Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

This paper presents a machine vision guidance system for an autonomous agricultural machine. A zero turning radius lawnmower which had been previously outfitted for autonomous operation was used as the test platform for integrating a machine vision system as a relative position reference navigation system.

Using a DVT 542C integrated machine vision system an algorithm was developed to distinguish a bright line from a dark background, a simulation of near-infrared images of crop rows, and to develop navigation measurements from this. Software was written to use those measurements to steer the machine. Numerous tests were run to demonstrate the efficacy and robustness of the system, including comparison to a skilled human operator. Problems and potential options for integrating this into trajectory control are discussed.