Vehicle platooning is an important innovation in the automotive industry that aims at improving safety, mileage, effciency, and the time needed to travel. This research focuses on the various aspects of vehicle platooning, one of the important aspects being analysis of different control strategies that lead to a stable and robust platoon. Safety of passengers being a very important consideration, the control design should be such that the controller remains robust under uncertain environments. As a part of the Department of Energy (DOE) project, this research also tries to show a demonstration of vehicle platooning using robots. In an automated highway scenario, a vehicle platoon can be thought of as a string of vehicles, following one another as a platoon. Being equipped by wireless communication capabilities, these vehicles communicate with one another to maintain their formation as a platoon, hence are "cognitive." Autonomous capable vehicles in tightly spaced, computer-controlled platoons will lead to savings in energy due to reduced aerodynamic forces, as well as increased passenger comfort since there will be no sudden accelerations or decelerations. Impacts in the occurrence of collisions, if any, will be very low. The greatest benefit obtained is, however, an increase in highway capacity, along with reduction in traffic congestion, pollution, and energy consumption. Another aspect of this project is the automated electric transportation (AET). This aims at providing energy directly to vehicles from electric highways, thus reducing their energy consumption and CO2 emission. By eliminating the use of overhead wires, infrastructure can be upgraded by electrifying highways and providing energy on demand and in real time to moving vehicles via a wireless energy transfer phenomenon known as "wireless inductive coupling." The work done in this research will help to gain an insight into vehicle platooning and the control system related to maintaining the vehicles in this formation.

This thesis is concerned with an experimental platform for studying cooperative driving and techniques for embedded systems programming. Cooperative driving systems use vehicle-to-vehicle and vehicle-to-infrastructure communication for safe, smooth and efficient transportation. Cooperative driving systems are considered as a promising solution for traffic situations such as blind crossings. For the thesis work we use a robotic vehicle known as PIE (Platform for Intelligent Embedded Systems) equipped with a wireless communication device, electrical motors and controlled via a SAM7-P256 development board. For the infrastructure side we use a SAM7-P256 development board equipped with nRF24l01. Vehicle to vehicle and base station to vehicle communication is established and different platooning scenarios are implemented. The scenarios are similar to platooning scenarios from the Grand Cooperative Driving Challenge GCDC1. The performance of the platoon control algorithm is measured in terms of throughput (a measure of string stability), smoothness and safety, where the safety requirements serve as pass/fail criteria.

Vehicle platoons are efficient, closely-spaced groups of robotically controlled vehicles which travel at high speeds down the road, similar to carts in a train. Within this thesis, a promising control algorithm for vehicle platooning is explored. The control algorithm was previously demonstrated in a sterile setting which significantly reduced the challenges facing full-scale implementation of platoons, most notably loss of shared data and imprecision within the data. As found within this work, transmission loss and imprecise position, velocity, and acceleration data significantly degraded the control algorithm's performance. Vehicles in the platoon became more closely spaced, changed speeds more frequently, and expended far more energy than necessary. Introducing a measure of each following vehicle's position with respect to the lead vehicle into the control algorithm noticeably reduced platoon contraction. Adjusting the control algorithm's responsiveness based on what data was successfully received reduced the speed-variations by vehicles. Finally, using past behavior to predict the next acceleration reduced the energy used by each vehicle. Combining these modifications with a model of the proposed communication scheme shows platoons of up to 25 vehicles are feasible.

<p>This thesis is concerned with an experimental platform for studying cooperative driving and techniques for embedded systems programming. Cooperative driving systems use vehicle-to-vehicle and vehicle-to-infrastructure communication for safe, smooth and efficient transportation. Cooperative driving systems are considered as a promising solution for traffic situations such as blind crossings. For the thesis work we use a robotic vehicle known as PIE (Platform for Intelligent Embedded Systems) equipped with a wireless communication device, electrical motors and controlled via a SAM7-P256 development board. For the infrastructure side we use a SAM7-P256 development board equipped with nRF24l01. Vehicle to vehicle and base station to vehicle communication is established and different platooning scenarios are implemented. The scenarios are similar to platooning scenarios from the Grand Cooperative Driving Challenge GCDC1. The performance of the platoon control algorithm is measured in terms of throughput (a measure of string stability), smoothness and safety, where the safety requirements serve as pass/fail criteria.</p>

Automated vehicles promise to be one of the most constructive inventions of late as they promote road safety, fuel efficiency, and reduced time road travel, by decreasing traffic congestion and workload on the driver. In a platoon (which is a method of grouping vehicles, which helps increase the capacity of roads by managing the distance between vehicles by using electrical and mechanical coupling) of such automated vehicles, as in automated highway systems (AHS), tracking of inter-vehicular spacing is one of the significant factors to be considered. Because of the close spacing, computer-controlled platoons with inter-vehicular communication, which is the concept of adaptive cruise control (ACC), become open to cyber security attacks. Cyber physical and cyber attacks on smart grid systems in the electricity market have been a focus of researchers, and much work has been done on that front. However, cyber physical (CP) attacks on autonomous vehicle platoons have not been examined. Thus this research entails the survey of a number of vehicle models used in different works pertaining to longitudinal vehicle motion and analysis of a special class of cyber physical attacks called false data injection (FDI) attacks on vehicle platoons moving with longitudinal motion. In this kind of attack, an attacker can exploit the configuration of any cyber physical system to launch such attacks to successfully introduce arbitrary errors into certain state variables so as to gain control over the system. So here, an n-vehicle platoon is considered and a linearized vehicle model is used as a testbed to study vehicle dynamics and control, after false information is fed into the system.

Platooning concept involves a group of vehicles acting as a single unit through coordination of movements. While Platooning as an evolving trend in mobility and transportation diminishes the individual and manual driving concerns, it creates new risks. New technologies and passenger’s safety and security further complicate matters and make platooning attractive target for the malicious minds. To improve the security of the vehicular platooning, threats and their potential impacts on vehicular platooning should be identified to protect the system against security risks. Furthermore, algorithms should be proposed to detect intrusions and mitigate the effects in case of attack. This dissertation introduces a new vulnerability in vehicular platooning from the control systems perspective and presents the detection and mitigation algorithms to protect vehicles and passengers in the event of the attack.

The demand for road freight transport continues to grow with the growing economy, resulting in increased fossil fuel consumption and emissions. At the same time, the fossil fuel use needs to decrease substantially to counteract the ongoing global warming. One way to reduce fuel consumption is to utilize emerging intelligent transport system (ITS) technologies and introduce heavy-duty vehicle (HDV) platooning, i.e. HDVs driving with small inter-vehicle gaps enabled by the use of sensors and controllers. It is of importance for transport authorities and industries to investigate the effects of introducing HDV platooning. Previous studies have investigated the potential benefits, but the effects in real traffic, both for the platoons and for the surrounding vehicles, have barely been explored. To further utilize ITS and optimize the platoons, information about the traffic situation ahead can be used to optimize the vehicle trajectories for the platoons. Paper I presents a dynamic programming-based optimal speed control including information of the traffic situation ahead. The optimal control is applied to HDV platoons in a deceleration case and the potential fuel consumption reduction is evaluated by a microscopic traffic simulation study with HDV platoons driving in real traffic conditions. The effects for the surrounding traffic are also analysed. Paper II and Paper III present a simulation platform to assess the effects of HDV platooning in real traffic conditions. Through simulation studies, the potential fuel consumption reduction by adopting HDV platooning on a real highway stretch is evaluated, and the effects for the other vehicles in the network are investigated. / Efterfrågan på godstransporter på väg fortsätter att öka i takt med den växande ekonomin, vilket resulterar i ökad förbrukning av fossila bränslen och ökade utsläpp. Samtidigt behöver användandet av fossila bränslen minska för att motverka den pågående globala uppvärmningen. Ett sätt för att minska bränsleförbrukningen är att utnyttja den teknik kring intelligenta transportsystem som är under utveckling och introducera lastbilskonvojer, det vill säga lastbilar som använder sensorer och regulatorer för att kunna köra med korta avstånd mellan sig. För transportföretag och -myndigheter är det viktigt att undersöka effekterna av att införa lastbilskonvojkörning. Tidigare studier har undersökt de möjliga fördelarna, men effekterna vid körning i trafik, både för konvojerna och för omgivande fordon, är outforskade. För att ytterligare utnyttja intelligenta transportsystem och optimera konvojerna kan information om trafiksituationen längre fram på vägen användas för att optimera konvojernas körning. Artikel I presenterar en optimal hastighetsregulator baserad på dynamisk programmering och som inkluderar information om trafiksituationen längre fram. Den optimala regulatorn appliceras på lastbilskonvojer under ett inbromsningsscenario och den potentiella minskningen i bränsleförbrukning utvärderas genom en mikroskopisk trafiksimuleringsstudie där lastbilskonvojerna kör i verkliga trafikförhållanden. Effekterna för omgivande fordon är också analyserade.Artikel II och artikel III presenterar en simuleringsplattform för att utvärdera effekterna av lastbilskonvojkörning i verkliga trafikförhållanden. Genom simuleringsstudier analyseras den potentiella bränsleförbrukningsminskningen då lastbilskonvojer körs på en verklig motorvägssträcka och effekterna för de övriga fordonen på vägen undersöks. / <p>QC 20180516</p>

The current development of autonomous vehiclesallow for several new applications to form and evolve. One ofthese are platooning, where several vehicles drive closely togetherwith automatic car following. The method of getting informationabout the other vehicles in a platoon can vary. One of thesemethods is using visual information from a camera. Having acamera on-board an autonomous vehicle has further potential, forexample for recognition of objects in the vehicle’s surroundings.This bachelor thesis uses small RC vehicles to test an example ofa vision based platooning system. The system is then evaluatedusing a step response, from which the stability of the systemis analyzed. Additionally, a previously developed communicationbased platooning system was tested in the same way and it’sstability compared. The main conclusion of this thesis is that it isfeasible to use a camera, ArUco marker and an Optimal VelocityRelative Velocity model to achieve a vision based platoon on asmall set of RC vehicles. / Forskningsframsteg inom området autonoma fordon möjliggör utveckling av ett flertal nya tillämpningar. En av dessa är platooning, som innebär att flera fordon kör nära varandra med automatisk farthållning. Metoden för att erhålla information om de andra fordonen i platoonen kan variera. En av dessa metoder är att använda visuell information från en kamera. Att ha en kamera ombord på ett autonomt fordon har stor potential, exempelvis för detektering av objekt i fordonets omgivning. Det här kandidatexamensarbetet använder små radiostyrda bilar för att testa ett exempel av ett kamerabaserat platooning-system. Systemet är sedan utvärderat med hjälp av ett stegsvar, från vilket stabiliteten av systemet är analyserat. Dessutom testas ett tidigare utvecklat kommunikationsbaserat platooning-system, hittills bara testat i simulering, på samma uppsättning bilar. Den huvudsakliga slutsatsen av detta arbete är att det är möjligt att använda en kamera, ArUco markör och en Optimal Velocity Relative Velocity modell för att uppnå kamerabaserad platoon med en liten uppsättning radiostyrda bilar. / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm

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

Vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication enable the sharing, in real time, of vehicular locations and speeds with other vehicles, traffic signals, and traffic control centers. This shared information can help traffic to better traverse intersections, road segments, and congested neighborhoods, thereby reducing travel times, increasing driver safety, generating data for traffic planning, and reducing vehicular pollution. This study, which focuses on vehicular pollution, used an analysis of data from NREL, BTS, and the EPA to determine that the widespread use of V2V-based truck platooning—the convoying of trucks in close proximity to one another so as to reduce air drag across the convoy—could eliminate 37.9 million metric tons of CO2 emissions between 2022 and 2026.