Unmanned Systems Technology 027 l Hummingbird XRP l Gimbals l UAVs insight l AUVSI report part 2 l O’Neill Power Systems NorEaster l Kratos Defense ATMA l Performance Monitoring l Kongsberg Maritime Sounder

6 Mission-critical info for UST professionals Platform one Researchers at Cambridge University have developed a vegetable-picking robot that uses machine learning to identify and harvest lettuce, a crop that has been difficult to harvest effectively (writes Nick Flaherty). The Vegebot was initially trained to recognise and harvest Iceberg lettuce in a lab setting, but has now been successfully tested in various field conditions. Iceberg is the most common lettuce grown in the UK, but it is easily damaged and grows relatively flat to the ground, presenting a challenge for robotic harvesters. “Every field is different, every lettuce is different,” said researcher Simon Birrell from the university’s Department of Engineering. “But if we can make a robotic harvester work with Iceberg lettuce, we could also make it work with many other crops.” Julia Cai, who worked on the computer vision components of the system, added, “At the moment, harvesting is the only part of the lettuce lifecycle that is done manually, and physically it’s very demanding.” An overhead camera in the Vegebot first identifies the ‘target’ crop in its field of vision, then determines whether a particular lettuce is healthy and ready to be harvested. It then cuts the lettuce from the rest of the plant at a height of 2 cm from the ground without crushing it. “For a human, the entire process takes only a couple of seconds, but it’s a really challenging problem for a robot,” said researcher Josie Hughes. “We’re also collecting lots of data about lettuce, such as which fields have the highest yields, which could be used to improve efficiency. “We still have to speed up the Vegebot to the point where it could compete with a human, but we think robots have lots of potential in agritech.” The researchers developed and trained a machine learning algorithm on example images of lettuces. Once the Vegebot could recognise healthy lettuces in the lab, it was then trained in the field, in a variety of weather conditions and on thousands of real lettuces. A second camera on the Vegebot is positioned near its cutting blade, to help ensure a smooth cut. The researchers were also able to adjust the pressure of the robot’s gripping arm so that it held the lettuce firmly enough not to drop it, but not so firm as to crush it. The force of the grip can be adjusted for other crops. The system also reduces food waste, as each field is typically harvested only once, and any unripe crop is discarded. It could be trained to pick only ripe vegetables, and since it could harvest round the clock, it could perform multiple passes on the same field, returning at a later date to harvest the vegetables that were previously unripe. Ground vehicles Reaping reward of r&d The Vegebot is able to identify and harvest Iceberg lettuce crops (Courtesy of Cambridge University) August/September 2019 | Unmanned Systems Technology