By Jamie Martin
A new innovation from the University of Guelph is set to improve weed management in agriculture. Dr. Medhat Moussa and his team, working with industry partners, have developed an AI powered robotic tractor attachment that scans crop fields for weeds.
The system generates weed density maps, showing farmers exactly where to apply herbicides. By targeting only areas that require treatment, farmers save money, use fewer chemicals, and improve crop health. Better weed control also means stronger yields and less impact from herbicide-resistant weeds.
Traditionally, weed scouting has been done by walking through fields and inspecting samples, which is time consuming and prone to human error. The new robotic system automates this process, offering accuracy and efficiency at a lower cost than fully autonomous weeding robots.
“Our robotic attachment, equipped with cameras, gets mounted onto a small tractor or similar vehicles,” said Moussa. “As the tractor is driven through the field, the cameras scan the ground and take photos that are analyzed by a three-stage AI algorithm. Our algorithm differentiates between lima beans and weeds in each image, then combines the images into a complete density map showing exactly which areas need to be treated.”
This innovation was developed in partnership with Nortera Foods and Haggerty AgRobotics, ensuring testing and adoption on real farms. The technology builds on the University’s robotics expertise, following earlier projects such as a self-operating tomato-picking robot.
Now in its final testing stages, the system may expand to other crops in the future. Beyond practical benefits, it also provides students valuable training opportunities in agricultural robotics.
For farmers, the technology represents a balanced, accessible step forward in precision agriculture, combining cost savings, environmental benefits, and higher crop quality.
Photo Credit: gettyimages-shotbydave
Categories: National