Row follower training
AssigneeZimeno Inc.
InventorRama Venkata BHUPATIRAJU
Life of this patent
Estimating the term…
Abstract
Images are captured with a camera from between consecutive rows as the camera is moved along consecutive rows. A verification is made as to whether the row follower vehicle is at a targeted row position during the capture of the images. The images are output to a machine learning model to train the machine learning model to determine whether the row follower vehicle is at the targeted row position based on images from the camera and verification that the row follower vehicle is at the targeted row position during capture of the images.
Claims20
A row follower training system comprising:
- a camera to be coupled to a row follower vehicle;
- a processing resource;
- a non-transitory computer readable medium comprising instructions configured to direct the processing resource to:
- capture images with a camera as the camera is moved along plant rows;
- for each of the images, verify that the row follower vehicle is at a targeted row position during the capture of the images;
- output the images to a machine learning model to train the machine learning model to determine whether the row follower vehicle is at the targeted row position based on images from the camera and based on a verification that the row follower vehicle at the targeted row position during capture of the images;
- and
- output steering control signals to steer the row follower vehicle or a second row follower vehicle, in an automated fashion, along other consecutive rows using the trained machine learning model and images from the camera, or a second camera coupled to the second row follower vehicle.
A non-transitory computer-readable medium containing instructions to direct a processing unit, the instructions being configured to direct the processing unit to:
- capture images with a camera from between consecutive rows as the camera is moved along the consecutive rows;
- for each of the images, verify that a row follower vehicle is at a targeted row position during the capture of the images;
- output the images to a machine learning model to train the machine learning model to determine whether the row follower vehicle is at the targeted row position based on images from the camera and verification that the row follower vehicle is at the targeted row position during capture of the images;
- and
- output steering control signals to steer the row follower vehicle or a second row follower vehicle, in an automated fashion, along the rows using the trained machine learning model and images from the camera or a second camera coupled to the second row follower vehicle.
A method for steering a row follower vehicle, the method comprising:
- capturing images with a camera from between consecutive rows as the camera is moved along and between the consecutive rows;
- for each of the images, verifying that the row follower vehicle is in a navigable space during the capture of the images;
- outputting the images to a machine learning model to train the machine learning model to determine whether the row follower vehicle is within the navigable space between consecutive rows based on images from the camera and verification the row follower vehicle is in the navigable space during capture of the images;
- and
- outputting steering control signals to steer the row follower vehicle or a second row follower vehicle, in an automated fashion, between other consecutive rows using the trained machine learning model and images from the camera or a second camera coupled to the second row follower vehicle.
Dependencies are inferred from the claim text.