. The method of claim 13 , further comprising:

in response to the difference between the depth of the subregion of the ground area and the extension distance of the first weeding module exceeding a threshold difference:

identifying malfunction of the depth sensor;

estimating a second depth profile of the plant bed surface proximal the first target plant based on the first extension distance of each tool module in the set of tool modules and the first lateral position of each tool module in the set of tool modules; and

updating the real lateral location of the first target plant relative to the ground-facing camera based on the lateral pixel location of the first target plant and the second depth profile.

17. The method of claim 16 , wherein estimating the second depth profile comprises:

for each tool module in the set of tool modules, defining a contact point of the tool module at an intersection of the first extension distance of the tool module and the first lateral position of the tool module to generate a set of contact points; and

interpolating between the set of contact points to generate the second depth profile.