Small unmanned vehicles are used to provide the eye-in-the-sky alternative to monitoring and regulating traffic dynamically. Spatial-temporal visual data are collected in real-time and they are used to generate traffic-related statistical profiles, serving as inputs to traffic simulation models. Generated profiles, which are continuously updated, are used to calibrate traffic model parameters, to obtain more accurate and reliable simulation models, and for model modifications. This method overcomes limitations of existing traffic simulation models, which suffer from outdated data, poorly calibrated parameters, questionable accuracy and poor predictions of traffic patterns.

Today transportation systems are facing big transitions all over the world. We created fly overs, roads under the ground, bridges over the river and ocean to get efficient access and to increase the road connectivity. Our transportation system is more intelligent than ever. Our traffic signaling system became adaptive. Our vehicles equipped with new gadgets and we developed new tools for more efficient analysis of traffic. Our research relies on existing traffic infrastructure to generate better understanding of traffic. More specifically, this research focused on traffic and UAV cameras to extract information about the traffic. Our first goal was to create an automatic system to count the cars using traffic cameras. To achieve this goal, we implemented Background Subtraction Method (BSM) and OverFeat Framework. BSM compares consecutive frames to detect the moving objects. Because BSM only works for ideal lab conditions, therefor we implemented a Convolutional Neural Network (CNN) based classification algorithm called OverFeat Framework. We created different segments on the road in various lanes to tabulate the number of passing cars. We achieved 96.55% accuracy for car counting irrespective of different visibility conditions of the day and night. Our second goal was to find out traffic density. We implemented two CNN based algorithms: Single Shot Detection (SSD) and MobileNet-SSD for vehicle detection. These algorithms are object detection algorithms. We used traffic cameras to detect vehicles on the roads. We utilized road markers and light pole distances to determine distances on the road. Using the distance and count information we calculated density. SSD is a more resource intense algorithm and it achieved 92.97% accuracy. MobileNet-SSD is a lighter algorithm and it achieved 79.30% accuracy. Finally, from a moving platform we estimated the velocity of multiple vehicles. There are a lot of roads where traffic cameras are not available, also traffic monitoring is necessary for special events. We implemented Faster R-CNN as a detection algorithm and Discriminative Correlation Filter (with Channel and Spatial Reliability Tracking) for tracking. We calculated the speed information from the tracking information in our study. Our framework achieved 96.80% speed accuracy compared to manual observation of speeds. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2019. / FAU Electronic Theses and Dissertations Collection

Despite the explosion of popularity of UASs, and the recognition that such systems must find a way to safely operate alongside manned aviation, a literature review by this author as well as interviews with three commercial aerial photography companies in Tampa Bay, Florida, indicate that regulatory restrictions are still the greatest obstacle to law abiding commercial UAS operators. It can take six to eight months with a backlog of 12,000 waiver applications to get either a Part 333 or Part 107 exemption, which grants FAA permission for a commercial operator to fly a UAS inside controlled airspace (Gardner, 2018). A manned pilot can file a flight plan and hover a helicopter over the same area in just a few hours. The purpose of this research was to determine what industry experts perceive the future of UAS regulations hold, and how the industry will be impacted in both the short term of 5 years and less, and long-term of 5 years or more. UAS industry expert interviews were conducted in the “reflection of the meaning”, semi-structured style, with each interviewee given the latitude to discuss topics as they came to mind. A preset approved bank of questions helped to guide the interview, but in many cases as experts in the field, the interviewees naturally discussed the topics covered in the preset questions and the interview adapted to avoid unnecessary repetition. One interview was conducted in-person, but the rest were via phone calls due to geographical separation.

In this thesis, an architecture for the adaptive mode transition control of unmanned aerial vehicles (UAV) is presented. The proposed architecture consists of three levels: the highest level is occupied by mission planning routines where information about way points the vehicle must follow is processed. The middle level uses a trajectory generation component to coordinate the task execution and provides set points for low-level stabilizing controllers. The adaptive mode transitioning control algorithm resides at the lowest level of the hierarchy consisting of a mode transitioning controller and the accompanying adaptation mechanism. The mode transition controller is composed of a mode transition manager, a set of local controllers, a set of active control models, a set point filter, a state filter, an automatic trimming mechanism and a dynamic compensation filter. Local controllers operate in local modes and active control models operate in transitions between two local modes. The mode transition manager determines the actual mode of operation of the vehicle based on a set of mode membership functions and activates a local controller or an active control model accordingly. The adaptation mechanism uses an indirect adaptive control methodology to adapt the active control models. For this purpose, a set of plant models based on fuzzy neural networks is trained based on input/output information from the vehicle and used to compute sensitivity matrices providing the linearized models required by the adaptation algorithms. The effectiveness of the approach is verified through software-in-the-loop simulations, hardware-in-the-loop simulations and flight testing.

Unmanned Aerial Vehicles (UAVs) are capable of placing sensors at unique vantage points without endangering a pilot. Therefore, they are well suited to perform target tracking missions. However, performing the mission can be burdensome for the operator. To track a target, the operator must estimate the position of the target from the incoming video stream, update the orientation of the camera, and move the vehicle to an appropriate vantage point. The purpose of the research in this thesis is to provide a target tracking system that performs these tasks automatically in real-time. The first task, which receives the majority of the attention, is estimating the position of the target within the incoming video stream. Because of the inherent clutter in the imagery, the resulting probability distributions are typically non-Gaussian and multi-modal. Therefore, classical state estimation techniques, such as the Kalman filter and its variants are unacceptable solutions. The particle filter has become a popular alternative since it is able to approximate the multi-modal distributions using a set of samples, and it is used as part of this research. To improve the performance of the filter and manage the inherently large computational burden a neural network is used to estimate the performance of the particle filter. The filter parameters are then changed in response to the performance. Once the position of the target is estimated in the frame, it is projected on the ground using the camera orientation and vehicle attitude and input into a linear predictor. The output of the predictor is used to update the orientation of the camera and vehicle waypoints. Through offline, simulation, and flight testing, the approach is shown to provide a powerful visual tracking system for use onboard the GTMax unmanned research helicopter.

Synthetic jet actuators for flow control applications have been an active topic of experimental research since the 90’s. Numerical simulations have become an important complement of that experimental work, providing detailed information of the dynamics of the controlled flow. This study is part of the AVOCET (Adaptive VOrticity Control Enabled flighT) project and is intended to provide computational support for the design and evaluation of closed-loop flow control with synthetic jet actuators for small scale Unmanned Aerial Vehicles (UAVs). The main objective is to analyze active flow control of a NACA4415 airfoil with tangential synthetic jets via computational modeling. A hybrid Reynolds-Averaged Navier-Stokes/Large Eddy Simulation (RANS/LES) turbulent model (called Delayed Detached-Eddy Simulation-DDES) was implemented in CDP, a kinetic energy conserving Computational Fluid Dynamics (CFD) code. CDP is a parallel unstructured grid incompressible flow solver, developed at the Center for Integrated Turbulence Simulations (CITS) at Stanford University. Two models of synthetic jet actuators have been developed and validated. The first is a detailed model in which the flow in and out of the actuator cavity is modeled. A second less costly model (RSSJ) was also developed in which the Reynolds stress produced by the actuator is modeled, based on information from the detailed model. Several static validation test cases at different angle of attack with modified NACA 4415 and Dragon Eye airfoils were performed. Numerical results show the effects of the actuators on the vortical structure of the flow, as well as on the aerodynamic properties. The main effect of the actuation on the time averaged vorticity field is a bending of the separation shear layer from the actuator toward the airfoil surface, resulting in changes in the aerodynamic properties. Full actuation of the suction side actuator reduces the pitching moment and increases the lift force, while the pressure side actuator increases the pitching moment and reduces the lift force. These observations are in agreement with experimental results. The effectiveness of the actuator is measured by the change in the aerodynamic properties of the airfoil in particular the lift ([Delta]C[subscript t]) and moment ([Delta]C[subscript m]) coefficients. Computational results for the actuator effectiveness show very good agreement with the experimental values (over the range of −2° to 10°). While the actuation modifies the global pressure distribution, the most pronounced effects are near the trailing edge in which a spike in the pressure coefficient (C[subscript p]) is observed. The local reduction of C[subscript p], for both the suction side and pressure side actuators, at x/c = 0.96 (the position of the actuators) is about 0.9 with respect to the unactuated case. This local reduction of the pressure is associated with the trapped vorticity and flow acceleration close to the trailing edge. The RSSJ model is designed to capture the synthetic jet time averaged behavior so that the high actuation frequencies are eliminated. This allows the time step to be increased by a factor of 5. This ad hoc model is also tested in dynamic simulations, in which its capacity to capture the detail model average performance was demonstrated. Finally, the RSSJ model was extended to a different airfoil profile (Dragon Eye) with good results. / text

Remote sensing has been demonstrated an important tool in agricultural and natural resource management and research applications, however there are limitations that exist with traditional platforms (i.e., hand held sensors, linear moves, vehicle mounted, airplanes, remotely piloted vehicles (RPVs), unmanned aerial vehicles (UAVs) and satellites). Rapid technological advances in electronics, computers, software applications, and the aerospace industry have dramatically reduced the cost and increased the availability of remote sensing technologies.Remote sensing imagery vary in spectral, spatial, and temporal resolutions and are available from numerous providers. Appendix A presented results of a test project that acquired high-resolution aerial photography with a RPV to map the boundary of a 0.42 km2 fire area. The project mapped the boundaries of the fire area from a mosaic of the aerial images collected and compared this with ground-based measurements. The project achieved a 92.4% correlation between the aerial assessment and the ground truth data.Appendix B used multi-objective analysis to quantitatively assess the tradeoffs between different sensor platform attributes to identify the best overall technology. Experts were surveyed to identify the best overall technology at three different pixel sizes.Appendix C evaluated the positional accuracy of a relatively low cost UAV designed for high resolution remote sensing of small areas in order to determine the positional accuracy of sensor readings. The study evaluated the accuracy and uncertainty of a UAV flight route with respect to the programmed waypoints and of the UAV's GPS position, respectively. In addition, the potential displacement of sensor data was evaluated based on (1) GPS measurements on board the aircraft and (2) the autopilot's circuit board with 3-axis gyros and accelerometers (i.e., roll, pitch, and yaw). The accuracies were estimated based on a 95% confidence interval or similar methods. The accuracy achieved in the second and third manuscripts demonstrates that reasonably priced, high resolution remote sensing via RPVs and UAVs is practical for agriculture and natural resource professionals.

This thesis is divided into two parts that each is concerned with a specific problem. The problem under consideration in the first part is to find suitable graph representations, abstractions, cost measures and algorithms for calculating placements of unmanned aerial vehicles (UAVs) such that they can keep one or several static targets under constant surveillance. Each target is kept under surveillance by a surveillance UAV, which transmits information, typically real time video, to a relay UAV. The role of the relay UAV is to retransmit the information to another relay UAV, which retransmits it again to yet another UAV. This chain of retransmission continues until the information eventually reaches an operator at a base station. When there is a single target, then all Pareto-optimal solutions, i.e. all relevant compromises between quality and the number of UAVs required, can be found using an efficient new algorithm. If there are several targets, the problem becomes a variant of the Steiner tree problem and to solve this problem we adapt an existing algorithm to find an initial tree. Once it is found, we can further improve it using a new algorithm presentedin this thesis. The second problem is optimization of time-consuming problems where the objective function is seen as a black box, where the input parameters are sent and a function valueis returned. This has the important implication that no gradient or Hessian information is available. Such problems are common when simulators are used to perform advanced calculations such as crash test simulations of cars, dynamic multibody simulations etc. It is common that a single function evaluation takes several hours. Algorithms for solving such problems can be broadly divided into direct search algorithms and model building algorithms. The first kind evaluates the objective function directly, whereas the second kind builds a model of the objective function, which is then optimized in order to find a new point where it is believed that objective function has agood value. Then the objective function is evaluated in that point. Since the objective function is very time-consuming, it is common to focus on minimizing the number of function evaluations. However, this completely disregards the possibility to perform calculations in parallel and to exploit this we investigate different ways parallelization can be used in model-building algorithms. Some of the ways to do this is to use several starting points, generate several new points in each iteration, new ways of predicting a point’s value and more. We have implemented the parallel extensions in one of the state of the art algorithms for derivative-free optimization and report results from testing on synthetic benchmarksas well as from solving real industrial problems.

This thesis presents the development of small, inexpensive unmanned aerial vehicles (UAVs) to achieve autonomous fight. Fixed wing hobby model planes are modified and instrumented to form experimental platforms. Different sensors employed to collect the flight data are discussed along with their calibrations. The time constant and delay for the servo-actuators for the platform are estimated. Two different data collection and processing units based on micro-controller and PC104 architectures are developed and discussed. These units are also used to program the identification and control algorithms. Flight control of fixed wing UAVs is a challenging task due to the coupled, time-varying, nonlinear dynamic behaviour. One of the possible alternatives for the flight control system is to use the intelligent adaptive control techniques that provide online learning capability to cope with varying dynamics and disturbances. Neural network based indirect adaptive control strategy is applied for the current work. The two main components of the adaptive control technique are the identification block and the control block. Identification provides a mathematical model for the controller to adapt to varying dynamics. Neural network based identification provides a black-box identification technique wherein a suitable network provides prediction capability based upon the past inputs and outputs. Auto-regressive neural networks are employed for this to ensure good retention capabilities for the model that uses the past outputs and inputs along with the present inputs. Online and offline identification of UAV platforms are discussed based upon the flight data. Suitable modifications to the Levenberg-Marquardt training algorithm for online training are proposed. The effect of varying the different network parameters on the performance of the network are numerically tested out. A new performance index is proposed that is shown to improve the accuracy of prediction and also reduces the training time for these networks. The identification algorithms are validated both numerically and flight tested. A hardware-in-loop simulation system has been developed to test the identification and control algorithms before flight testing to identify the problems in real time implementation on the UAVs. This is developed to keep the validation process simple and a graphical user interface is provided to visualise the UAV flight during simulations. A dual neural network controller is proposed as the adaptive controller based upon the identification models. This has two neural networks collated together. One of the neural networks is trained online to adapt to changes in the dynamics. Two feedback loops are provided as part of the overall structure that is seen to improve the accuracy. Proofs for stability analysis in the form of convergence of the identifier and controller networks based on Lyapunov's technique are presented. In this analysis suitable bounds on the rate of learning for the networks are imposed. Numerical results are presented to validate the adaptive controller for single-input single-output as well as multi-input multi-output subsystems of the UAV. Real time validation results and various flight test results confirm the feasibility of the proposed adaptive technique as a reliable tool to achieve autonomous flight. The comparison of the proposed technique with a baseline gain scheduled controller both in numerical simulations as well as test flights bring out the salient adaptive feature of the proposed technique to the time-varying, nonlinear dynamics of the UAV platforms under different flying conditions.

Veículos aéreos não-tripulados (VANTs) são relativamente recentes no meio acadêmico, onde muitas tecnologias e algoritmos vêm sendo pesquisados e desenvolvidos. A engenharia de software apliacada a este âmbito possui poucas abordagens em relação a sistemas autônomos e inteligentes, enquanto que sistemas multi-agentes e a programação orientada a agentes vêm sendo cada vez mais utilizadas. Este trabalho foca na aplicação do paradigma da programação orientada a agentes para o controle de VANTs, de modo a conceber um framework e utilizar arquitetura, teoria e ferramentas orientados a agentes como forma de prover uma abstração mais sofisticada para a programação de comportamentos inteligentes em VANTs. Na pesquisa, propõem-se o modelo UAVAS – Unmanned Aerial Vehicles AgentSpeak que é um framework de programação de comportamentos para VANTs que possui um modelo de abstração de veículos aéreos tripulados para veículos aéreos não-tripulados. Ao final, a pesquisa foi avaliada e validada por meio de resultados obtidos em simulações com a infraestrutura implementada. Dois estudos de caso foram realizados, um com ênfase nas comunicações inter-VANTs e cooperação de time, e outro com ênfase nas verificações dos mapeamentos de sinais com o envio de dados da infraestrutura. Para cada um dos casos, simuladores específicos foram criados no intuito de observar as características pertinentes de cada estudo de caso. / Unmanned aerial vehicles (UAVs) are relatively new in civilian context, where many technologies and algorithms have been the focus at much research and development. Software engineering applied to this field has few approaches in relation to autonomous systems and intelligent behavior development, while multi-agent system and agent-oriented programming are being increasingly used. This work focuses on applying the paradigm of agent-oriented programming for the control of UAVs, in order to design a framework and use architecture, theory and agent oriented tools as a way to provide a more sophisticated abstraction for programming intelligent behaviors in UAVs . The main contribution of this work is an architecture that allows the use of the Jason platform to program multiagent system which can control teams of autonomous unmanned aerial vehicles. In this research, we propose the UAVAS - Unmanned Aerial Vehicles AgentSpeak model, which is a framework to program intelligent behaviors to UAVs and owns an abstraction model of manned aircraft to unmanned aerial vehicles. At the end, the survey was evaluated and validated by means of results from simulations in the implemented infrastructure. Two case studies were performed, with emphasis on inter-UAV communication and cooperation of team, and the another one focusing on mapping verifications of data signals sent to the infrastructure. For each case, specific simulators have been created in order to observe the relevant characteristics of each case study.