Training fields

Robot trained to remove weeds from organic fields


A large database of images forms the basis for the formation of a small robot that in the future will remove unwanted weeds from organic pastures.

In the future, a robot the size of a large lawn mower will help organic farmers remove weeds from the docks of their pastures. The dock is a big problem because it takes up space on the plants in the field which give the cows the best nutrition.

It may seem like a small task, but it takes a lot of effort for the robot to recognize weeds. At first glance, it is actually not that easy to distinguish a green weed from the grass in the field, writes Anne Kirsten Frederiksen in a Press release.

“Initially, we took a lot of photos at three organic farmers. These were photos of the quay plant and its leaves as well as different pastures to use as a background, ”says Ronja Güldenring, DTU Electrical Engineering, who is leading the project.

“The next step was to create a lot of photo combinations so that the docks appeared with different backgrounds. These can be photos taken in different areas, at different times of the day, at different times of the year, etc. », Explains Ronja Güldenring.

Subscribe to our newsletter!

Your Weekly Innovation Snapshot Every Sunday, the best articles of the week are delivered to your inbox.

The robot must be robust

The goal of the first months of photographic work was to create a database of several thousand different images with combinations of docks and backgrounds. The large amount of photos is needed to have a sufficient base to train the robot to recognize and locate weeds under very different conditions.

“For example, a downpour or morning dew means that there may be water droplets on the leaves of the dock which give unwanted reflections from the camera. The robot must also be able to take this into account, ”explains Ronja Güldenring.

Ronja Güldenring will now start training the robot so that using a camera mounted on top and another mounted under the robot’s “shell”, he can recognize and locate weeds in a pasture. When this has been successfully achieved, the robot will be supplemented with instruments capable of destroying the dock by means of techniques based on laser or electrocution. However, that won’t be until 2022. By then, Ronja Güldenring has released all of his image data – so that other researchers can use it in their work – as it is both expensive and time-consuming to collect. such large data. sets.

New technology makes the robot possible

Organic dairy farmers who have made pasture available for photography are convinced that the robot will be a good thing. This pleases Ronja Güldenring, who hopes the project can contribute to the green transition by allowing even more conventional dairy farmers to grow their fields organically in the future.

The overall project manager, Lazaros Nalpantidis, is also positive about the possibilities. “The agricultural sector has already come a long way with the use of autonomous systems, which is, in particular, linked to the fact that fewer and fewer people are employed in the sector.

Lazaros Nalpantidis underlines in this regard that some new technological advances have made the development of the new robot possible.

“The introduction of the 5G network has made wireless connections more stable and, with access to data from the new Galileo satellites, it has also become possible to establish precise positioning of weeds within centimeters of previous deviations. going up to several meters, ”explains Lazaros Nalpantidis.

The new robot is being developed as part of an EU project that includes several partners, including Wageningen UR in the Netherlands, which is considered one of the world’s leading universities for agricultural research. During the year 2022, DTU will work closely with the other project partners to combine the different technologies to be used in the robot, which will then be tested further.

Also interesting: Multifunctional agricultural robot capable of sustainable cultivation

Source link

Leave a Reply

Your email address will not be published.