New robotic tractor tool supports precision spraying in crops
Precision spraying is being reimagined with a new smart technology designed to support farmers in managing weeds more effectively. Researchers at the University of Guelph, led by Dr. Medhat Moussa, have partnered with industry leaders to create an agricultural robotic system that attaches to tractors.
The technology uses cameras and computer vision powered by AI algorithms to scan fields and generate weed density maps. These maps highlight areas that require herbicide, ensuring chemicals are applied only where needed. This approach saves time, lowers production costs, reduces chemical use, and supports healthier crops.
Traditionally, weed scouting is done manually, where farmers walk through fields and check limited sections. This method is time consuming and often inaccurate, especially when weeds are small. The new robotic tool offers a full field overview, making the process more precise and efficient.
“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.”
Developed with Nortera Foods and Haggerty AgRobotics, the system is in its final testing stages. It builds on the University’s previous robotics work, including a tomato-picking robot. The technology may also be adapted for other crops in the future.
For farmers, this advancement means healthier yields and improved efficiency, while for students and industry, it offers valuable training and real-world benefits.