The last two decades have ushered in an age of data-driven science that was not previously possible. In 1965, Moore’s law stipulated that the number of transistors on an integrated circuit would double every two years, and that “law” has been met or exceeded every year since, with the accompanying increase in computer processing speed and reduction in processor size. Computing capacity has reached a level that has enabled the application of new artificial intelligence (AI) algorithms, particularly deep neural networks. At the same time, sensors are smaller, have increased capabilities and require less energy. High-speed land and over-the-air communications make big data cloud storage feasible for even small farms.
Combining these trends has led to a significant increase in robotics and automation research and solutions for more robust, resilient and profitable agriculture—from the mundane tasks of robotically moving pots in a nursery to the advent of automated tractors, unmanned aerial vehciles, robotic fruit harvesters, automated milking parlors and pest management.
UGA researchers are developing a small, multi-purpose robotic platforms to use in peanuts, cotton, vegetables and other crops. These small rovers will be used in teams and can be scaled by their numbers to the size of operation and required product throughput. Other current research is focused on weed management solutions, cotton harvesting, planting and scouting operations. Encoders, inertial measurement units, GPS-enabled real-time kinetic positioners and stereo-cameras are the main sensors used for navigating rows of crops and providing data on crop yield, fruit location and abiotic/biotic plant stress.