Artificial Neural Network Based Automatic Emergency Landing Site Selection for UAVs and Highly Automated Aircraft

In this report an artificial neural network (ANN) based automated emergency landing site selection system for unmanned aerial vehicle (UAV) and general aviation (GA) is described. The system aims increase safety of UAV operation by emulating pilot decision making in emergency landing scenarios using an ANN to select a safe landing site from available candidates. The strength of an ANN to model complex input relationships makes it a perfect system to handle the multicriteria decision making (MCDM) process of emergency landing site selection. The ANN operates by identifying the more favorable of two landing sites when provided with an input vector derived from both landing site's parameters, the aircraft's current state and wind measurements. The system consists of a feed forward ANN, a pre-processor class which produces ANN input vectors and a class in charge of creating a ranking of landing site candidates using the ANN. The system was successfully implemented in C++ using the FANN C++ library and ROS. Results obtained from ANN training and simulations using randomly generated landing sites by a site detection simulator data verify the feasibility of an ANN based automated emergency landing site selection system.

Development and Simulation of a Variable Rate Controller for an Air search and Air Sampling Unmanned Aerial System

This report describes the development and simulation of a variable rate controller for a 6-degree of freedom nonlinear model. The variable rate simulation model represents an off the shelf autopilot. Flight experiment involves risks and can be expensive. Therefore a dynamic model to understand the performance characteristics of the UAS in mission simulation before actual flight test or to obtain parameters needed for the flight is important. The control and guidance is implemented in Simulink. The report tests the use of the model for air search and air sampling path planning. A GUI in which a set of mission scenarios, in which two experts (mission expert, i.e. air sampling or air search and an UAV expert) interact, is presented showing the benefits of the method.

Design and Simulation of a Solar Powered UAV for Remote Sensing Tasks Technical Report

This research deals with the development of a Solar-Powered UAV designed for remote sensing, in particular to the development of the autopilot sub-system and path planning. The design of the Solar-Powered UAS followed a systems engineering methodology, by first defining system architecture, and selecting each subsystem. Validation tests and integration of autopilot is performed, in order to evaluate the performances of each subsystem and to obtain a global operational system for data collection missions. The flight tests planning and simulation results are also explored in order to verify the mission capabilities using an autopilot on a UAS. The important aspect of this research is to develop a Solar-Powered UAS for the purpose of data collection and video monitoring, especially data and images from the ground; transmit to the GS (Ground Station), segment the collected data, and afterwards analyze it with a Matlab code.

Multi-Disciplinary Design and Simulation of a Fuel Cell Engine for a UAV

This report describes a methodology for the design and coupling of a proton exchange membrane (PEM) Fuel Cell to an Unmanned Aerial Vehicle (UAV). The report summarizes existing work in the field, the type of UAV and the mission requirements, design the fuel cell system, simulation environment, and compares endurance and range to when the aircraft is fitted with a conventional internal combustion engine (ICE).

Unmanned Aerial Vehicles (UAVs) and artificial intelligence revolutionizing wildlife monitoring and conservation

Surveying threatened and invasive species to obtain accurate population estimates is an important but challenging task that requires a considerable investment in time and resources. Estimates using existing ground-based monitoring techniques, such as camera traps and surveys performed on foot, are known to be resource intensive, potentially inaccurate and imprecise, and difficult to validate. Recent developments in unmanned aerial vehicles (UAV), artificial intelligence and miniaturized thermal imaging systems represent a new opportunity for wildlife experts to inexpensively survey relatively large areas. The system presented in this paper includes thermal image acquisition as well as a video processing pipeline to perform object detection, classification and tracking of wildlife in forest or open areas. The system is tested on thermal video data from ground based and test flight footage, and is found to be able to detect all the target wildlife located in the surveyed area. The system is flexible in that the user can readily define the types of objects to classify and the object characteristics that should be considered during classification.

Creative Arts in Counselling and Mental Health

Drawing on evidence-based discoveries in neuroscience, narrative psychology and creativity theory, this text explores the beneficial role of expressive arts within a recovery perspective. A framework of practice principles for the visual arts, creative writing, music, drama, dance, and digital storytelling is addressed across a number of settings and populations, providing readers with an accessible overview of theory and techniques relevant to counselling programs in the United States, Australia and the United Kingdom.

Uncertainty based online planning for UAV target finding in cluttered and GPS-denied environments

There are some scenarios in which Unmmaned Aerial Vehicle (UAV) navigation becomes a challenge due to the occlusion of GPS systems signal, the presence of obstacles and constraints in the space in which a UAV operates. An additional challenge is presented when a target whose location is unknown must be found within a confined space. In this paper we present a UAV navigation and target finding mission, modelled as a Partially Observable Markov Decision Process (POMDP) using a state-of-the-art online solver in a real scenario using a low cost commercial multi rotor UAV and a modular system architecture running under the Robotic Operative System (ROS). Using POMDP has several advantages to conventional approaches as they take into account uncertainties in sensor information. We present a framework for testing the mission with simulation tests and real flight tests in which we model the system dynamics and motion and perception uncertainties. The system uses a quad-copter aircraft with an board downwards looking camera without the need of GPS systems while avoiding obstacles within a confined area. Results indicate that the system has 100% success rate in simulation and 80% rate during flight test for finding targets located at different locations.

The effect of pressure and W-doping on the properties of ZnO thin films for NO2 gas sensing

Pure and W-doped ZnO thin films were obtained using magnetron sputtering at working pressures of 0.4 Pa and 1.33 Pa. The films were deposited on glass and alumina substrates at room temperature and subsequently annealed at 400oC for 1 hour in air. The effects of pressure and W-doping on the structure, chemical, optical and electronic properties of the ZnO films for gas sensing were examined. From AFM, the doped film deposited at higher pressure (1.33 Pa) has spiky morphology with much lower grain density and porosity compared to the doped film deposited at 0.4 Pa. The average gain size and roughness of the annealed films were estimated to be 65 nm and 2.2 nm, respectively with slightly larger grain size and roughness appeared in the doped films. From XPS the films deposited at 1.33 Pa favored the formation of adsorbed oxygen on the film surface and this has been more pronounced in the doped film which created active sites for OH adsorption. As a consequence the W-doped film deposited at 1.33 Pa was found to have lower oxidation state of W (35.1 eV) than the doped film deposited at 0.4 Pa (35.9 eV). Raman spectra indicated that doping modified the properties of the ZnO film and induced free-carrier defects. The transmittance of the samples also reveals an enhanced free-carrier density in the W-doped films. The refractive index of the pure film was also found to increase from 1.7 to 2.2 after W-doping whereas the optical band gap only slightly increased. The W-doped ZnO film deposited at 0.4 Pa appeared to have favorable properties for enhanced gas sensing. This film showed significantly higher sensing performance towards 5-10 ppm NO2 at lower operating temperature of 150oC most dominantly due to increased free-carrier defects achieved by W-doping.