Visual Simultaneous Localization And Mapping (V-SLAM) and object detection algorithms are two critical prerequisites for modern XR applications. V-SLAM allows XR devices to geometrically map the environment and localize itself within the environment, simultaneously. Furthermore, object detectors based on Deep Neural Network (DNN) can be used to semantically understand what those features in the environment represent. However, both of these algorithms are computationally expensive, which makes it challenging for them to achieve good real-time performance on device. In this thesis, we first present TensoRT Quantized YOLOv4 (TRTQYOLOv4), a faster implementation of YOLOv4 architecture [1] using FP16 reduced precision and INT8 quantization powered by NVIDIA TensorRT [2] framework. Second, we propose the V-SLAM Hurdler: A Faster VSLAM System using Online Dynamic-and-Hardness-aware Approximation. The proposed system integrates the base RGB-D V-SLAM ORB-SLAM3 [3] with the INT8 TRTQ-YOLOv4 object detector, a novel Entropy-based Degreeof- Difficulty Estimator, an Online Hardness-aware Approximation Controller and a Dynamic Object Eraser, applying online dynamic-and-hardness aware approximation to the base V-SLAM system during runtime while increasing its robustness in dynamic scenes. We first evaluate the proposed object detector on public object detection dataset. The proposed FP16 precision TRTQ-YOLOv4 achieves 2×faster than the full-precision model without loss of accuracy, while the INT8 quantized TRTQ-YOLOv4 is almost 3×faster than the full-precision one with only 0.024 loss in mAP@50:5:95. Second, we evaluate our proposed V-SLAM system on public RGB-D SLAM dataset. In static scenes, the proposed system speeds up the base VSLAM system by +21.2% on average with only −0.7% loss of accuracy. In dynamic scenes, the proposed system not only accelerate the base system by +23.5% but also improves the accuracy by +89.3%, making it as robust as in the static scenes. Lastly, the comparison against the state-of-the-art SLAMs designed dynamic environments shows that our system outperforms most of the compared methods in highly dynamic scenes. / Visual SLAM (V-SLAM) och objektdetekteringsalgoritmer är två kritiska förutsättningar för moderna XR-applikationer. V-SLAM tillåter XR-enheter att geometriskt kartlägga miljön och lokalisera sig i miljön samtidigt. Dessutom kan DNN-baserade objektdetektorer användas för att semantiskt förstå vad dessa egenskaper i miljön representerar. Men båda dessa algoritmer är beräkningsmässigt dyra, vilket gör det utmanande för dem att uppnå bra realtidsprestanda på enheten. I det här examensarbetet presenterar vi först TRTQ-YOLOv4, en snabbare implementering av YOLOv4 arkitektur [1] med FP16 reducerad precision och INT8 kvantisering som drivs av NVIDIA TensorRT [2] ramverk. För det andra föreslår vi V-SLAM-häckaren: ett snabbare V-SLAM-system som använder online-dynamisk och hårdhetsmedveten approximation. Det föreslagna systemet integrerar basen RGB-D V-SLAM ORB-SLAM3 [3] med INT8 TRTQYOLOv4 objektdetektorn, en ny Entropi-baserad svårighetsgradsuppskattare, en online hårdhetsmedveten approximationskontroller och en Dynamic Object Eraser, applicerar online-dynamik- och hårdhetsmedveten approximation till bas-V-SLAM-systemet under körning samtidigt som det ökar dess robusthet i dynamiska scener. Vi utvärderar först den föreslagna objektdetektorn på datauppsättning för offentlig objektdetektering. Den föreslagna FP16 precision TRTQ-YOLOv4 uppnår 2× snabbare än fullprecisionsmodellen utan förlust av noggrannhet, medan den INT8 kvantiserade TRTQ-YOLOv4 är nästan 3× snabbare än fullprecisionsmodellen med endast 0.024 förlust i mAP@50:5:95. För det andra utvärderar vi vårt föreslagna V-SLAM-system på offentlig RGB-D SLAM-datauppsättning. I statiska scener snabbar det föreslagna systemet upp V-SLAM-bassystemet med +21.2% i genomsnitt med endast −0.7% förlust av noggrannhet. I dynamiska scener accelererar det föreslagna systemet inte bara bassystemet med +23.5% utan förbättrar också noggrannheten med +89.3%, vilket gör det lika robust som i de statiska scenerna. Slutligen visar jämförelsen med de senaste SLAM-designade dynamiska miljöerna att vårt system överträffar de flesta av de jämförda metoderna i mycket dynamiska scener.

Dynamic Spectrum Access (DSA) has strong potential to address the need for improved spectrum efficiency. Unfortunately, traditional DSA approaches such as simple "sense-and-avoid" fail to provide sufficient performance in many scenarios. Thus, the combination of sensing with deep reinforcement learning (DRL) has been shown to be a promising alternative to previously proposed simplistic approaches. DRL does not require the explicit estimation of transition probability matrices and prohibitively large matrix computations as compared to traditional reinforcement learning methods. Further, since many learning approaches cannot solve the resulting online Partially-Observable Markov Decision Process (POMDP), Deep Recurrent Q-Networks (DRQN) have been proposed to determine the optimal channel access policy via online learning. The fundamental goal of this dissertation is to develop DRL-based solutions to address this POMDP-DSA problem. We mainly consider three aspects in this work: (1) optimal transmission strategies, (2) combined intelligent sensing and transmission strategies, and (c) learning efficiency or online convergence speed. Four key challenges in this problem are (1) the proposed DRQN-based node does not know the other nodes' behavior patterns a priori and must to predict the future channel state based on previous observations; (2) the impact to primary user throughput during learning and even after learning must be limited; (3) resources can be wasted the sensing/observation; and (4) convergence speed must be improved without impacting performance performance. We demonstrate in this dissertation, that the proposed DRQN can learn: (1) the optimal transmission strategy in a variety of environments under partial observations; (2) a sensing strategy that provides near-optimal throughput in different environments while dramatically reducing the needed sensing resources; (3) robustness to imperfect observations; (4) a sufficiently flexible approach that can accommodate dynamic environments, multi-channel transmission and the presence of multiple agents; (5) in an accelerated fashion utilizing one of three different approaches. / Doctor of Philosophy / With the development of wireless communication, such as 5G, global mobile data traffic has experienced tremendous growth, which makes spectrum resources even more critical for future networks. However, the spectrum is an exorbitant and scarce resource. Dynamic Spectrum Access (DSA) has strong potential to address the need for improved spectrum efficiency. Unfortunately, traditional DSA approaches such as simple "sense-and-avoid" fail to provide sufficient performance in many scenarios. Thus, the combination of sensing with deep reinforcement learning (DRL) has been shown to be a promising alternative to previously proposed simplistic approaches. Compared with traditional reinforcement learning methods, DRL does not require explicit estimation of transition probability matrices and extensive matrix computations. Furthermore, since many learning methods cannot solve the resulting online partially observable Markov decision process (POMDP), a deep recurrent Q-network (DRQN) is proposed to determine the optimal channel access policy through online learning. The basic goal of this paper is to develop a DRL-based solution to this POMDP-DSA problem. This paper mainly focuses on improving performance from three directions. 1. Find the optimal (or sub-optimal) channel access strategy based on fixed partial observation mode; 2. Based on work 1, propose a more intelligent way to dynamically and efficiently find more reasonable (higher efficiency) sensing/observation policy and corresponding channel access strategy; 3. On the premise of ensuring performance, use different machine learning algorithms or structures to improve learning efficiency and avoid users waiting too long for expected performance. Through the research in these three main directions, we have found an efficient and diverse solution, namely DRQN-based technology.

“Temporary urbanism” is a concept that can go by a number of different names and can take different forms. This means that the concept has a dynamic and experimental character, it can represent different types of uses and needs of different target groups and users. The concept originates from New York, during the 20th-century, and usually involves an urban planning strategy that promotes social sustainability by reducing the car use in cities and instead shift the focus to the citizens. Temporary urbanism can therefore act as a catalyst to change the norm and meaning of urban spaces, and who they are for. In the Swedish context, information about the concept is not available to everyone, as it is limited to existing within urban planning and is therefore primarily aimed at top-down initiated projects. If temporary urbanism is to be represented in the right way, as a flexible and versatile tool, more target groups need to be able to use the concept, in order to create their own initiatives in urban spaces. If the public space, evaluated as a resource, is not used all year round in different ways and by a variation of target groups, it would become what we call wasted space. Hence, citizens must be given access to proper tools in order to influence the development of the urban spaces and what they contain. Throughout the bachelor's thesis, desk studies have been used, supplemented with interviews and an example of the trendy concept of “summer streets”. All this to understand how temporary urbanism commonly is expressed in Sweden and what potential development the concept has in the utilization in Swedish context. This thesis has resulted in a design proposal for a handbook. The handbook summarizes and analyzes the concept of temporary urbanism and its use in the Swedish context. It also showcases international examples of how the concept could be expressed broadly and diversified to inspire. The handbook results in an understanding of how awareness can increase, create an understanding of the concept, and promote citizen participation in the design of public spaces. It clarifies the concept of temporary urbanism and makes it accessible for all, so that more people can use the strategies it includes to curate urban spaces. / “Temporär urbanism” är ett begrepp som kan gå under en rad olika benämningar och kan ta olika skepnader. Det innebär att konceptet har en dynamisk och experimentell karaktär, det kan representera olika typer av användningar samt olika målgruppers och användares behov. Konceptet har sitt ursprung i New York, under 1900-talet, och innebär oftast en stadsplaneringsstrategi som främjar social hållbarhet genom att minska bilismens starka fäste i staden för att istället skifta fokuset till medborgarna. Temporär urbanism kan därför fungera som katalysator för att förändra normen för vad urbana rum innebär och vilka de är till för. I svensk kontext är informationen om detta koncept inte tillgängligt för alla, då den begränsas till att vara ett begrepp inom stadsplaneringen och riktar sig därför främst till top-down initierade projekt. Om temporär urbanism ska representeras på rätt sätt, som ett flexibelt och mångsidigt verktyg, behöver fler målgrupper kunna använda sig av konceptet för att ta egna initiativ i urbana rum. Om stadsrummet, sedd som resurs, inte utnyttjas året om på olika sätt och av varierande målgrupper, skulle det bli vad vi kallar ett outnyttjat utrymme. Därav måste medborgare ges tillgång till goda verktyg för att få påverka utvecklingen av stadsrummen och vad de innehåller. Genom uppsatsen har skrivbordsstudier använts, kompletterat med intervjuer och ett typexempel av det trendiga konceptet “sommargator”, även kallat “sommargågator”. Detta för att förstå hur temporär urbanism oftast uttrycker sig i Sverige och därmed vad konceptet har för utvecklingspotential i tillämpningen i den svenska kontexten.  Denna uppsats har mynnat ut i ett designförslag av en handbok. Handboken sammanfattar och analyserar konceptet temporär urbanism och dess användning i svensk kontext. Den tar även upp internationella exempel på hur konceptet skulle kunna uttryckas för att inspirera och visa på bredd och mångfald. Handboken resulterar i att förstå hur medvetenheten kan öka, skapa förståelse för konceptet, främja medborgarnas deltagande i utformningen av stadens offentliga rum. Den tillgängliggör och tydliggör konceptet för temporär urbanism för att fler ska kunna använda sig av strategierna som det innefattar, för att kurera urbana rum.