An integrated modeling approach to assess the impact on road freight transport demand of allowing longer and heavier vehicles (LHVs) in Spain

The assessment on introducing Longer and Heavier Vehicles (LHVs) on the road freight transport demand is performed in this paper by applying an integrated modeling approach composed of a Random Utility-Based Multiregional Input-Output model (RUBMRIO) and a road transport network model. The approach strongly supports the concept that changes in transport costs derived from the LHVs allowance as well as the economic structure of regions have both direct and indirect effects on the road freight transport system. In addition, we estimate the magnitude and extent of demand changes in the road freight transportation system by using the commodity-based structure of the approach to identify the effect on traffic flows and on pollutant emissions over the whole network of Spain by considering a sensitivity analysis of the main parameters which determine the share of Heavy-Goods Vehicles (HGVs) and LHVs. The results show that the introduction of LHVs will strengthen the competitiveness of the road haulage sector by reducing costs, emissions, and the total freight vehicles required.

Online Learning-based Robust Visual Tracking for Autonomous Landing of Unmanned Aerial Vehicles

Autonomous landing is a challenging and important technology for both military and civilian applications of Unmanned Aerial Vehicles (UAVs). In this paper, we present a novel online adaptive visual tracking algorithm for UAVs to land on an arbitrary field (that can be used as the helipad) autonomously at real-time frame rates of more than twenty frames per second. The integration of low-dimensional subspace representation method, online incremental learning approach and hierarchical tracking strategy allows the autolanding task to overcome the problems generated by the challenging situations such as significant appearance change, variant surrounding illumination, partial helipad occlusion, rapid pose variation, onboard mechanical vibration (no video stabilization), low computational capacity and delayed information communication between UAV and Ground Control Station (GCS). The tracking performance of this presented algorithm is evaluated with aerial images from real autolanding flights using manually- labelled ground truth database. The evaluation results show that this new algorithm is highly robust to track the helipad and accurate enough for closing the vision-based control loop.

Robust Real-time Vision-based Aircraft Tracking From Unmanned Aerial Vehicles.

Aircraft tracking plays a key and important role in the Sense-and-Avoid system of Unmanned Aerial Vehicles (UAVs). This paper presents a novel robust visual tracking algorithm for UAVs in the midair to track an arbitrary aircraft at real-time frame rates, together with a unique evaluation system. This visual algorithm mainly consists of adaptive discriminative visual tracking method, Multiple-Instance (MI) learning approach, Multiple-Classifier (MC) voting mechanism and Multiple-Resolution (MR) representation strategy, that is called Adaptive M3 tracker, i.e. AM3. In this tracker, the importance of test sample has been integrated to improve the tracking stability, accuracy and real-time performances. The experimental results show that this algorithm is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant surrounding illumination, partial aircraft occlusion, blur motion, rapid pose variation and onboard mechanical vibration, low computation capacity and delayed information communication between UAVs and Ground Station (GS). To our best knowledge, this is the first work to present this tracker for solving online learning and tracking freewill aircraft/intruder in the UAVs.

A General Purpose Configurable Navigation Controller for Micro Aerial Multirotor Vehicles

In this paper, we consider the problem of autonomous navigation of multirotor platforms in GPS-denied environments. The focus of this work is on safe navigation based on unperfect odometry measurements, such as on-board optical flow measurements. The multirotor platform is modeled as a flying object with specific kinematic constraints that must be taken into account in order to obtain successful results. A navigation controller is proposed featuring a set of configurable parameters that allow, for instance, to have a configuration setup for fast trajectory following, and another to soften the control laws and make the vehicle navigation more precise and slow whenever necessary. The proposed controller has been successfully implemented in two different multirotor platforms with similar sensoring capabilities showing the openness and tolerance of the approach. This research is focused around the Computer Vision Group's objective of applying multirotor vehicles to civilian service applications. The presented work was implemented to compete in the International Micro Air Vehicle Conference and Flight Competition IMAV 2012, gaining two awards: the Special Award on "Best Automatic Performance - IMAV 2012" and the second overall prize in the participating category "Indoor Flight Dynamics - Rotary Wing MAV". Most of the code related to the present work is available as two open-source projects hosted in GitHub.

Online Learning-based Robust Visual Tracking for Autonomous Landing of Unmanned Aerial Vehicles

Autonomous landing is a challenging and important technology for both military and civilian applications of Unmanned Aerial Vehicles (UAVs). In this paper, we present a novel online adaptive visual tracking algorithm for UAVs to land on an arbitrary field (that can be used as the helipad) autonomously at real-time frame rates of more than twenty frames per second. The integration of low-dimensional subspace representation method, online incremental learning approach and hierarchical tracking strategy allows the autolanding task to overcome the problems generated by the challenging situations such as significant appearance change, variant surrounding illumination, partial helipad occlusion, rapid pose variation, onboard mechanical vibration (no video stabilization), low computational capacity and delayed information communication between UAV and Ground Control Station (GCS). The tracking performance of this presented algorithm is evaluated with aerial images from real autolanding flights using manually- labelled ground truth database. The evaluation results show that this new algorithm is highly robust to track the helipad and accurate enough for closing the vision-based control loop.

Real-Time Adaptive Multi-Classifier Multi-Resolution Visual Tracking Framework for Unmanned Aerial Vehicles

This paper presents a novel robust visual tracking framework, based on discriminative method, for Unmanned Aerial Vehicles (UAVs) to track an arbitrary 2D/3D target at real-time frame rates, that is called the Adaptive Multi-Classifier Multi-Resolution (AMCMR) framework. In this framework, adaptive Multiple Classifiers (MC) are updated in the (k-1)th frame-based Multiple Resolutions (MR) structure with compressed positive and negative samples, and then applied them in the kth frame-based Multiple Resolutions (MR) structure to detect the current target. The sample importance has been integrated into this framework to improve the tracking stability and accuracy. The performance of this framework was evaluated with the Ground Truth (GT) in different types of public image databases and real flight-based aerial image datasets firstly, then the framework has been applied in the UAV to inspect the Offshore Floating Platform (OFP). The evaluation and application results show that this framework is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant illumination, partial/full target occlusion, blur motion, rapid pose variation and onboard mechanical vibration, among others. To our best knowledge, this is the first work to present this framework for solving the online learning and tracking freewill 2D/3D target problems, and applied it in the UAVs.

Using the Cross-Entropy Method for Control Optimization: A Case Study of See-and-Avoid on Unmanned Aerial Vehicles

This paper presents an adaptation of the Cross-Entropy (CE) method to optimize fuzzy logic controllers. The CE is a recently developed optimization method based on a general Monte-Carlo approach to combinatorial and continuous multi-extremal optimization and importance sampling. This work shows the application of this optimization method to optimize the inputs gains, the location and size of the different membership functions' sets of each variable, as well as the weight of each rule from the rule's base of a fuzzy logic controller (FLC). The control system approach presented in this work was designed to command the orientation of an unmanned aerial vehicle (UAV) to modify its trajectory for avoiding collisions. An onboard looking forward camera was used to sense the environment of the UAV. The information extracted by the image processing algorithm is the only input of the fuzzy control approach to avoid the collision with a predefined object. Real tests with a quadrotor have been done to corroborate the improved behavior of the optimized controllers at different stages of the optimization process.

Estudio, ensamblaje, caracterización y ensayos de dos modelos reales de RPA

Un dron o un RPA (del inglés, Remote Piloted Aircraft) es un vehículo aéreo no tripulado capaz de despegar, volar y aterrizar de forma autónoma, semiautónoma o manual, siempre con control remoto. Además, toda aeronave de estas características debe ser capaz de mantener un nivel de vuelo controlado y sostenido. A lo largo de los años, estos aparatos han ido evolución tanto en aplicaciones como en su estética y características físicas, siempre impulsado por los requerimientos militares en cada momento. Gracias a este desarrollo, hoy en día los drones son uno más en la sociedad y desempeñan tareas que para cualquier ser humano serían peligrosas o difíciles de llevar a cabo. Debido a la reciente proliferación de los RPA, los gobiernos de los distintos países se han visto obligados a redactar nuevas leyes y/o modificar las ya existentes en relación a los diferentes usos del espacio aéreo para promover la convivencia de estas aeronaves con el resto de vehículos aéreos. El objeto principal de este proyecto es ensamblar, caracterizar y configurar dos modelos reales de dron: el DJI F450 y el TAROT t810. Para conseguir un montaje apropiado a las aplicaciones posteriores que se les va a dar, antes de su construcción se ha realizado un estudio individualizado en detalle de cada una de las partes y módulos que componen estos vehículos. Adicionalmente, se ha investigado acerca de los distintos tipos de sistemas de transmisión de control remoto, vídeo y telemetría, sin dejar de lado las baterías que impulsarán al aparato durante sus vuelos. De este modo, es sabido que los RPA están compuestos por distintos módulos operativos: los principales, todo aquel módulo para que el aparato pueda volar, y los complementarios, que son aquellos que dotan a cada aeronave de características adicionales y personalizadas que lo hacen apto para diferentes usos. A lo largo de este proyecto se han instalado y probado diferentes módulos adicionales en cada uno de los drones, además de estar ambos constituidos por distintos bloques principales, incluyendo el controlador principal: NAZA-M Lite instalado en el dron DJI F450 y NAZA-M V2 incorporado en el TAROT t810. De esta forma se ha podido establecer una comparativa real acerca del comportamiento de éstos, tanto de forma conjunta como de ambos controladores individualmente. Tras la evaluación experimental obtenida tras diversas pruebas de vuelo, se puede concluir que ambos modelos de controladores se ajustan a las necesidades demandadas por el proyecto y sus futuras aplicaciones, siendo más apropiada la elección del modelo M Lite por motivos estrictamente económicos, ya que su comportamiento en entornos recreativos es similar al modelo M V2. ABSTRACT. A drone or RPA (Remote Piloted Aircraft) is an unmanned aerial vehicle that is able to take off, to fly and to land autonomously, semi-autonomously or manually, always connected via remote control. In addition, these aircrafts must be able to keep a controlled and sustained flight level. Over the years, the applications for these devices have evolved as much as their aesthetics and physical features both boosted by the military needs along time. Thanks to this development, nowadays drones are part of our society, executing tasks potentially dangerous or difficult to complete by humans. Due to the recent proliferation of RPA, governments worldwide have been forced to draft legislation and/or modify the existing ones about the different uses of the aerial space to promote the cohabitation of these aircrafts with the rest of the aerial vehicles. The main objective of this project is to assemble, to characterize and to set-up two real drone models: DJI F450 and TAROT t810. Before constructing the vehicles, a detailed study of each part and module that composes them has been carried out, in order to get an appropriate structure for their expected uses. Additionally, the different kinds of remote control, video and telemetry transmission systems have been investigated, including the batteries that will power the aircrafts during their flights. RPA are made of several operative modules: main modules, i.e. those which make the aircraft fly, and complementary modules, that customize each aircraft and equip them with additional features, making them suitable for a particular use. Along this project, several complementary modules for each drone have been installed and tested. Furthermore, both are built from different main units, including the main controller: NAZA-M Lite installed on DJI F450 and NAZA-M V2 on board of TAROT t810. This way, it has been possible to establish an accurate comparison, related to the performance of both models, not only jointly but individually as well. After several flight tests and an experimental evaluation, it can be concluded that both main controller models are suitable for the requirements fixed for the project and the future applications, being more appropriate to choose the M Lite model strictly due to economic reasons, as its performance in recreational environment is similar to the M V2.