Foto: Mikal Schlosser

Robots are getting better at handling unforeseen situations

Wednesday 09 Dec 20

Contact

Ole Ravn
Professor
DTU Electro
+45 45 25 35 60

In future, the agricultural sector will use collaborating robots to remove organic weeds and get the harvest done.

Artificial intelligence robots are becoming increasingly useful. You may have heard of oxygen robots that turn on oxygen for patients with breathing difficulties, or autonomous vessels that sail on their own. Now intelligent robots are also making their entrance into the agricultural sector, which has long worked with automation.

In line with robots getting closer and closer to humans, they also become better at handling unforeseen situations, such as driving in fields that are much more unstructured than a road with stripes and surface. These collaborating robots are known as cobots—and the technology is today so advanced that they will be equipped with situation awareness, enabling them to read their surroundings and incorporate any changes.

"With cobots, we no longer have to perform the boring work ourselves, and the tasks are performed much more precisely. What we’re seeing now is that these cobots are being used in industries that are a little more unstructured than previously. This is typically in the agricultural sector and the shipping industry, in small industrial enterprises, as well as in the healthcare sector,” says Ole Ravn, Professor at the Department of Electrical Engineering and head of DTU’s automation and robot technology research.

Will eradicate weeds

He mentions two examples in the agricultural sector where researchers are working to introduce intelligent robots. One example concerns one of the world’s three largest producers of agricultural machinery—AGCO Corporation—which is working with DTU to develop technology to automate agricultural machinery.

Here, the goal is to automate the combine harvester with sensors so that it can itself measure and react to the changes it encounters in the field. It may be a stone or an animal hidden in the crop that is being harvested. The machine must be able to adjust, so that it runs as optimally as possible and produces the best quality of harvested crop.

The other example is the EU-funded project GALIRUMI in which leading researchers in robot technology are working to develop an autonomous robot to be trained—using artificial intelligence—to find and eradicate weeds in organic fields. Here it will look for the weed ‘common dock’, which poses a major problem for farmers, as it takes up space in the field meant for grass for the cows.

Once the robot has found the weed, its next task is to combat it with one of its two instruments. This is either a laser or a device that can give the plant an electric shock.

Behind the project is Wageningen University & Research in the Netherlands—which is the world’s leading university in developing new technological solutions for the agricultural sector—and DTU Electrical Engineering, which contributes with expertise in autonomous systems.