Automated Leaf-Level Inspection of Crops by Combining UAV and UGVs (PhenoRob Demonstrator)

Описание: Robotic systems play a major role for realizing the vision of sustainable crop production. While Unmanned Aerial Vehicles (UAVs) are increasingly used to monitor the health status of agricultural fields using sensors like RGB cameras, multi-spectral cameras, and LiDAR, it is often still necessary to literally walk into the field to do close-up inspections of individual plants or even leaves for the detection of diseases or nutrient deficiencies in early stages of plant growth. The main contribution of this work is demonstrating the integration of aerial and ground robotic systems to automate plant inspection processes, thereby enhancing efficiency in field monitoring tasks. A UAV identifies areas or plants of interest from higher altitudes whose coordinates are transferred to an Unmanned Ground Vehicle (UGV). The UGV then autonomously navigates to the specified location and a mounted robotic arm with five cameras captures close-range images with automatically optimized camera poses. The result is a high-resolution 3D reconstruction suitable for further plant analysis. This integration of UAV and UGV allows us to 'zoom in' on any coordinate in the field with a few centimeters of accuracy.