This mechanical engineer builds robots to harvest berries

This mechanical engineer builds robots to harvest berries


About 38% Of the world’s total land area is used for agriculture – but hunger is getting worse, and Food security is in crisisthreatened by stresses including climate change, conflicts and global recessions.

Although there is no universal solution, technology can help fill in some of the gaps. Mechanical engineer Josie Hughes is on a mission to show how robots can play a role in our everyday lives, particularly when it comes to food. Starting with LEGO robots as a child, the Cambridge graduate now leads the Computational Robotics Design and Manufacturing Laboratory (CREATE) at the Swiss Federal Institute of Technology Lausanne (EPFL), where she was one of the youngest researchers to join as a Career Assistant. professor.

One of its innovations, an AI-powered berry-picking robot, could help make farming more efficient and cost-effective, and solve a labor shortage – which the UK has left alone. 60 million pounds sterling ($74 million) of rotting fruit and vegetables in the fields this summer. CNN spoke with Hughes about her research, and when robots might harvest your next meal.

This interview has been edited for length and clarity.

CNN: How can robots help with tasks like harvesting in agriculture?

Josie Hughes: Robots can play a vital role in harvesting, as they can work 24 hours a day. We could have more careful harvesting – picking crops only when they are ready – which could reduce waste and improve quality. Bots can also collect data along with the harvest: for example, information for farmers about the quantity or quality of fruit.

CNN: How does the harvester affect the nutrition and quality of the fruit?

Hughes: Harvesting with a robot gives us the opportunity to harvest at night and early in the morning – the best time for the fruits in terms of ripeness and water content, which vary throughout the day.

CNN: How does the robot work?

Hughes: The robot has a four-wheel base with a six-jointed robotic arm mounted on it. At the end of the arm, the robot has a “gripper” for harvesting, with a silicone coating to make it softer on the fruit. The gripper contains a camera that gives us information about the robot’s distance from the fruit and uses color vision to detect berries. Additional sensors in the fingers measure the gripping and pulling forces we apply to the berry. We used artificial intelligence to help locate the berry within the cameras view, as well as to improve the control of grasping fingers. Harvesting is done completely autonomously – however, we manually move the robot to the berry plants.

CNN: Why did you choose to harvest berries?

Hughes: Raspberries are very fragile and easily damaged. If we use too much force, they become squishy – but we need enough force to remove them from plants. In addition, the force must be adjusted during the harvesting motion, as the fruits become less hard once they come off the plant.

CNN: What is the “physical twin” you created, and how does it help train the robot?

Hughes: A physical twin is a device that mimics a raspberry on a plant, and how it behaves when pulled from the plant. It has an outer layer of silicone, which can be pulled out of the plant by separating two magnets. However, our “fake” Raspberry Pi has something special: it uses what we call soft sensors, which provide information about the force applied. These sensors allow us to record how a person harvests raspberries, providing us with a reference or benchmark that we can use to train the robot.

CNN: How do berry picking robots compare to human fruit pickers?

Hughes: Right now, our robot is optimized for accuracy, not speed, while humans are good at accuracy And the Speed. We’re speeding up the robot’s working process, so that it’s half as fast as a human — so that if a robot runs twice as long as a human, it’s comparable.

CNN: People are often worried about losing jobs to robots. What jobs will robots replace?

Hughes: Harvesting robots is still a new technology, and it’s not necessarily clear how this will affect jobs. However, many farmers and agricultural organizations say they cannot hire the workers needed to harvest, particularly in countries that previously relied on migrant workers at very low wages. This presents an opportunity to present the bots in a positive light.

Using artificial intelligence, sensors, and cameras, the robot detects its distance from the berries.

CNN: How will a robot affect or change conditions for farm workers?

Hughes: Harvesting is a difficult physical task. It has long hours, and exposure to the elements—sun, rain, storms, even snow—with agricultural workers having an abnormally high rate of injury and disease. Instead, if robots can do the hard work, with the support of farm workers, we hope to help with employment challenges while improving the quality of work.

CNN: How can robotics and artificial intelligence like this help agriculture cope with the pressures of climate change?

Hughes: Robotics allow us to rethink what farming could look like in the future and robots can help us harvest a range of different crops together into a single field that aids in their growth and soil conditions, rather than our current single crop fields. We can move on to precision farming, where harvesting, pesticide use, or any other task is tailored to individual plants. This has a significant impact on the entire field or farm, as pesticides and resources are used only when they are really needed – which, in addition to great environmental benefits, can also be cheaper for the farmer.

CNN: When can we expect to see these robots in use on farms, and what areas are they currently in use?

Hughes: There is more work to do to automate the driving and navigation of the harvesting vehicle – but we believe that such robots could be working safely and usefully on farms in the next two to three years. We’re also looking at how we can use a similar approach to harvest other delicate berries, such as blackberries or raspberries.

#mechanical #engineer #builds #robots #harvest #berries

Leave a Comment

Your email address will not be published. Required fields are marked *