Dagens trafikstyrning sker främst med hjälp av nedgrävda induktionsslingor som detekterar fordon som passerar över dem. Dessa detektorer går relativt ofta sönder och kräver utgrävningar av vägbanan vid reparation. Dessa reparationer tar tid, skapar hinder i trafikflödet och leder till ytterligare samhällskostnader. Detta arbete undersöker möjligheten att byta ut induktionsslingorna mot kameror som monteras direkt på trafikljusen. En kamerabaserad lösning skulle kunna underlätta reparationsarbetet och på så sätt vara ett mer ekonomiskt alternativ till induktionsslingor. För att detta ska fungera krävs det att den kamerabaserade lösningen kan prestera på en likvärdig nivå till lösningen med induktionsslingor. Detta arbete bygger upp en modell av en trafikkorsning för att besvara denna fråga. Trafikkorsningen byggs upp i Unreal Engine 5 och baserar sig på en verklig korsning i Linköping, Sverige. I modellen byggs korsningens induktionsslingor upp med liknande logik som den som finns i den verkliga korsningen. Det byggs även en kamerabaserad detektionslösning där kamerorna monteras på ett trovärdigt sätt. För att mäta prestandan av de olika lösningarna används måttet fördröjningstid, vilket är den extra tid som ett fordon spenderar i korsningen på grund av trafikljusen. Arbetet fann att den simulerade induktionsslingorna presterade bättre än den kamerabaserade detektionsmetoden. Skillnaden är tillräckligt liten för att inte helt utesluta en kamerabaserad lösning som ett alternativ till induktionsslingor. Det skulle däremot krävas vidare forskning för att täcka fler scenarion och få en bättre förståelse för den kamerabaserade lösningens fulla potential. / The traffic control of today is primarily controlled using buried induction loops that detect vehicles passing over them. These detectors break relatively often and require excavation of the roadway to repair. These reparations take time, generate obstructions in the flow of traffic and lead to further societal costs. This paper explores the possibility of using cameras directly mounted to the traffic lights of an intersection as a substitute for induction loops. The camera-based solution is required to perform on a similar level to the solution based on induction loop for this to be plausible. This paper constructs a model of an intersection and uses that model to evaluate if this is possible or not. The intersection is constructed in Unreal Engine 5 and is based on a real-world intersection from Linköping, Sweden. The model includes a representation of the induction loops present in the real-world intersection. It also includes an implementation of a camera-based vehicle detection solution where the cameras are mounted in a realistic way throughout the simulated intersection. The measurement Fördröjningstid is used to measure the performance of the different solutions. Delay time is the added time a vehicle that passes through the intersection experiences because of the traffic lights. The paper finds that the simulated induction loops outperform the camerabased solution. The difference is small enough to not completely rule out a camera-based solution as an alternative to induction loops. Further research would be required to cover more scenarios and to get a better understanding of the full potential of a camera-based solution.

No description available.

No description available.

In traffic networks, appropriately determining the traffic signal plan of each intersection is a ünecessary condition for a reasonable level of service. This paper presents the development of a new system for automatically designing optimal actuated traffic signal plans with transit signal priority. It uses an optimization algorithm combined with a mesoscopic traffic simulation model to design and evaluate optimal traffic signal plans for each intersection in the traffic network, therefore reducing the need for human intervention in the design process. The proposed method can simultaneously determine the optimal logical structure, priority strategies, timing parameters, phase composition and sequence, and detector placements. The integrated system was tested by a real-world isolated intersection in Haifa city. The results demonstrated that this approach has the potential to efficiently design signal plans without human intervention, which can minimize time, cost, and design effort. It can also help uncover problems in the design that may otherwise not be detected.

A challenge in today's society is to handle a large amount of vehicles traversing an intersection. Traffic lights are often used to control the traffic flow in these intersections. However, there are inefficiencies since the algorithms used to control the traffic lights do not perfectly adapt to the traffic situation. The purpose of this paper is to compare three different types of algorithms used in traffic control systems to find out how to minimize vehicle waiting times. A pretimed, a deterministic and a reinforcement learning algorithm were compared with each other. Test were conducted on a four-way intersection with various traffic demands using the program Simulation of Urban MObility (SUMO). The results showed that the deterministic algorithm performed best for all demands tested. The reinforcement learning algorithm performed better than the pretimed for low demands, but worse for varied and higher demands. The reasons behind these results are the deterministic algorithm's knowledge about vehicular movement and the negative effects the curse of dimensionality has on the training of the reinforcement learning algorithm. However, more research must be conducted to ensure that the results obtained are trustworthy in similar and different traffic situations. / En utmaning i dagens samhälle är att hantera en stor mängd fordon som kör igenom en korsning. Trafikljus används ofta för att kontrollera trafikflödena genom dessa korsningar. Det finns däremot ineffektiviteter eftersom algoritmerna som används för att kontrollera trafikljusen inte är perfekt anpassade till trafiksituationen. Syftet med denna rapport är att jämföra tre typer av algoritmer som används i trafiksystem för att undersöka hur väntetid för fordon kan minimeras. En tidsbaserad, en deterministisk och en förstärkande inlärning-algoritm jämfördes med varandra. Testerna utfördes på en fyrvägskorsning med olika trafikintensiteter med hjälp av programmet Simulation of Urban MObility (SUMO). Resultaten visade att den deterministiska algoritmen presterade bäst för alla olika trafikintensiteter. Inlärningsalgoritmen presterade bättre än den tidsbaserade på låga intensiteter, men sämre på varierande och högre intensiteter. Anledningarna bakom resultaten är att den deterministiska algoritmen har kunskap om hur fordon rör sig samt att dimensionalitetsproblem påverkar träningen av inlärningsalgoritmen negativt. Det krävs däremot mer forskning för att säkerställa att resultaten är pålitliga i liknande och annorlunda trafiksituationer.

In recent years, unmanned aerial vehicles (UAVs) have become a dominant force in the aerospace industry. Recent technological developments have moved these aircraft from remote operation roles to more active response missions. Of particular interest is the possibility of applying UAVs toward solving complex problems in long-endurance missions. Under that belief, the feasibility of utilizing UAVs for wildfire detection and response was investigated in a partnership that included NASA’s Aeronautics Research Mission Directorate and Science Mission Directorate, and the United States Forest Service. Under NASA’s Intelligent Mission Management (IMM) project, research was conducted to develop a mission architecture that would enable use of a high altitude UAV to search for reported wildfires with a separate low altitude UAV supporting ground assets. This research proposes a “straw man” concept incorporating both a High Altitude Long Endurance (HALE) UAV and a Low Altitude Short Endurance (LASE) UAV in a loosely coupled, low cost solution tailored towards wildfire response. This report identifies the communications architecture, algorithms, and required system configuration that meets the outlined goals of the IMM project by mitigating wildfires and addressing the United States Forest Service immediate needs. The end product is a defined parent-child framework capable of meeting all wildfire mission goals. The concept has been implemented in simulation, the results of which are presented in this report.

The selection of the most appropriate traffic control actions to solve non-recurrent traffic congestion is a complex task which requires significant expert knowledge and experience. In this thesis we develop and investigate the application of an intelligent traffic control decision support system for road traffic management to assist the human operator to identify the most suitable control actions in order to deal with non-recurrent and non-predictable traffic congestion in a real-time situation. Our intelligent system employs a Fuzzy Neural Networks (FNN) Tool that combines the capabilities of fuzzy reasoning in measuring imprecise and dynamic factors and the capabilities of neural networks in terms of learning processes. In this work we present an effective learning approach with regard to the FNN-Tool, which consists of three stages: initializing the membership functions of both input and output variables by determining their centres and widths using self-organizing algorithms; employing an evolutionary Genetic Algorithm (GA) based learning method to identify the fuzzy rules; tune the derived structure and parameters using the back-propagation learning algorithm. We evaluate experimentally the performance and the prediction capability of this three-stage learning approach using well-known benchmark examples. Experimental results demonstrate the ability of the learning approach to identify all relevant fuzzy rules from the training data. A comparative analysis shows that the proposed learning approach has a higher degree of predictive capability than existing models. We also address the scalability issue of our intelligent traffic control decision support system by using a multi-agent based approach. The large network is divided into sub-networks, each of which has its own associated agent. Finally, our intelligent traffic control decision support system is applied to a number of road traffic case studies using the traffic network in Riyadh, in Saudi Arabia. The results obtained are promising and show that our intelligent traffic control decision support system can provide an effective support for real-time traffic control.

No description available.

Ever wondered how trains arrive and depart on time? Traffic Control systems are there to help control the traffic flow, with many operators monitoring and taking actions when necessary. Operators of the traffic control systems use a keyboard and a mouse to interact. Current user interface and work setup consist of many usability issues that can be improved in order to increase operator’s efficiency and productivity in controlling the traffic. Interviewing users of the system and researching on related topics led to a newly proposed design in interaction, user interface as well as some suggestions for increasing productivity. Gesture-based interaction is introduced and simulated for traffic control systems that tend to improve the operation. Various gestures are designed such as panning, zooming and hovering the map using Leap Motion controller which enables intuitive interaction. These gestures aim to solve identified usability issues discovered during the interview with the user. The project aims to answer the following question: Can gesture-based interaction solve usability issues and establish the intuitive use of the CTC system? Performing exploratory research on this topic involved designing, implementing and testing hand gestures with users. From an ergonomic perspective, body posture and hand position of the operator is examined and suggested to use sit-to-stand workstations in order to reduce pain and discomfort while working. Gesture-based interaction eliminates finding mouse cursor on large screens, it enables fast request of detailed information and also it provides a better overview of the map surroundings. Laboratory tests confirm that gesture-based interaction brings more natural and intuitive use of traffic control systems. There is a big potential for gesture-based interaction to increase usability and bring efficient controlling for operators. It would reduce delays of the train and maintain safe traffic flow. / Har du någonsin undrat hur tåg anländer och avgaå i tid? Trafikledningssystem (CTC-system) hjälper till att kontrollera trafikflöet där operatörer övervakar och vidtar åtgärder vid behov. Operatörer av ett trafikledningssystem använder idag ett tangentbord och en mus för att interagera. Det nuvarande användargränssnittet och arbetsinstallationen består av många användbarhetsproblem som kan förbättras för att öka operatörens effektivitet och produktivitet för att kontrollera trafiken. Intervjuer med användare av systemet samt forskning om ämnet ledde till ett nytt föreslag av interaktion, utformning av användargränssnitt samt några förslag för att öka produktiviteten. Den gestbaserade interaktionen som infördes och simulerades för trafikkontrollsystemet tenderar att förbättra funktionen. Olika gester utformades som möjliggör för användaren att panorera, zooma och sväva över kartan. Gesterna implementerades med hjälp av Leap Motion Controller som möjliggör intuitiv interaktion. Dessa gester syftar till att lösa identifierade användbarhetsproblem som upptäcks under intervjuerna med användarna. Syftet med detta arbete var att svara på följande forskningsfråga: Kan gestbaserad interaktion lösa användbarhetsproblem och etablera intuitiv användning av CTC-systemet? Den explorativa forskning som utfördes i detta arbete inkluderade att utforma, genomföra och testa gester med användare. Kroppshållning och handposition för operatorerna undersöktes ur ett ergonomiskt perspektiv och studien föreslår att använda sitt-till-stå arbetsstationer för att minska smärta och obehag under arbetet. Gestbaserad interaktion eliminerar problemet att hitta muspekaren på stora skärmar, vilket gör det enkelt att snabbt hitta detaljerad information och ger även en bättre överblick över kartans omgivning. Laboratorietester bekräftar att gestbaserad interaktion ger mer naturlig och intuitiv användning av trafikledningssystemet. Det finns en stor potential för gestbaserad interaktion för att öka användbarheten och ge en effektiv kontroll för operatörerna. Det skulle minska förseningarna av tåget och upprätthålla ett säkert trafikflöde.

We develop and evaluate two significant modeling concepts within the context of a large-scale Airspace Planning and Collaborative Decision-Making Model (APCDM) and, thereby, enhance its current functionality in support of both strategic and tactical level flight assessments. The first major concept is a new severe weather-modeling paradigm that can be used to assess existing tactical en route flight plan strategies such as the Flight Management System (FMS) as well as to provide rerouting strategies. The second major concept concerns modeling the mediated bartering of slot exchanges involving airline trade offers for arrival/departure slots at an arrival airport that is affected by the Ground Delay Program (GDP), while simultaneously considering issues related to sector workloads, airspace conflicts, as well as overall equity concerns among the airlines. This research effort is part of an $11.5B, 10-year, Federal Aviation Administration (FAA)-sponsored program to increase the U.S. National Airspace (NAS) capacity by 30 percent by the year 2010. Our innovative contributions of this research with respect to the severe weather rerouting include (a) the concept of "Probability-Nets" and the development of discretized representations of various weather phenomena that affect aviation operations; (b) the integration of readily accessible severe weather probabilities from existing weather forecast data provided by the National Weather Service (NWS); (c) the generation of flight plans that circumvent severe weather phenomena with specified probability levels, and (d) a probabilistic delay assessment methodology for evaluating planned flight routes that might encounter potentially disruptive weather along its trajectory. Given a fixed set of reporting stations from the CONUS Model Output Statistics (MOS), we begin by constructing weather-specific probability-nets that are dynamic with respect to time and space. Essential to the construction of the probability-nets are the point-by-point forecast probabilities associated with MOS reporting sites throughout the United States. Connections between the MOS reporting sites form the strands within the probability-nets, and are constructed based upon a user-defined adjacency threshold, which is defined as the maximum allowable great circle distance between any such pair of sites. When a flight plan traverses through a probability-net, we extract probability data corresponding to the points where the flight plan and the probability-net strand(s) intersect. The ability to quickly extract this trajectory-related probability data is critical to our weather-based rerouting concepts and the derived expected delay and related cost computations in support of the decision-making process. Next, we consider the superimposition of a flight-trajectory-grid network upon the probability-nets. Using the U.S. Navigational Aids (Navaids) as the network nodes, we develop an approach to generate flight plans that can circumvent severe weather phenomena with specified probability levels based on determining restricted, time-dependent shortest paths between the origin and destination airports. By generating alternative flight plans pertaining to specified threshold strand probabilities, we prescribe a methodology for computing appropriate expected weather delays and related disruption factors for inclusion within the APCDM model. We conclude our severe weather-modeling research by conducting an economic benefit analysis using a k-means clustering mechanism in concert with our delay assessment methodology in order to evaluate delay costs and system disruptions associated with variations in probability-net refinement-based information. As a flight passes through the probability-net(s), we can generate a probability-footprint that acts as a record of the strand intersections and the associated probabilities from origin to destination. A flight plan's probability-footprint will differ for each level of data refinement, from whence we construct route-dependent scenarios and, subsequently, compute expected weather delay costs for each scenario for comparative purposes. Our second major contribution is the development of a novel slot-exchange modeling concept within the APCDM model that incorporates various practical issues pertaining to the Ground Delay Program (GDP), a principal feature in the FAA's adoption of the Collaborative Decision-Making (CDM) paradigm. The key ideas introduced here include innovative model formulations and several new equity concepts that examine the impact of "at-least, at-most" trade offers on the entire mix of resulting flight plans from respective origins to destinations, while focusing on achieving defined measures of "fairness" with respect to the selected slot exchanges. The idea is to permit airlines to barter assigned slots at airports affected by the Ground Delay Program to their mutual advantage, with the FAA acting as a mediator, while being cognizant of the overall effect of the resulting mix of flight plans on air traffic control sector workloads, collision risk and safety, and equity considerations. We start by developing two separate slot-exchange approaches. The first consists of an external approach in which we formulate a model for generating a set of package-deals, where each package-deal represents a potential slot-exchange solution. These package-deals are then embedded within the APCDM model. We further tighten the model representation using maximal clique cover-based cuts that relate to the joint compatibility among the individual package-deals. The second approach significantly improves the overall model efficiency by automatically generating package-deals as required within the APCDM model itself. The model output prescribes a set of equitable flight plans based on admissible trades and exchanges of assigned slots, which are in addition conformant with sector workload capabilities and conflict risk restrictions. The net reduction in passenger-minutes of delay for each airline is the primary metric used to assess and compare model solutions. Appropriate constraints are included in the model to ensure that the generated slot exchanges induce nonnegative values of this realized net reduction for each airline. In keeping with the spirit of the FAA's CDM initiative, we next propose four alternative equity methods that are predicated on different specified performance ratios and related efficiency functions. These four methods respectively address equity with respect to slot-exchange-related measures such as total average delay, net delay savings, proportion of acceptable moves, and suitable value function realizations. For our computational experiments, we constructed several scenarios using real data obtained from the FAA based on the Enhanced Traffic Management System (ETMS) flight information pertaining to the Miami and Jacksonville Air Route Traffic Control Centers (ARTCC). Through our experimentation, we provide insights into the effect of the different proposed modeling concepts and study the sensitivity with respect to certain key parameters. In particular, we compare the alternative proposed equity formulations by evaluating their corresponding slot-exchange solutions with respect to the net reduction in passenger-minutes of delay for each airline. Additionally, we evaluate and compare the computational-effort performance, under both time limits and optimality thresholds, for each equity method in order to assess the efficiency of the model. The four slot-exchange-based equity formulations, in conjunction with the internal slot-exchange mechanisms, demonstrate significant net savings in computational effort ranging from 25% to 86% over the original APCDM model equity formulation. The model has been implemented using Microsoft Visual C++ and evaluated using a C++ interface with CPLEX 9.0. The overall results indicate that the proposed modeling concepts offer viable tools that can be used by the FAA in a timely fashion for both tactical purposes, as well as for exploring various strategic issues such as air traffic control policy evaluations; dynamic airspace resectorization strategies as a function of severe weather probabilities; and flight plan generation in response to various disruption scenarios. / Ph. D.