Machine-learned obstruction detection in a farming machine

A non-transitory computer-readable storage medium storing instructions for achieving a machine objective in an environment using a machine, wherein the instructions when executed by one or more processors causes the one or more processors to perform a method comprising:

• accessing, an obstruction model configured to identify obstructions in the environment from image data of the environment, the obstruction model generated by:
• accessing image data of obstructions in a training environment, each obstruction in the training environment corresponding to a prescribed action occurring at a prescribed time;
• labelling the image data of the obstructions in the training environment, each obstruction in the image data of the obstructions in the training environment labelled based on the prescribed time that the corresponding prescribed action occurred;
• and
• training the obstruction model to identify the obstructions in the environment using the labelled image data;
• capturing the image data of the environment including an obstruction in the environment;
• inputting the image data of the environment into the obstruction model to identify the obstruction in the environment;
• and
• responsive to identifying the obstruction in the environment, modifying machine instructions executed by the machine for implementing the machine objective, execution of the modified machine instructions causing the machine to avoid the obstruction in the environment.

A machine comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium storing instructions for achieving a machine objective in an environment using a machine, wherein the instructions when executed by one or more processors causes the one or more processors to perform a method comprising:
• accessing, an obstruction model configured to identify obstructions in the environment from image data of the environment, the obstruction model generated by:
• accessing image data of obstructions in a training environment, each obstruction in the training environment corresponding to a prescribed action occurring at a prescribed time;
• labelling the image data of the obstructions in the training environment, each obstruction in the image data of the obstructions in the training environment labelled based on the prescribed time that the corresponding prescribed action occurred;
• and
• training the obstruction model to identify the obstructions in the environment using the labelled image data;
• capturing the image data of the environment including an obstruction in the environment;
• inputting the image data of the environment into the obstruction model to identify the obstruction in the environment;
• and
• responsive to identifying the obstruction in the environment, modifying machine instructions executed by the machine for implementing the machine objective, execution of the modified machine instructions causing the machine to avoid the obstruction in the environment.