A Framework for Multi-Agent UAV Exploration and Target-Finding in GPS-Denied and Partially Observable Environments.

The problem of multi-agent remote sensing for the purposes of finding survivors or surveying points of interest in GPS-denied and partially observable environments remains a challenge. This paper presents a framework for multi-agent target-finding using a combination of online POMDP based planning and Deep Reinforcement Learning based control. The framework is implemented considering planning and control as two separate problems. The planning problem is defined as a decentralised multi-agent graph search problem and is solved using a modern online POMDP solver. The control problem is defined as a local continuous-environment exploration problem and is solved using modern Deep Reinforcement Learning techniques. The proposed framework combines the solution to both of these problems and testing shows that it enables multiple agents to find a target within large, simulated test environments in the presence of unknown obstacles and obstructions. The proposed approach could also be extended or adapted to a number of time sensitive remote-sensing problems, from searching for multiple survivors during a disaster to surveying points of interest in a hazardous environment by adjusting the individual model definitions.

A Novel Methodology for Improving Plant Pest Surveillance in Vineyards and Crops Using UAV-Based Hyperspectral and Spatial Data.

Recent advances in remote sensed imagery and geospatial image processing using unmanned aerial vehicles (UAVs) have enabled the rapid and ongoing development of monitoring tools for crop management and the detection/surveillance of insect pests. This paper describes a (UAV) remote sensing-based methodology to increase the efficiency of existing surveillance practices (human inspectors and insect traps) for detecting pest infestations (e.g., grape phylloxera in vineyards). The methodology uses a UAV integrated with advanced digital hyperspectral, multispectral, and RGB sensors. We implemented the methodology for the development of a predictive model for phylloxera detection. In this method, we explore the combination of airborne RGB, multispectral, and hyperspectral imagery with ground-based data at two separate time periods and under different levels of phylloxera infestation. We describe the technology used-the sensors, the UAV, and the flight operations-the processing workflow of the datasets from each imagery type, and the methods for combining multiple airborne with ground-based datasets. Finally, we present relevant results of correlation between the different processed datasets. The objective of this research is to develop a novel methodology for collecting, processing, analising and integrating multispectral, hyperspectral, ground and spatial data to remote sense different variables in different applications, such as, in this case, plant pest surveillance. The development of such methodology would provide researchers, agronomists, and UAV practitioners reliable data collection protocols and methods to achieve faster processing techniques and integrate multiple sources of data in diverse remote sensing applications.

Enabling UAV Navigation with Sensor and Environmental Uncertainty in Cluttered and GPS-Denied Environments.

Unmanned Aerial Vehicles (UAV) can navigate with low risk in obstacle-free environments using ground control stations that plan a series of GPS waypoints as a path to follow. This GPS waypoint navigation does however become dangerous in environments where the GPS signal is faulty or is only present in some places and when the airspace is filled with obstacles. UAV navigation then becomes challenging because the UAV uses other sensors, which in turn generate uncertainty about its localisation and motion systems, especially if the UAV is a low cost platform. Additional uncertainty affects the mission when the UAV goal location is only partially known and can only be discovered by exploring and detecting a target. This navigation problem is established in this research as a Partially-Observable Markov Decision Process (POMDP), so as to produce a policy that maps a set of motion commands to belief states and observations. The policy is calculated and updated on-line while flying with a newly-developed system for UAV Uncertainty-Based Navigation (UBNAV), to navigate in cluttered and GPS-denied environments using observations and executing motion commands instead of waypoints. Experimental results in both simulation and real flight tests show that the UAV finds a path on-line to a region where it can explore and detect a target without colliding with obstacles. UBNAV provides a new method and an enabling technology for scientists to implement and test UAV navigation missions with uncertainty where targets must be detected using on-line POMDP in real flight scenarios.