Vehicle controllers for agricultural and industrial applications

1. A system, comprising:

a sensor connected to a vehicle;

actuators configured to control motion of the vehicle; and

a processing apparatus configured to:

access current point cloud data captured using the sensor;

detect a crop row based on the current point cloud data;

detect an end of the crop row based on point cloud data captured using the sensor;

plan a turn at the end of the crop row;

control one or more of the actuators to cause the vehicle to execute the turn;

after executing the turn, detect a last seen plant at the end of the crop row;

based on a position of the last seen plant, identify a trajectory to enter a next agricultural lane bounded by the crop row; and

control one or more of the actuators to cause the vehicle to enter the next agricultural lane.

2. The system of claim 1 , in which the processing apparatus is configured to:

detect a furrow in the ground based on the current point cloud data;

match the detected furrow with a furrow represented in a map; and

determine an estimate of a current location of the vehicle based on a current position in relation to the detected furrow.

3. The system of claim 1 , in which the processing apparatus is configured to:

filter the current point cloud data to consider only points in a zone of interest when comparing the current point cloud data to point cloud data of a map to match the detected crop row with a crop row represented in the map, where in the zone of interest is limited to a range of heights and a maximum distance from the vehicle.

4. The system of claim 1 , comprising:

one or more image sensors connected to the vehicle; and

actuators configured to control operation of an implement, wherein the implement is connected to the vehicle and configured to selectively perform an operation in a vicinity of the vehicle, and in which the processing apparatus is configured to:

receive image data, captured using the one or more image sensors, depicting one or more plants in the vicinity of the vehicle;

detect the one or more plants based on the image data;

responsive to detecting the one or more plants, adjust implement control data; and

control one or more of the actuators, based on the adjusted implement control data, to cause the implement to deposit an input on the one or more plants.

5. The system of claim 4 , in which the one or more image sensors comprise a normalized difference vegetation index camera connected to the vehicle, in which the processing apparatus is configured to:

receive normalized difference vegetation index data, captured using the normalized difference vegetation index camera, for the one or more plants, wherein adjusting the implement control data includes adjusting an amount of input to be deposited on the one or more plants based on the normalized difference vegetation index data.

6. The system of claim 4 , in which the vehicle is a tractor and the implement is a sprayer.

7. The system of claim 4 , in which the implement control data is adjusted based on a count of the one or more plants detected in the vicinity of the vehicle.

8. The system of claim 1 , in which the vehicle is a tractor.

9. A method comprising:

accessing current point cloud data captured using a sensor connected to a vehicle;

detecting a crop row based on the current point cloud data;

detecting an end of the crop row based on point cloud data captured using the sensor;

planning a turn at the end of the crop row;

controlling one or more actuators to cause the vehicle to execute the turn;

after executing the turn, detecting a last seen plant at the end of the crop row;

based on a position of the last seen plant, identifying a trajectory to enter a next agricultural lane bounded by the crop row; and

controlling one or more actuators to cause the vehicle to enter the next agricultural lane.

10. The method of claim 9 , comprising:

detecting a furrow in the ground based on the current point cloud data;

matching the detected furrow with a furrow represented in a map; and

determining an estimate of a current location of the vehicle based on a current position in relation to the detected furrow.

11. The method of claim 9 , comprising:

filtering the current point cloud data to consider only points in a zone of interest when comparing the current point cloud data to point cloud data of a map to match the detected crop row with at crop row represented in the map, where in the zone of interest is limited to a range of heights and a maximum distance from the vehicle.

12. The method of claim 9 , comprising:

receiving image data, captured using one or more image sensors connected to the vehicle, depicting one or more plants in a vicinity of the vehicle;

detecting the one or more plants based on the image data;

responsive to detecting the one or more plants, adjusting implement control data; and

controlling, based on the adjusted implement control data, an implement to deposit an input on the one or more plants, wherein the implement is connected to the vehicle and configured to selectively deposit input in a vicinity of the vehicle.

13. The method of claim 12 , in which the one or more image sensors comprise a normalized difference vegetation index camera connected to the vehicle, and the method comprising:

receiving normalized difference vegetation index data, captured using the normalized difference vegetation index camera, for the one or more plants, wherein adjusting the implement control data includes adjusting an amount of input to be deposited on the one or more plants based on the normalized difference vegetation index data.

14. The method of claim 12 , in which the vehicle is a tractor and the implement is a sprayer.

15. The method of claim 12 , in which the implement control data is adjusted based on a count of the one or more plants detected in the vicinity of the vehicle.

16. The method of claim 9 , in which the vehicle is a tractor.

17. A non-transitory computer-readable storage medium storing executable instructions that, when executed by a processor, facilitate performance of operations comprising:

accessing current point cloud data captured using a sensor connected to a vehicle;

detecting a crop row based on the current point cloud data;

detecting an end of the crop row based on point cloud data captured using the sensor;

planning a turn at the end of the crop row;

controlling one or more actuators to cause the vehicle to execute the turn;

after executing the turn, detecting a last seen plant at the end of the crop row;

based on a position of the last seen plant, identifying a trajectory to enter a next agricultural lane bounded by the crop row; and

controlling one or more actuators to cause the vehicle to enter the next agricultural lane.

18. The non-transitory computer-readable storage medium of claim 17 , in which the operations comprise:

detecting a furrow in the ground based on the current point cloud data;

matching the detected furrow with a furrow represented in a map; and

determining an estimate of a current location of the vehicle based on a current position in relation to the detected furrow.

19. The non-transitory computer-readable storage medium of claim 17 , in which the operations comprise:

filtering the current point cloud data to consider only points in a zone of interest when comparing the current point cloud data to point cloud data of a map to match the detected crop row with a crop row represented in the map, where in the zone of interest is limited to a range of heights and a maximum distance from the vehicle.

20. The non-transitory computer-readable storage medium of claim 17 , in which the operations comprise:

receiving image data, captured using one or more image sensors connected to the vehicle, depicting one or more plants in a vicinity of the vehicle;

detecting the one or more plants based on the image data;

responsive to detecting the one or more plants, adjusting implement control data; and

controlling, based on the adjusted implement control data, an implement to deposit an input on the one or more plants, wherein the implement is connected to the vehicle and configured to selectively deposit input in a vicinity of the vehicle.