This mechanical engineer is building a robot to harvest raspberries | Jobs Vox



Around 38% of the world’s total land area is used for agriculture – yet hunger is worsening, and food security is at risk, threatened by pressures including climate change, conflict and global recession.

While there is no one-stop solution, technology can help fill in some of the gaps. Mechanical engineer Josie Hughes is on a mission to show how robotics can play a role in our daily lives, especially when it comes to food. Starting with Lego robots as a child, the Cambridge graduate now leads the Computational Robot Design and Fabrication Lab (CREATE) at the Swiss Federal Institute of Technology Lausanne (EPFL), where he joins as a tenure-track assistant. One of the youngest researchers to be Professor.

One of his innovations, a raspberry-picking robot powered by artificial intelligence, could help make farming more efficient and cost-effective, and solve labor shortages – which cost £60 million ($74 million) in the UK alone million) worth of fruits and vegetables are rotting in the fields this summer. CNN talked to Hughes about his research, and when robots might be harvesting 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 an important role in harvesting, as they can work 24 hours a day. We can harvest more precisely – picking crops just when they are ready – which can reduce waste and improve quality. Robots can harvest as well as collect data: for example, information about the quantity of fruit or its quality for farmers.

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

Hughes: Robotic harvesting gives us the opportunity to harvest at night and early in the morning – the optimal time in terms of fruit ripeness and water content, which varies throughout the day.

Josie Hughes (pictured) was just 29 when she became a tenure-track assistant professor at EPFL.

CNN: How does the robot work?

Hughes: The robot consists of a four-wheeled base on which a six-jointed robotic arm is mounted. At the end of the arm, the robot has a “gripper” for harvesting, which has a silicone coating to make the fruit soft. The gripper has a camera that gives us information about the robot’s distance from the fruit and uses color vision to detect raspberries. Additional sensors in the fingertip measure the holding and pulling forces applied to the raspberry. We used artificial intelligence to help identify the location of the raspberries within the camera’s field of view, and to optimize the controls of the grasping fingers. Harvesting is fully autonomous – however, we move the robot manually to the raspberry plants.

CNN: Why did you choose raspberries to harvest?

Hughes: Raspberries are very delicate and get damaged easily. If we apply too much force, they shrink – although we need enough force to remove them from plants. Additionally, the force needs to be adjusted throughout the harvesting motion, as the fruit becomes less rigid once released from the plant.

CNN: What is the Raspberry “physical twin” you built, and how does it help train robots?

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

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

Hughes: Right now, our robots are optimized for precision and not speed, whereas humans are good at accuracy And pace. We are working to reduce the robot’s work process to half the speed of a person – such that if the robot worked twice as long as a person, it would be comparable.

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

Hughes: Harvesting robots are still a new technology, and it’s unclear how it will affect jobs. However, many farmers and farm organizations are saying they cannot recruit the workers needed for harvesting, especially in countries that previously relied on migrant labor for very low wages. This presents an opportunity to positively introduce robots.

With the help of artificial intelligence, sensors and cameras, the robot detects its distance from the raspberry.

CNN: How will robots affect or change circumstances for farm workers?

Hughes: Harvesting is a physically challenging job. This includes prolonged exposure to the elements – sun, rain, storms and even snow – with unusually high injury and illness rates of agricultural workers. Instead, if robots can perform the hard labor supported by agricultural workers, we can hopefully assist with recruitment challenges while improving the quality of work.

CNN: How can robots and AI help agriculture in the face of climate change pressures like this one?

Hughes: Robots allow us to rethink what agriculture might look like in the future and robots can help us harvest different crops simultaneously in the same field that we have instead of the current single-crop farms we have on our farms. aid in their own growth and soil condition. We could move towards precision agriculture, where harvesting, pesticide application or any other action is tailored to the individual plant. This has a significant impact on the entire farm or field, as pesticides and resources are used only where they are really needed – which, in addition to significant 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 you currently working in?

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


Source link

Implement tags. Simulate a mobile device using Chrome Dev Tools Device Mode. Scroll page to activate.