No description available.

The aim of this thesis is to understand the current implementation, how different hardware and output frequency affects the hydraulic actuators in the current platform and Then an improve the controller should be presented. This needs to be both faster then the current controller and should not use more CPU recurses then necessary. With the understanding of current controller, three new regulators where implemented and tested. One uses a PI regulator and the other two uses an adaptive algorithm to generate the control signal. All where faster than the current one and the PI-implementation uses the lowest amount of CPU recurses, on the other hand this needs to be calibrated for the different hardware and output frequency’s. ThetwoadaptivecontrollersrequiresahigheramountofCPUrecurses, instead it requires less calibration to work.

It is the period of the World's history, where the technological progress reached a level that enables the first steps towards the development of vehicles with automated driving capabilities. The swift response from the significant portion of the industry resulted in a race, the final line set at the introduction of vehicles with full automated driving capabilities. Vehicles with automated driving capabilities target making driving safer, more comfortable, and economically more efficient by assisting the driver or by taking responsibilities for different driving tasks. While vehicles with assistance and partial automation capabilities are already in series production, the ultimate goal is in the introduction of vehicles with full automated driving capabilities. Reaching this level of automation will require shifting all responsibilities, including the responsibility for the overall vehicle safety, from the human to the computer-based system responsible for the automated driving functionality (i.e., the Automated Driving System (ADS)). Such a shift makes the ADS highly safe-critical, requiring a safety level comparable to an aircraft system. It is paramount to understand that ensuring such a level of safety is a complex interdisciplinary challenge. Traditional approaches for ensuring safety require the use of fault-tolerance techniques that are unproven when it comes to the automated driving domain. Moreover, existing safety assurance methods (e.g., ISO 26262) suffer from requirements incompleteness in the automated driving context. The use of artificial intelligence-based components in the ADS further complicate the matter due to their non-deterministic behavior. At present, there is no single straightforward solution for these challenges. Instead, the consensus of cross-domain experts is to use a set of complementary safety methods that together are sufficient to ensure the required level of safety. In the context of that, runtime monitors that verify the safe operation of the ADS during execution, are a promising complementary approach for ensuring safety. However, to develop a runtime monitoring solution for ADS, one has to handle a wide range of challenges. On a conceptual level, the complex and opaque technology used in ADS often make researchers ask the question ``how should ADS be verified in order to judge it is operating safely?". Once the initial Runtime Verification (RV) concept is developed, researchers and practitioners have to deal with research and engineering challenges encountered during the realization of the RV approaches into an actual runtime monitoring solution for ADS. These challenges range from, estimating different safety parameters of the runtime monitors, finding solutions for different technical problems, to meeting scalability and efficiency requirements. The focus of this thesis is to propose novel runtime monitoring solutions for verifying the safe operation of ADS. This encompasses (i) defining novel RV approaches explicitly tailored for automated driving, and (ii) developing concepts, methods, and architectures for realizing the RV approaches into an actual runtime monitoring solution for ADS. Contributions to the former include defining two runtime RV approaches, namely the Computer Vision Monitor (CVM) and the Safe Driving Envelope Verification. Contributions to the latter include (i) estimating the sufficient diagnostic test interval of the runtime verification approaches (in particular the CVM), (ii) addressing the out-of-sequence measurement problem in sensor fusion-based ADS, and (iii) developing an architectural solution for improving the scalability and efficiency of the runtime monitoring solution. / RetNet

Wireless sensor networks (WSNs) are used in all kinds of different sectors ranging from agriculture, environment, healthcare and the military. Embedded systems such as sensor nodes are low-power and consist of low memory, which creates a challenge for its security. One of WSN’s worst enemies is interference radio jamming attacks. They are easy to construct and execute, but hard to detect and identify. In this thesis, we tackle the problems of detecting, but most importantly identifying, and distinguishing the most commonly used interference radio jamming attacks. Presenting SpeckSense++, a firmware that makes it possible for low-power embedded systems to detect, identify and distinguish interference radio jamming attacks and unintentional interference such as Bluetooth and WiFi to a certain degree. Showing an accuracy of 96 to 90 % for proactive jammers, 89% for reactive, and 92 to 85 % for unintentional interference.

The purpose of this project was to investigate if it is possible to have local wireless control of an industrial robot. This was achieved by first doing a diversity of research. Based on the research, the project was conceptualized and a real-life product was developed showcasing the functionality. The standard robot set up as of today consists of three main parts: A robot, a control unit and a handheld controller device, called Teach Pendant. All of these parts are connected with long aggravating cables. The cables cause inconvenience and can in some cases introduce unnecessary risks in the factory. Can this hardware be removed, and an overall more convenient use case be developed? The product was developed by programming an application on a Windows tablet. Further, a Bluetooth Low Energy server was created to handle the communication between the tablet and the robot control unit. The final product consisted of a tablet, a single-board computer, a robot and a control unit. The tablet is what replaces the Teach Pendant as a handheld device. The tablet is connected to the singleboard computer via Bluetooth. The single-board computer acts as a Bluetooth server and sends out advertisements for the tablet to detect. When the tablet detects a nearby robot it can then connect to it and send start and stop commands. The server then forwards it to the control unit which finally sends the data to the robot control unit to execute. The project shows that it is possible to develop wireless robot control. It showcases a potential solution on how one could set it up. However, the final product developed had a simple functionality compared to the wired Teach Pendant. To manage the same capacity as the wired Teach Pendent, further development is required.

To set up port forwarding rules on network gateways, certain technical skills are requiredfrom end-users. These assumptions in the gateway software stack, can lead to an increasein support calls to network operators and resellers of customer premises equipment. Theuser interface itself is also an important part of the product and a complicated interfacewill contribute to a lessened user experience. Other issues with an overwhelming userinterface include the risk of faulty configuration by the user, potentially leaving the networkvulnerable to attacks.We present an enhancement of the current port forwarding configuration in the gatewaysoftware, with an extensible library of presets along with usability improvements. To helpusers with detecting available services, a wrapper for a network scanner is implemented, fordetecting devices and services on the local network. These parts combined relieves end-usersof looking up forwarding rules for ports and protocols to configure their gateway, basingtheir decisions on data collected by the network scanner or by using an applications nameinstead of looking up its ports. Another usability improvement is an internal DNS service,which enables access to the gateway interface through a human-memorable domain name,instead of using the LAN IP address.Using the Nmap utility for identifying services on the network, could be consideredharmful activity by network admins and intrusion detection systems. The preset libraryis extensible and generic enough to be included in the default software suite shipping withthe network equipment. Working within the unified configuration system of OpenWrt, thepreset design will add value and allow resellers to easily customize it to their services. Thisproposal could reduce support costs for the service operators and improve user experiencein configuring network gateways. / Vid portmappning i nätverksgateways krävs det vissa tekniska förkunskaper av användaren.Höga krav på kunskapsnivå kan leda till ett ökat antal supportsamtal för återförsäljareoch nätverksoperatörer. Användargränssnittet i sig är också en viktig del i produkten ochett komplicerat gränssnitt bidrar till försämrad användarupplevelse. Övriga problem medkomplicerade användargränssnitt är risken för felaktig konfiguration, vilket kan försämraIT-säkerheten på nätverket.En förändring av nuvarande inställningar för portmappning presenteras, tillsammansmed ett utbyggbart bibliotek med förinställda regler, samt generella förbättringar av an-vändargränssnittet. Ytterligare förbättringar av användarvänligheten sker i form av nä-tadressöversättning, som möjliggör åtkomst till nätverksgateway via domännamn som ärenklare att minnas än IP adressens siffror. För att hjälpa användare med identifikationav enheter och att göra rätt inställningar, utvecklas en wrapper för en portskanner, somautomatiskt kan identifiera enheter och nättjänster på det lokala nätverket. Tillsammansunderlättar dessa delar för slutanvändaren, befriar den från att referera till regler för portaroch protokoll och möjliggör inställningar enbart genom att använda portskanning eller väljanamnet på önskad tjänst från en lista.Användandet av verktyget Nmap för att identifiera nättjänster på nätverket kan kommaatt betraktas som dataintrång av nätverksadministratörer och intrångdetekteringssystem.Konfigurationsfilerna med förinställningar är utbyggbar, fungerar och passar in tillräck-ligt bra för att levereras med standardmjukvaran. Via det centraliserade konfigurationssys-temet i OpenWrt, kommer utformningen av systemet med förinställningar för portmappningmöjliggöra för komplementering av återförsäljare, för att innefatta deras respektive nät-tjänster och enheter som kräver vidarebefodring av särskilda portar. Systemet kan minskasupportkostnader för bredbandsleverantörer och bidra till en förbättrad användarupplevelsevid konfiguration av nätverksgateways.

This report is about the evaluation of different microcontrollers and their current con-sumption, specifically microcontrollers that will run AI models. The company Sensorbeeneeds a new microcontroller for their future projects. One of the areas of use will be AImodels. The most important parameter for Sensorbee is current consumption, minimizingcurrent consumption is a top priority as their products are powered by batteries or solarpanels. At the beginning of the project, the focus was on which microcontroller had thelowest current consumption. For AI models in particular, however, it turned out to be avery big difference in the optimization of the software. A well-optimized AI model canquickly classify data, which in turn leads to the microcontroller being able to spend muchof its time in sleep mode. This meant that not only the current consumption of the micro-controller could be taken into account, but how fast it ran through an AI model was at leastas important, if not more important. Even how easy it was for Sensorbee to get startedwith the new processor had to be evaluated, as Sensorbee is a small company that has littleresources to move around with. The candidate that was most promising in the beginningproved to be useless as the performance of the AI model was too poor and the general sup-port for the microcontroller was unsatisfactory. It turns out that there are a lot of variablesto consider when choosing a microcontroller and not just what is in the datasheet.

The heart disease Atrial Fibrillation (AFib) has increased worldwide in recent years. Untreated AFib can lead to cardiovascular complications such as stroke and heart failure. AFib is detected by physicians using Electrocardiogram (ECG). Since this disease can occur without symptoms for some patients, it can lead to late detection. Therefore, smart solutions for continuous monitoring of ECG to detect AFib is needed. This paper presents an approach to model an low-cost intelligent health monitoring system (IHMS) to classify and detect AFib in ECG using 1D Convolutional Neural Network (CNN). The core objective of this paper were to investigate the suitability of the computing architecture, edge and cloud, for an IHMS, and how complex 1D-CNN could be deployed to an edge device. Three 1D-CNN models with increased complexity was designed, trained and tested on AFib and NSR episodes collected from 25 records of the LTAF database. Each record were noise filtered and segmented into 10 sec. The best 1D-CNN model presented an accuracy of 83.93 %, 89.83 % in AUC, 84.32 % in sensitivity (AFIb), 83.46 % in specificity (NSR), 84.81 % in F1-score and 68.23 % in MCC. Two experiments into end-to-end delay and prediction time were performed todetermine the computing architectures suitability. The end-to-end delay were measured by sending ECG segments of different sizes to both computing architectures, while the prediction time were measured by deploying the designed 1D-CNN models on both computing architectures. Both measurements were added together to form the response time of the computing architectures. The edge computing architecture produced a delay around 0.019-0.377 sec and prediction time around 0.00X sec compared to cloud’s delay around 1.32-4.43 sec and 0.000X in prediction time. Resulting, that the edge computing architecture produced a lower response time and therefore considered the more suitable architecture for an IHMS. The designed 1D-CNN models had no issues in executing on the edge device, resulting in the conclusion that the most complex model to execute had 6 convolutional layers. The presented result in this paper contributes to the development of a health monitoring system in terms of choosing computing architecture platform and model complexity for a resource constraint device.

In real-time systems functional requirements are coupled to timing requirements, a specified event needs to occur at the appropriate time.  In order to ensure that timing requirements are fulfilled, there are two main approaches, static and measurement-based. The static approach relies on modeling the hardware and software and calculating upper bounds for the timing behavior. On the other hand, measurement-based approaches use timing data collected from the system to estimate the timing behavior. The usability of static and measurement-based approaches is limited in many modern systems due to the increased complexity of hardware and software architectures. Static approaches to timing and schedulability analysis are often infeasible due to their complexity. Measurement-based approaches require that design-time measurements are representative of the timing behavior at runtime, which is problematic to ensure in many cases. Designing systems that guarantee the timing requirements without excessive resource overprovisioning is a challenge. A Hidden Markov Model (HMM) describes a system where the behavior is state-dependent.  In this thesis, we model the execution time distribution of a periodic task as an HMM where the states are associated with continuous emission distributions. By modeling the execution times in this manner with a limited number of parameters, a step is taken on the path toward tracking and controlling timing properties at runtime.  We present a framework for parameter identification of an HMM with Gaussian emission distributions from timing traces, and validation of the identified models. In evaluated cases, the parameterized models are valid in relation to timing traces. For cases where design-time measurements are not representative of the system at runtime we present a method for the online adaptive update of the emission distributions of an HMM. Evaluation with synthetic data shows that the estimate tracks the ground truth distribution.  A method for estimating the deadline miss probability for a task with execution times modeled by an HMM with Gaussian emission distributions, in a Constant Bandwidth Server (CBS) is proposed. The method is evaluated with simulation and for a synthetic task with a known Markov Chain structure running on real hardware. / I realtidssystem är funktionella krav kopplade till tidskrav – en viss händelse måste inträffa vid rätt tid. För att försäkra sig om att tidskrav är uppfyllda finns två huvudsakliga metoder – statisk eller mätningsbaserad. En statisk analys baseras på modeller av hårdvara och mjukvara, och beräknar en övre gräns för tidsbeteendet. Mätningsbaserade analyser använder insamlat data från systemet för att uppskatta tidsbeteendet. Användbarheten av både statiska och mätningsbaserade metoder är begränsad i många moderna system eftersom komplexiteten hos hårdvara och mjukvara ökat. Statiska metoder är ofta omöjliga att genomföra på grund av komplexiteten. För mätningsbaserade metoder krävs att mätningarna som insamlats vid design är representativa för tidsbeteendet i drift, vilket är svårt att garantera i många fall. Att designa system som garanterar tidskraven utan överdriven resurstilldelning är en utmaning. En Hidden Markov Model (HMM) beskriver ett system med beteende som är tillståndsberoende. I denna avhandling modellerar vi exekveringstidens fördelning hos en periodisk task (uppgift) som en HMM där tillstånden är kopplade till kontinuerliga emissionsfördelningar. Genom att modellera exekveringstiderna på detta vis med ett begränsat antal parametrar, tar vi ett steg på vägen mot att följa och kontrollera tidsbeteendet i drift. Vi presenterar ett ramverk för parameteridentifiering för en HMM med Gaussiska emissionsfördelningar från tidsdata, och validering av de identifierade modellerna. De parametriserade modellerna är giltiga i relation till tidsdata i de fall som utvärderats. För fall när mätningar vid design inte är representativa för systemet i drift presenterar vi en metod för direkt adaptiv uppdatering av emissionsfördelningarna i en HMM. Utvärdering med syntetiska data visar att uppskattningen följer den sanna fördelningen. En metod föreslås för att uppskatta sannolikheten för att missa en deadline när exekveringstiden modelleras som en HMM med Gaussiska emissionsfördelningar hos en task i en Constant Bandwidth Server (CBS). Metoden utvärderas med simulering och med syntetiska program med känd Markov-struktur som körs på verklig hårdvara.

The increasing usage of electronics and software in a modern automobile enables realization of many advanced features. One such feature is autonomous driving. Autonomous driving means that a human driver’s intervention is not required to drive the automobile; rather, theautomobile is capable of driving itself. Achieving automobile autonomyrequires research in several areas, one of which is the area of automotive electrical/electronics (E/E) architectures. These architectures deal with the design of the computer hardware and software present inside various subsystems of the vehicle, with particular attention to their interaction and modularization. The aim of this thesis is to investigate how automotive E/E architectures should be designed so that 1) it ispossible to realize autonomous features and 2) a smooth transition canbe made from existing E/E architectures, which have no explicit support for autonomy, to future E/E architectures that are explicitly designed for autonomy.The thesis begins its investigation by considering the specific problem of creating autonomous behavior under cooperative driving condi-tions. Cooperative driving conditions are those where continuous wireless communication exists between a vehicle and its surroundings, which consist of the local road infrastructure as well as the other vehicles in the vicinity. In this work, we define an original reference architecture for cooperative driving. The reference architecture demonstrates how a subsystem with specific autonomy features can be plugged into an existing E/E architecture, in order to realize autonomous driving capabilities. Two salient features of the reference architecture are that it isminimally invasive and that it does not dictate specific implementation technologies. The reference architecture has been instantiated on two separate occasions and is the main contribution of this thesis. Another contribution of this thesis is a novel approach to the design of general, autonomous, embedded systems architectures. The approach introduces an artificial consciousness within the architecture, that understands the overall purpose of the system and also how the different existing subsystems should work together in order to meet that purpose.This approach can enable progressive autonomy in existing embedded systems architectures, over successive design iterations. / <p>QC 20130412</p>