Unmanned Systems Technology 011 | C-Astral Bramor ppX | IMUs | Autonomous farming | UAV Turbines UTP50R | London Show report | Advanced materials | Las Vegas Expo report

49 Autonomous farming | Insight positioning along with a magnetometer to provide data on turns. All of this is fed into a central flight computer. On the grape vine But UAVs are not the only craft being used in vineyards. Wall Ye in France has developed several autonomous vehicles for pruning grape vines, while a team at the University of Canterbury in New Zealand, backed by drinks maker Pernod Ricard, is developing a similar system, using image recognition. This is mounted on a platform that straddles the vines and moves along the row, pruning as it goes. The Canterbury system uses three high-resolution digital cameras to image the vines, then uses computer vision algorithms to make a 3D model of the vine from the images. An AI system uses this model to decide which vines to keep and which to cut. A six-jointed robot arm then reaches among the canes and makes the required cuts with a spinning cutting tool. The robot was trained to make good pruning decisions by providing it with examples of how human experts prune vines. This all took four years to develop, with the first prototype being tested in 2015. Blue River Technology in the US is working on similar technology for handling lettuce. The LettuceBot identifies every plant, makes a decision based on what it sees, and then sprays individual plants. It automatically thins lettuce fields with a precision that increases yield, as the robot can keep the best plants using criteria based on optimal spacing and the most uniform size of the plants available. A range of cameras coupled to 20 processors running computer vision algorithms allow more than 5000 decisions per minute. Blue River is also developing an unmanned aerial system that can survey a field of crops and sense for various plant and environmental characteristics so that the spray technology can be used more accurately. Conclusion Precision land management using autonomous systems can help boost the productivity and efficiency of farmers, but there is no one system that meets every agricultural need. Directing autonomous tractors with UAVs to the right area tackles problems quickly and efficiently, while new swarm algorithms will also help groups of UAVs operate across wider areas. New technologies such as hydrogen fuel cells and advances in machine vision are extending the life of systems in the air and providing more capabilities on the ground, while the cost of accurate navigation systems is falling. The design and development of autonomous systems has only just begun, but a wide range of technologies will make their way into and above farmers’ fields over the next few years. Unmanned Systems Technology | December/January 2017 This autonomous robot has been designed for pruning grape vines (Courtesy of Wall Ye) Machine vision and a large array of processing power is used here to plant and thin-out lettuces (Courtesy of Blue River Technology)