No description available.

Tesis por compendio / [ES] Debido a la creciente popularidad sobre la variedad de los Vehículos No Tripulados tanto en el campo militar como en el comercial, y de sus capacidades para navegar por diversos entornos, ya sean terrestres, aéreos o marinos, se evidencia que la clásica planificación de trayectorias y movimientos bidimensionales 2D podría no ser suficiente en un futuro inmediato. De esta manera, se debe resaltar que el presente trabajo aborda el problema de los Vehículos Aéreos No Tripulados (UAVs) de ala fija. En este sentido, la necesidad de encontrar una trayectoria navegable en el espacio euclídeo 3D se hace cada vez más necesario. En el caso de los UAV, considerar su cinemática para generar trayectorias suaves en tres dimensiones puede tener un interés significativo para la navegación autónoma aérea. Finalmente, los beneficios adicionales que se pueden producir son importantes. La principal dificultad de este problema es que los vehículos aéreos de características no-holonómicas se ven obligados a avanzar sin la posibilidad de detenerse a través de trayectorias 3D con curvaturas limitadas. En este sentido, se ha investigado la manera de proporcionar una completa caracterización de trayectorias óptimas para UAVs con un radio de giro limitado que se mueve en el plano tridimensional a una velocidad constante. Para completar tales tareas, un planificador de trayectorias no sólo debe proporcionar rutas tridimensionales para alcanzar una posición de destino sin colisionar con obstáculos, sino también debe asegurar que tal trayectoria sea adecuada para los UAVs que poseen propiedades cinemáticas específicas. Por lo tanto, el desarrollo del trabajo ha completado la algoritmia que genera una trayectoria discreta tridimensional al definir un conjunto de puntos 3D, resultantes de una división del espacio euclídeo tridimensional de manera dinámica, determinando las mejores opciones de avance, evitando analizar cada espacio del entorno completo. De esta manera, partiendo de los puntos 3D resultantes de la planificación de trayectoria tridimensional, se ha generado una trayectoria en forma de curva suave construida en función de las limitaciones de giro del UAV (resaltando que es difícil asegurar que el camino resultante cumpla con las restricciones cinemáticas en las tres dimensiones simultáneamente). Finalmente, es importante destacar que a menudo las restricciones mencionadas se calculan secuencialmente y de forma bidimensional, sobre un par de dimensiones desacopladas, lo que limita la capacidad de optimización. Para todo ello, se ha desarrollado un algoritmo de suavizado para un planificador de trayectorias que considera las restricciones cinemáticas tridimensionales completas sin desacoplar las dimensiones. / [CA] Debut a la creixent popularitat sobre la varietat dels Vehicles No Tripulats tant en el camp militar com en el comercial, i de les seves capacitats per navegar per diversos entorns, ja siguin terrestres, aeris o marins, s'evidencia que la clàssica planificació de trajectòries i moviments bidimensionals 2D podria no ser suficient en un futur immediat. D'aquesta manera, s'ha de ressaltar que el present treball aborda el problema dels Vehicles Aeris No Tripulats (UAV) d'ala fixa. En aquest sentit, la necessitat de trobar una trajectòria navegable en l'espai euclidià 3D es fa cada vegada més necessari. En el cas dels UAV, considerar la seva cinemàtica per generar trajectòries suaus en tres dimensions pot tenir un interès significatiu per a la navegació autònoma aèria. Finalment, els beneficis addicionals que es poden produir són importants. La principal dificultat d'aquest problema és que els vehicles aeris de característiques no-holonómicas es veuen obligats a avançar sense la possibilitat de detenir-se a través de trajectòries 3D amb curvatures limitades. En aquest sentit, s'ha investigat la manera de proporcionar una completa caracterització de trajectòries òptimes per UAVs amb un radi de gir limitat que es mou en el pla tridimensional a una velocitat constant. Per completar aquestes tasques, un planificador de trajectòries no només ha de proporcionar rutes tridimensionals per assolir una posició de destinació sense col·lisionar amb obstacles, sinó també ha d'assegurar que tal trajectòria sigui adequada per als UAVs que posseeixen propietats cinemàtiques específiques. Per tant, el desenvolupament de la feina ha completat la algorísmia que genera una trajectòria discreta tridimensional a l'definir un conjunt de punts 3D, resultants d'una divisió de l'espai euclidià tridimensional de manera dinàmica, determinant les millors opcions d'avanç, evitant analitzar cada espai de l' entorn complet. D'aquesta manera, partint dels punts 3D resultants de la planificació de trajectòria tridimensional, s'ha generat una trajectòria en forma de corba suau construïda en funció de les limitacions de gir de l'UAV (ressaltant que és difícil assegurar que el camí resultant compleixi amb les restriccions cinemàtiques en les tres dimensions simultàniament). Finalment, és important destacar que sovint les restriccions esmentades es calculen seqöencialment i de forma bidimensional, sobre un parell de dimensions desacoblades, el que limita la capacitat d'optimització. Per tot això, s'ha desenvolupat un algoritme de suavitzat per a un planificador de trajectòries que considera les restriccions cinemàtiques tridimensionals completes sense desacoblar les dimensions. / [EN] Due to the growing popularity of the variety of Unmanned Vehicles in both the military and commercial fields, and their capabilities to navigate diverse environments, whether land, air or sea, it is evident that the classic two-dimensional 2D trajectory and motion planning may not be enough in the near future. Thus, it should be noted that this paper addresses the problem of fixed-wing Unmanned Aerial Vehicles (UAVs). In this sense, the need to find a navigable path in 3D Euclidean space becomes more and more necessary. In the case of UAVs, considering their kinematics to generate smooth trajectories in three dimensions may be of significant interest for autonomous air navigation. Finally, the additional benefits that can be produced are important. The main difficulty of this problem is that air vehicles with non-holonomic characteristics are forced to advance without the possibility of stopping through 3D trajectories with limited curvatures. In this regard, research has been conducted to provide a complete characterization of optimal trajectories for UAVs with a limited turning radius that move in the 3D plane at a constant speed. To complete such tasks, a path planner must not only provide three-dimensional paths to reach a target position without colliding with obstacles, but must also ensure that such a path is suitable for UAVs that possess specific kinematic properties. Therefore, the development of the work has completed the algorithm that generates a discrete three-dimensional path by defining a set of 3D points, resulting from a division of the three-dimensional Euclidean space in a dynamic way, determining the best forward options, avoiding to analyze each space of the whole environment. In this way, starting from the 3D points resulting from the three-dimensional path planning, a smooth curve path has been generated, built according to the UAV turning constraints (highlighting that it is difficult to ensure that the resulting path meets the kinematic constraints in the three dimensions simultaneously). Finally, it is important to note that often the constraints mentioned are calculated sequentially and in a two-dimensional shape, on a pair of decoupled dimensions, which limits the ability to optimize. For all this, a smoothing algorithm has been developed for a path planner that considers the complete three-dimensional kinematic constraints without decoupling the dimensions. / Este trabajo ha sido parcialmente financiado por el Gobierno de España a través del Ministerio de Economía y Competitividad bajo el proyecto de Investigación DP I2015−71443−R, y por la administración local de la Generalitat Valenciana a través de los proyectos GV /2017/029 y AICO/2019/055. El autor ha sido beneficiario de una beca otorgada por el Instituto de Fomento al Talento Humano (IFTH) (2015−AR2Q9209) a través del Gobierno de Ecuador. / Samaniego Riera, FE. (2021). Diseño de nuevos algoritmos de guiado y navegación con evasión de colisiones para vehículos aéreos no tripulados [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/161274 / Compendio

<p>Cereal rye (<i>Secale cereale</i>, L., CR) is the most commonly utilized cover crop species within the United States. Yet, the total land area planted to CR on an annual basis remains relatively low despite its numerous proven environmental benefits. The relatively low rates of CR adoption could be due to a dearth of knowledge surrounding certain agronomic and economic components of CR adoption. Currently, there exists knowledge gaps within the scientific literature regarding CR performance, N cycling, and associated economic risk. <a>Thus, to address the above-mentioned knowledge gaps, three individual studies were developed to: i) investigate the fate of scavenged CR nitrogen (N) amongst soil N pools, ii) assess the suitability of visible-spectrum vegetation indices (VIs) to predict CR biomass and nutrient accumulation (BiNA), and iii) characterize the economic risk of CR adoption at a regional scale over time.</a></p> <p>In the first study, ¹⁵N, a stable isotope of N, was used in an aerobic incubation to track the fate of CR root and shoot N among the soil microbial biomass, inorganic, and organic N pools, as well as explore CR N bioavailability over a simulated corn growing season. In this study, the C:N ratio of the shoot residues was 16:1 and the roots was 31:1 and differences in residue quality affected the dynamics of CR N release from each residue type. On average, 14% of whole plant CR N was recovered in the soil inorganic N pool at the final sample date. Correspondingly, at the final sampling date 53%, 33%, and less than 1% of whole plant CR N was recovered as soil organic N, undecomposed residue, and as microbial biomass N, respectively. Most CR N remained unavailable to plants during the first cash crop growing season subsequent to termination. This knowledge could support the advancement of N fertilizer management strategies for cropping systems containing cereal rye.</p> <p>In the second study, a commercially available unmanned aerial vehicle (UAV) outfitted with a standard RGB sensor was used to collect aerial imagery of growing CR from which visible-spectrum VIs were computed. Computed VIs were then coupled with weather and geographic data using linear multiple regression to produce prediction models for CR biomass, carbon (C), N, phosphorus (P), potassium (K), and sulfur (S). Five visible-spectrum VIs (Visible Atmospherically Resistant Index (VARI), Green Leaf Index (GLI), Modified Green Red Vegetation Index (MGRVI), Red Green Blue Vegetation Index (RGBVI), and Excess of Green (ExG)) were evaluated and the results determined that MGRVI was the best predictor for CR biomass, C, K, and S and that RGBVI was the best predictor for CR N and P. Furthermore, the final prediction models for the VIs selected as the best predictors developed in this study performed satisfactorily in the prediction of CR biomass, C, N, P, K, and S producing adjusted R² values of 0.79, 0.79, 0.75, 0.81, 0.81, and 0.78, respectively. The results of this study have the potential to aid producers in making informed decisions regarding CR and fertility management. </p> <p>In the final study, agronomic data for corn and soybean cropping systems with and without CR was collected from six states (Illinois, Indiana, Iowa, Minnesota, Missouri, and Wisconsin) and used within a Monte-Carlo stochastic simulation to characterize the economic risk of adopting CR at a regional scale over time. The results of this study indicate that average net returns to CR are always negative regardless of CR tenure primarily due to added costs and increased variability in cash crop grain yields associated with CR adoption. Further, the results demonstrate that the additional risk assumed by adopting CR is not adequately compensated for with current CR adoption incentive programs and that the risk premium necessary can be 1.7 to 15 times greater than existing incentive payments. Knowledge gained from this study could be used to reimagine current incentive programs to further promote adoption of CR.</p>

General aircraft dynamic stability theory was used to predict the natural frequencies, damping ratios and time constants of the dynamic modes for three specific small UAVs with wingspans on the scale from 0.6 meters to 1.2 meters. Using USAF DatCom methods, a spreadsheet program for predicting the dynamic stability and handling qualities of small UAVs was created for use in the design stage of new small UAV concept development. This program was verified by inputting data for a Cessna-182, and by then comparing the program output with that of a similar program developed by DAR Corporation. Predictions with acceptable errors were made for all of the dynamic modes except for the spiral mode. The design tool was also used to verify and develop dynamic stability and handling qualities design guidelines for small UAV designers. Using this design tool, it was observed that small UAVs tend to exhibit higher natural frequencies of oscillation for all of the dynamic modes. Comparing the program outputs with military handling qualities specifications, the small UAVs at standard configurations fell outside the range of acceptable handling qualities for short-period mode natural frequency, even though multiple test pilots rated the flying qualities as acceptable. Using dynamic scaling methods to adjust the current military standards for the short period mode, a new scale was proposed specifically for small UAVs. This scale was verified by conducting flight tests of three small UAVs at various configurations until poor handling qualities were observed. These transitions were observed to occur at approximately the boundary predicted by the new, adjusted scale.

Tesis por compendio / [ES] El advenimiento de los Large Language Models (LLMs) marca una fase transformadora en el campo de la Inteligencia Artificial (IA), significando el cambio hacia sistemas inteligentes y autónomos capaces de una comprensión y toma de decisiones complejas. Esta tesis profundiza en las capacidades multifacéticas de los LLMs, explorando sus posibles aplicaciones en la optimización de decisiones, la comprensión de escenas y tareas avanzadas de resumen de video en diversos contextos. En el primer segmento de la tesis, el foco está en la comprensión semántica de escenas de Vehículos Aéreos No Tripulados (UAVs). La capacidad de proporcionar instantáneamente datos de alto nivel y señales visuales sitúa a los UAVs como plataformas ideales para realizar tareas complejas. El trabajo combina el potencial de los LLMs, los Visual Language Models (VLMs), y los sistemas de detección objetos de última generación para ofrecer descripciones de escenas matizadas y contextualmente precisas. Se presenta una implementación práctica eficiente y bien controlada usando microdrones en entornos complejos, complementando el estudio con métricas de legibilidad estandarizadas propuestas para medir la calidad de las descripciones mejoradas por los LLMs. Estos avances podrían impactar significativamente en sectores como el cine, la publicidad y los parques temáticos, mejorando las experiencias de los usuarios de manera exponencial. El segundo segmento arroja luz sobre el problema cada vez más crucial de la toma de decisiones bajo incertidumbre. Utilizando el problema de Multi-Armed Bandits (MAB) como base, el estudio explora el uso de los LLMs para informar y guiar estrategias en entornos dinámicos. Se postula que el poder predictivo de los LLMs puede ayudar a elegir el equilibrio correcto entre exploración y explotación basado en el estado actual del sistema. A través de pruebas rigurosas, la estrategia informada por los LLMs propuesta demuestra su adaptabilidad y su rendimiento competitivo frente a las estrategias convencionales. A continuación, la investigación se centra en el estudio de las evaluaciones de bondad de ajuste de las Generative Adversarial Networks (GANs) utilizando la Signature Transform. Al proporcionar una medida eficiente de similitud entre las distribuciones de imágenes, el estudio arroja luz sobre la estructura intrínseca de las muestras generadas por los GANs. Un análisis exhaustivo utilizando medidas estadísticas como las pruebas de Kruskal-Wallis proporciona una comprensión más amplia de la convergencia de los GANs y la bondad de ajuste. En la sección final, la tesis introduce un nuevo benchmark para la síntesis automática de vídeos, enfatizando la integración armoniosa de los LLMs y la Signature Transform. Se propone un enfoque innovador basado en los componentes armónicos capturados por la Signature Transform. Las medidas son evaluadas extensivamente, demostrando ofrecer una precisión convincente que se correlaciona bien con el concepto humano de un buen resumen. Este trabajo de investigación establece a los LLMs como herramientas poderosas para abordar tareas complejas en diversos dominios, redefiniendo la optimización de decisiones, la comprensión de escenas y las tareas de resumen de video. No solo establece nuevos postulados en las aplicaciones de los LLMs, sino que también establece la dirección para futuros trabajos en este emocionante y rápidamente evolucionante campo. / [CA] L'adveniment dels Large Language Models (LLMs) marca una fase transformadora en el camp de la Intel·ligència Artificial (IA), significat el canvi cap a sistemes intel·ligents i autònoms capaços d'una comprensió i presa de decisions complexes. Aquesta tesi profunditza en les capacitats multifacètiques dels LLMs, explorant les seues possibles aplicacions en l'optimització de decisions, la comprensió d'escenes i tasques avançades de resum de vídeo en diversos contexts. En el primer segment de la tesi, el focus està en la comprensió semàntica d'escenes de Vehicles Aeris No Tripulats (UAVs). La capacitat de proporcionar instantàniament dades d'alt nivell i senyals visuals situa els UAVs com a plataformes ideals per a realitzar tasques complexes. El treball combina el potencial dels LLMs, els Visual Language Models (VLMs), i els sistemes de detecció d'objectes d'última generació per a oferir descripcions d'escenes matisades i contextualment precises. Es presenta una implementació pràctica eficient i ben controlada usant microdrons en entorns complexos, complementant l'estudi amb mètriques de llegibilitat estandarditzades proposades per a mesurar la qualitat de les descripcions millorades pels LLMs. Aquests avenços podrien impactar significativament en sectors com el cinema, la publicitat i els parcs temàtics, millorant les experiències dels usuaris de manera exponencial. El segon segment arroja llum sobre el problema cada vegada més crucial de la presa de decisions sota incertesa. Utilitzant el problema dels Multi-Armed Bandits (MAB) com a base, l'estudi explora l'ús dels LLMs per a informar i guiar estratègies en entorns dinàmics. Es postula que el poder predictiu dels LLMs pot ajudar a triar l'equilibri correcte entre exploració i explotació basat en l'estat actual del sistema. A través de proves rigoroses, l'estratègia informada pels LLMs proposada demostra la seua adaptabilitat i el seu rendiment competitiu front a les estratègies convencionals. A continuació, la recerca es centra en l'estudi de les avaluacions de bondat d'ajust de les Generative Adversarial Networks (GANs) utilitzant la Signature Transform. En proporcionar una mesura eficient de similitud entre les distribucions d'imatges, l'estudi arroja llum sobre l'estructura intrínseca de les mostres generades pels GANs. Una anàlisi exhaustiva utilitzant mesures estadístiques com les proves de Kruskal-Wallis proporciona una comprensió més àmplia de la convergència dels GANs i la bondat d'ajust. En la secció final, la tesi introdueix un nou benchmark per a la síntesi automàtica de vídeos, enfatitzant la integració harmònica dels LLMs i la Signature Transform. Es proposa un enfocament innovador basat en els components harmònics capturats per la Signature Transform. Les mesures són avaluades extensivament, demostrant oferir una precisió convincent que es correlaciona bé amb el concepte humà d'un bon resum. Aquest treball de recerca estableix els LLMs com a eines poderoses per a abordar tasques complexes en diversos dominis, redefinint l'optimització de decisions, la comprensió d'escenes i les tasques de resum de vídeo. No solament estableix nous postulats en les aplicacions dels LLMs, sinó que també estableix la direcció per a futurs treballs en aquest emocionant i ràpidament evolucionant camp. / [EN] The advent of Large Language Models (LLMs) marks a transformative phase in the field of Artificial Intelligence (AI), signifying the shift towards intelligent and autonomous systems capable of complex understanding and decision-making. This thesis delves deep into the multifaceted capabilities of LLMs, exploring their potential applications in decision optimization, scene understanding, and advanced summarization tasks in diverse contexts. In the first segment of the thesis, the focus is on Unmanned Aerial Vehicles' (UAVs) semantic scene understanding. The capability of instantaneously providing high-level data and visual cues positions UAVs as ideal platforms for performing complex tasks. The work combines the potential of LLMs, Visual Language Models (VLMs), and state-of-the-art detection pipelines to offer nuanced and contextually accurate scene descriptions. A well-controlled, efficient practical implementation of microdrones in challenging settings is presented, supplementing the study with proposed standardized readability metrics to gauge the quality of LLM-enhanced descriptions. This could significantly impact sectors such as film, advertising, and theme parks, enhancing user experiences manifold. The second segment brings to light the increasingly crucial problem of decision-making under uncertainty. Using the Multi-Armed Bandit (MAB) problem as a foundation, the study explores the use of LLMs to inform and guide strategies in dynamic environments. It is postulated that the predictive power of LLMs can aid in choosing the correct balance between exploration and exploitation based on the current state of the system. Through rigorous testing, the proposed LLM-informed strategy showcases its adaptability and its competitive performance against conventional strategies. Next, the research transitions into studying the goodness-of-fit assessments of Generative Adversarial Networks (GANs) utilizing the Signature Transform. By providing an efficient measure of similarity between image distributions, the study sheds light on the intrinsic structure of the samples generated by GANs. A comprehensive analysis using statistical measures, such as the test Kruskal-Wallis, provides a more extensive understanding of the GAN convergence and goodness of fit. In the final section, the thesis introduces a novel benchmark for automatic video summarization, emphasizing the harmonious integration of LLMs and Signature Transform. An innovative approach grounded in the harmonic components captured by the Signature Transform is put forth. The measures are extensively evaluated, proving to offer compelling accuracy that correlates well with the concept of a good summary. This research work establishes LLMs as powerful tools in addressing complex tasks across diverse domains, redefining decision optimization, scene understanding, and summarization tasks. It not only breaks new ground in the applications of LLMs but also sets the direction for future work in this exciting and rapidly evolving field. / De Curtò I Díaz, J. (2023). Frontiers of Large Language Models: Empowering Decision Optimization, Scene Understanding, and Summarization Through Advanced Computational Approaches [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/202200 / Compendio

Tesis por compendio / [ES] La proliferación de sistemas autónomos y su creciente integración en la vida humana cotidiana han abierto nuevas fronteras de investigación y desarrollo. Dentro de este ámbito, la presente tesis se adentra en las aplicaciones multifacéticas de los LLMs (Large Language Models), técnicas de DL (Deep Learning) y algoritmos de optimización en el ámbito de estos sistemas autónomos. A partir de los principios de los métodos potenciados por la Inteligencia Artificial (IA), los estudios englobados en este trabajo convergen en la exploración y mejora de distintos sistemas autónomos que van desde sistemas de platooning de camiones en sistemas de comunicaciones Beyond 5G (B5G), Sistemas Multi-Agente (SMA), Vehículos Aéreos No Tripulados (UAV), estimación del área de incendios forestales, hasta la detección temprana de enfermedades como el glaucoma. Un enfoque de investigación clave, perseguido en este trabajo, gira en torno a la implementación innovadora de controladores PID adaptativos en el platooning de vehículos, facilitada a través de la integración de los LLMs. Estos controladores PID, cuando se infunden con capacidades de IA, ofrecen nuevas posibilidades en términos de eficiencia, fiabilidad y seguridad de los sistemas de platooning. Desarrollamos un modelo de DL que emula un controlador PID adaptativo, mostrando así su potencial en las redes y radios habilitadas para IA. Simultáneamente, nuestra exploración se extiende a los sistemas multi-agente, proponiendo una Teoría Coevolutiva Extendida (TCE) que amalgama elementos de la dinámica coevolutiva, el aprendizaje adaptativo y las recomendaciones de estrategias basadas en LLMs. Esto permite una comprensión más matizada y dinámica de las interacciones estratégicas entre agentes heterogéneos en los SMA. Además, nos adentramos en el ámbito de los vehículos aéreos no tripulados (UAVs), proponiendo un sistema para la comprensión de vídeos que crea una log de la historia basada en la descripción semántica de eventos y objetos presentes en una escena capturada por un UAV. El uso de los LLMs aquí permite razonamientos complejos como la predicción de eventos con mínima intervención humana. Además, se aplica una metodología alternativa de DL para la estimación del área afectada durante los incendios forestales. Este enfoque aprovecha una nueva arquitectura llamada TabNet, integrada con Transformers, proporcionando así una estimación precisa y eficiente del área. En el campo de la salud, nuestra investigación esboza una metodología exitosa de detección temprana del glaucoma. Utilizando un enfoque de entrenamiento de tres etapas con EfficientNet en imágenes de retina, logramos una alta precisión en la detección de los primeros signos de esta enfermedad. A través de estas diversas aplicaciones, el foco central sigue siendo la exploración de metodologías avanzadas de IA dentro de los sistemas autónomos. Los estudios dentro de esta tesis buscan demostrar el poder y el potencial de las técnicas potenciadas por la IA para abordar problemas complejos dentro de estos sistemas. Estas investigaciones en profundidad, análisis experimentales y soluciones desarrolladas arrojan luz sobre el potencial transformador de las metodologías de IA en la mejora de la eficiencia, fiabilidad y seguridad de los sistemas autónomos, contribuyendo en última instancia a la futura investigación y desarrollo en este amplio campo. / [CA] La proliferació de sistemes autònoms i la seua creixent integració en la vida humana quotidiana han obert noves fronteres de recerca i desenvolupament. Dins d'aquest àmbit, la present tesi s'endinsa en les aplicacions multifacètiques dels LLMs (Large Language Models), tècniques de DL (Deep Learning) i algoritmes d'optimització en l'àmbit d'aquests sistemes autònoms. A partir dels principis dels mètodes potenciats per la Intel·ligència Artificial (IA), els estudis englobats en aquest treball convergeixen en l'exploració i millora de diferents sistemes autònoms que van des de sistemes de platooning de camions en sistemes de comunicacions Beyond 5G (B5G), Sistemes Multi-Agent (SMA), Vehicles Aeris No Tripulats (UAV), estimació de l'àrea d'incendis forestals, fins a la detecció precoç de malalties com el glaucoma. Un enfocament de recerca clau, perseguit en aquest treball, gira entorn de la implementació innovadora de controladors PID adaptatius en el platooning de vehicles, facilitada a través de la integració dels LLMs. Aquests controladors PID, quan s'infonen amb capacitats d'IA, ofereixen noves possibilitats en termes d'eficiència, fiabilitat i seguretat dels sistemes de platooning. Desenvolupem un model de DL que emula un controlador PID adaptatiu, mostrant així el seu potencial en les xarxes i ràdios habilitades per a IA. Simultàniament, la nostra exploració s'estén als sistemes multi-agent, proposant una Teoria Coevolutiva Estesa (TCE) que amalgama elements de la dinàmica coevolutiva, l'aprenentatge adaptatiu i les recomanacions d'estratègies basades en LLMs. Això permet una comprensió més matissada i dinàmica de les interaccions estratègiques entre agents heterogenis en els SMA. A més, ens endinsem en l'àmbit dels Vehicles Aeris No Tripulats (UAVs), proposant un sistema per a la comprensió de vídeos que crea un registre de la història basat en la descripció semàntica d'esdeveniments i objectes presents en una escena capturada per un UAV. L'ús dels LLMs aquí permet raonaments complexos com la predicció d'esdeveniments amb mínima intervenció humana. A més, s'aplica una metodologia alternativa de DL per a l'estimació de l'àrea afectada durant els incendis forestals. Aquest enfocament aprofita una nova arquitectura anomenada TabNet, integrada amb Transformers, proporcionant així una estimació precisa i eficient de l'àrea. En el camp de la salut, la nostra recerca esbossa una metodologia exitosa de detecció precoç del glaucoma. Utilitzant un enfocament d'entrenament de tres etapes amb EfficientNet en imatges de retina, aconseguim una alta precisió en la detecció dels primers signes d'aquesta malaltia. A través d'aquestes diverses aplicacions, el focus central continua sent l'exploració de metodologies avançades d'IA dins dels sistemes autònoms. Els estudis dins d'aquesta tesi busquen demostrar el poder i el potencial de les tècniques potenciades per la IA per a abordar problemes complexos dins d'aquests sistemes. Aquestes investigacions en profunditat, anàlisis experimentals i solucions desenvolupades llançen llum sobre el potencial transformador de les metodologies d'IA en la millora de l'eficiència, fiabilitat i seguretat dels sistemes autònoms, contribuint en última instància a la futura recerca i desenvolupament en aquest ampli camp. / [EN] The proliferation of autonomous systems, and their increasing integration with day-to-day human life, have opened new frontiers of research and development. Within this scope, the current thesis dives into the multifaceted applications of Large Language Models (LLMs), Deep Learning (DL) techniques, and Optimization Algorithms within the realm of these autonomous systems. Drawing from the principles of AI-enhanced methods, the studies encapsulated within this work converge on the exploration and enhancement of different autonomous systems ranging from B5G Truck Platooning Systems, Multi-Agent Systems (MASs), Unmanned Aerial Vehicles, Forest Fire Area Estimation, to the early detection of diseases like Glaucoma. A key research focus, pursued in this work, revolves around the innovative deployment of adaptive PID controllers in vehicle platooning, facilitated through the integration of LLMs. These PID controllers, when infused with AI capabilities, offer new possibilities in terms of efficiency, reliability, and security of platooning systems. We developed a DL model that emulates an adaptive PID controller, thereby showcasing its potential in AI-enabled radio and networks. Simultaneously, our exploration extends to multi-agent systems, proposing an Extended Coevolutionary (EC) Theory that amalgamates elements of coevolutionary dynamics, adaptive learning, and LLM-based strategy recommendations. This allows for a more nuanced and dynamic understanding of the strategic interactions among heterogeneous agents in MASs. Moreover, we delve into the realm of Unmanned Aerial Vehicles (UAVs), proposing a system for video understanding that employs a language-based world-state history of events and objects present in a scene captured by a UAV. The use of LLMs here enables open-ended reasoning such as event forecasting with minimal human intervention. Furthermore, an alternative DL methodology is applied for the estimation of the affected area during forest fires. This approach leverages a novel architecture called TabNet, integrated with Transformers, thus providing accurate and efficient area estimation. In the field of healthcare, our research outlines a successful early detection methodology for glaucoma. Using a three-stage training approach with EfficientNet on retinal images, we achieved high accuracy in detecting early signs of this disease. Across these diverse applications, the core focus remains: the exploration of advanced AI methodologies within autonomous systems. The studies within this thesis seek to demonstrate the power and potential of AI-enhanced techniques in tackling complex problems within these systems. These in-depth investigations, experimental analyses, and developed solutions shed light on the transformative potential of AI methodologies in improving the efficiency, reliability, and security of autonomous systems, ultimately contributing to future research and development in this expansive field. / De Zarzà I Cubero, I. (2023). AI-Enhanced Methods in Autonomous Systems: Large Language Models, DL Techniques, and Optimization Algorithms [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/202201 / Compendio

<p dir="ltr">This research explored a solution to a high accident rate in remotely operating Unmanned Aerial Vehicles (UAVs) in a complex environment; it presented a new Brain-Computer Interface (BCI) enabled supervisory control system to fuse human and machine intelligence seamlessly. This study was highly motivated by the critical need to enhance the safety and reliability of UAV operations, where accidents often stemmed from human errors during manual controls. Existing BCIs confronted the challenge of trading off a fully remote control by humans and an automated control by computers. This study met such a challenge with the proposed supervisory control system to optimize human-machine collaboration, prioritizing safety, adaptability, and precision in operation.</p><p dir="ltr">The research work included designing, training, and testing BCI and the BCI-enabled control system. It was customized to control a UAV where the user’s motion intents and cognitive states were monitored to implement hybrid human and machine controls. The DJI Tello drone was used as an intelligent machine to illustrate the application of the proposed control system and evaluate its effectiveness through two case studies. The first case study was designed to train a subject and assess the confidence level for BCI in capturing and classifying the subject’s motion intents. The second case study illustrated the application of BCI in controlling the drone to fulfill its missions.</p><p dir="ltr">The proposed supervisory control system was at the forefront of cognitive state monitoring to leverage the power of an ML model. This model was innovative compared to conventional methods in that it could capture complicated patterns within raw EEG data and make decisions to adopt an ensemble learning strategy with the XGBoost. One of the key innovations was capturing the user’s intents and interpreting these into control commands using the EmotivBCI app. Despite the headset's predefined set of detectable features, the system could train the user’s mind to generate control commands for all six degrees of freedom of adapting to the quadcopter by creatively combining and extending mental commands, particularly in the context of the Yaw rotation. This strategic manipulation of commands showcased the system's flexibility in accommodating the intricate control requirements of an automated machine.</p><p dir="ltr">Another innovation of the proposed system was its real-time adaptability. The supervisory control system continuously monitors the user's cognitive state, allowing instantaneous adjustments in response to changing conditions. This innovation ensured that the control system was responsive to the user’s intent and adept at prioritizing safety through the arbitrating mechanism when necessary.</p>

Le concept de Ville Intelligent concerne l’interconnectivité totale de plusieurs industries vers l’amélioration des modes de vie des résidents. Ceci est rendu possible par la croissance et l'utilisation généralisée de l'Internet des objets (IoT), un vaste réseau de dispositifs de collecte de données répartis dans de multiples applications. Cependant, la plupart des appareils IoT disposent de peu de ressources et s'appuient sur des serveurs externes pour traiter et stocker les données collectées. En raison de la congestion et de la distance élevées, les centres de données Nuage (Cloud) peuvent entraîner une latence élevée dans leur réponse IoT, ce qui peut être inacceptable dans certaines applications IoT. Au lieu de cela, l'informatique Brouillard (fog-computing) a été proposé comme une couche hétérogène hautement virtualisée de serveurs à la périphérie du réseau, ce qui permet un traitement des données IoT à faible latence. Les contributions actuelles au brouillard informatique supposent qu'une infrastructure de brouillard est déjà en place. De plus, chaque contribution nécessite des caractéristiques différentes sur l’infrastructure du brouillard. Cette thèse formule un schéma de conception et de dimensionnement évolutif et modifiable pour une infrastructure de brouillard généralisée. Ceci est modélisé et résolu sous la forme d'un programme linéaire à nombres entiers mixtes (MILP), et détendu à l'aide de plusieurs techniques telles que la génération de colonnes et la décomposition de Benders. De nombreuses préoccupations concernant les performances du réseau brouillard sont prises en compte et résolues, telles que le trafic IoT élevé, la congestion du réseau et les dysfonctionnements des nœuds brouillard. Les nœuds de brouillard dynamiques, tels que les nœuds de brouillard à la demande et les véhicules aériens sans pilote mobiles (UAV-brouillard) sont intégrés dans les modèles de conception et de dimensionnement actuels pour ajouter de la flexibilité et de la robustesse au réseau. Un système basé sur la blockchain et des preuves de connaissance nulle est introduit pour renforcer l'intégrité des nœuds de brouillard. Le résultat est un schéma de conception et de dimensionnement évolutif pour une infrastructure de brouillard robuste, flexible et fiable dans un environnement de brouillard-IoT dynamique et malveillant. / The concept of a Smart City relies on the full interconnectivity of several industries towards the amelioration of resident lifestyles. This is made possible by the growth and wide-spread use of the Internet of Things (IoT) -- a large network of data collection devices throughout multiple applications. However, most IoT devices have few resources, and rely on external servers to process and store the collected data. Due to high congestion and distance, Cloud data centres may cause high latency in their IoT response, which may be unacceptable in certain IoT applications. Instead, fog-computing has been proposed as a highly-virtualized heterogeneous layer of servers on the network edge, resulting in low-latency IoT data processing. Current contributions in fog-computing assume a fog infrastructure is already in-place. Furthermore, each contribution requires different characteristics on the fog infrastructure. This thesis formulates a scalable and modifiable design & dimensioning scheme for a generalized fog infrastructure. This is modeled and solved as a mixed-integer linear program (MILP), and relaxed using several techniques such as Column Generation and Benders Decomposition. Many concerns on the fog network performance are considered and addressed, such as high IoT traffic, network congestion, and fog node malfunctions. Dynamic fog nodes, such as on-demand fog nodes and mobile fog-enabled unmanned aerial vehicles (fog-UAVs) are integrated into current design & dimensioning models to add flexibility and robustness to the network. A system based on blockchain and zero-knowledge proofs is introduced to enforce integrity on the fog nodes. The result is a scalable design & dimensioning scheme for a robust, flexible, and reliable fog infrastructure in a dynamic and malicious IoT-fog environment.

Taking as its starting point Nietzsche’s and Foucault’s theses on liberalism and war, and Dillon and Reid’s extensive engagement thereof, this thesis offers a critical conceptualization of drones and drone warfare. I argue that deployment of drones specifically over and against bodies and communities in conflict zones in and between Afghanistan, Pakistan, Iraq, Yemen, Somalia, and until recently, Libya, is the material practice of a legal and political doctrine and precedent that has been established and policed most prominently by the United States and its military and intelligence apparatuses since the end of the Cold War. This novel precedent, however - due to its necessarily mutually constitutive relationship with a perceived danger said to be emerging from specific spaces, bodies, and communities in the decolonized and still-colonized worlds - locates its ontological and thus political genealogy in the anthropological knowledge that legally justified the (in)humanity of peoples and communities in these spaces during the era of high imperialism that lasted roughly from the nineteenth to mid-twentieth centuries. I theorize this as a mode of political, tragic nihilism through a reading of some key theories of Deleuze and Guattari, Foucault, and Nietzsche and specifically, their import to the field of critical security and international relations theory. I demonstrate that the semiotic image of the drone is a highly pertinent point of departure through which we can understand these political stakes of strategic discourses enunciating the imperatives of both the Revolution in Military Affairs as well as recent global counterinsurgency/counterterrorism operations, specifically as they relate to claims about what it is drones are said to productively offer such militaristic projects. Ultimately, I argue that it is through the semiotic image of the drone as a clean, precise tactic that furthers the strategic goals of counterterrorism to target specific bodies that we can begin to politically theorize a particularly malignant political nihilism symptomatic of contemporary liberal societies. However, I also suggest that it is through Nietzsche’s politics of nihilism that we can begin to think about radical critical interventions that resist such a dangerous mode of politics. / Graduate

Vision-based conventional landing of a fixed wing UAV is addressed in this thesis. The work includes mathematical modeling, interface to a software for rendering the outside scenery, image processing techniques, control law development and outdoor experimentation. This research focuses on detecting the lines or the edges that flank the landing site, use them as visual cues to extract the geometrical parameters such as the line co-ordinates and the line slopes, that are mapped to the control law, to align and conventionally land the fixed wing UAV. Pre-processing and image processing techniques such as Canny Edge detection and Hough Transforms have been used to detect the runway lines or the edges of a landing strip. A Vision-in-the-Loop Simulation (VILS) set up on a personal computer or laptop, has been developed, without any external camera/equipment or networking cables that enables visual serving toper form vision-based studies and simulation. UAV mass, inertia, engine and aero data from literature has been used along withUAV6DOF equations to represent the UAV mathematical model. The UAV model is interfaced to a software using UDP data packets via ports, for rendering the outside scenery in accordance with the UAV’s translation and orientation. The snapshots of the outside scenery, that is passed through an internet URL by including the ‘http’ protocol, is image processed to detect the lines and the line parameters for the control. VILS set has been used to simulate UAV alignment to the runway and landing. Vision-based alignment is achieved by rolling the UAV such that the landing strip that is off center is brought to the center of the image plane. A two stage proportional aileron control input using the line co-ordinates, bringing the midpoints of the top ends of the runway lines to the center of the image, followed by bringing the mid points of the bottom ends of the runway lines to the center of the image has been demonstrated through simulation. A vision-based control for landing has been developed, that consists of an elevator command that is commiserate with the acceptable range of glide slope followed by a flare command till touch down, which is a function of the flare height and estimated height from the 3rd order polynomial of the runway slope obtained by characterization. The feasibility of using the algorithms for a semi-prepared or unprepared landing strip with no visible runway lines have also been demonstrated. Landing on an empty tract of land and in poor visibility condition, by synthetically drawing the runway lines based on a single 3rd order slope. vs height polynomial solution are also presented. A fixed area, and a dynamic area search for the Hough peaks in the Hough accumulator array for the correct detection of lines are addressed. A novel technique for crosswind landing, quite different from conventional techniques, has been introduced, using only the aileron control input for correcting the drift. Three different strategies using the line co-ordinates and the line slopes, with varying levels of accuracy have been presented and compared. About 125 landing data of a manned instrumented prototype aircraft have been analysed to corroborate the findings of this research. Outdoor experiments are also conducted to verify the feasibility of using the line detection algorithm in a realistic scenario and to generate experimental evidence for the findings of this research. Computation time estimates are presented to establish the feasibility of using vision for the problem of conventional landing. The thesis concludes with the findings and direction for future work.