Land monitoring is widely recognized as an invaluable tool to ensure situation awareness
for prevention, prediction and protection in almost any field when threats due to exogenous agents
may harm human safety and productivity. One of the applications in which monitoring systems can unleash
their full potential is agriculture, which accounts for 40% of the land usage on the entire planet.
The scarcity of infrastructure available on fields and the typical harshness and vastness of terrains make
it difficult to enable complete and continuous monitoring by skilled human personnel and calls for agile,
autonomous systems for accurate and precise inspection.
This project envisions the realization of a cooperative network of aerial sensing devices, capable of autonomous
and adaptive deployment over a field of interest, with the purpose of providing collaborative
heterogeneous sensing. The aerial monitoring network will enable threat and disease recognition, by autonomously
interacting with a complex and rich machine learning system which operates in a continuum
spectrum of fidelity, adaptively determined on the basis of the findings and of the uncertainty of detection
and related risk. On the basis of the output of the machine learning system, the aerial mobile sensors may
be called to more refined and complex missions on the field, to enhance network coverage of the field.
The combination of the two above autonomous systems, the autonomous aerial network and the machine
learning system, will enable monitoring at adaptive levels of accuracy for fast detection of diseased
crops, with identification of changes in the monitored features across the space and time domain, without
human guidance. The use of this system will enhance human performance by providing insight levels from
Umanned Aerial Vehicles (UAVs) that would be impossible for expert humans to see or record directly.
While the use of drone for precision agriculture is currently a hot research topic, the current project aims at advancing the state of the art by integrating two key ingredients:
1. the use of an autonomous squad of drones
2. the use of machine intelligence systems for the recognition of plants and related disease from cameras and processors located onboard the drones.
Autonomous path planning and task assignment on a squad of drones is something very new and unexplored so far.
The use of a machine intelligence system, with tunable fidelity, for recognition of plant diseases is also at a preliminary stage, and most of the work has been done with same height imaging, while the use of drone based imaging is still a challenge for the specific angle of sight which requires adapting existing images archives.
The results of the project are of interest to many other application scenario requiring situation awareness and preparedness. Monitoring systems are widely recognized to be an invaluable tool whenever surveillance, intrusion or hazard detection are required to ensure prevention, prediction and protection against critical events such as natural disasters or security threats.
The project focuses on the important application of crops in fields and ecosystems monitoring, with a large impact on food security, human safety, and global well being planet-wide. Additionally, the proposed system has the responsiveness, the robustness and the autonomous intelligence that make it suitable as well for other important applications such as disaster monitoring and homeland security.
The proposed monitoring systems will have a highly important impact in improving emergency response, providing critical information and minimizing societal crisis.
The project will also advance the current body of knowledge on monitoring systems, by providing high level scientific papers published in flagship international journals and conferences on heterogeneous network deployment, storage overflow prevention, topology improvement and real-time communication.
There are also other broader impacts of the project in the application area on which we mainly focused.
The project will use the archives of PlantVillage. PlantVillage has already provided a significant benefit to society by providing free, open access knowledge on plant health to over 3.5 million people around the world. PlantVillage is also a pioneer in Artificial Intellgence (AI) with the release of its AI algorithms, images and data to the public domain.
Our proposal seeks to extend the use of PlantVillage integrating AI decision making on crop diseases into
smart autonomous drone squads. Such an approach will immediately provide broader impacts.
Hence, besides the innovation in the realization of autonomous squad of drones for monitoring systems, the project will provide important innovations in the field of food security, as we will have a smart autonomous system collecting millions of data points on crop type and disease in real work farms.