Mobile robots need to move in the real world for the majority of tasks. Their control is often intertwined with the tasks they have to solve. Unforeseen events must have an adequate and prompt reaction, in order to solve the corresponding task satisfactorily. A robust system must be able to respond to a variety of events with specific solutions and strategies to keep the system running. Robot navigation control systems are essential for this. In this thesis we present a robot navigation control system that fulfills these requirements: Move Base Flex. Furthermore, the map representation used to model the environment is essential for path planning. Depending on the representation of the map, path planners can solve problems like simple 2D indoor navigation, but also complex rough terrain outdoor navigation with multiple levels and varying slopes, if the corresponding representation can model them accurately. With Move Base Flex, we present a middle layer navigation framework for navigation control, that is map independent at its core. Based on this, we present the Mesh Navigation Stack to master path planning in complex outdoor environments using a developed mesh map to model surfaces in 3D. Finally, to solve path planning in complex outdoor environments, we have developed and integrated the Continuous Vector Field Planner with the aforementioned solutions and evaluated it on five challenging and complex outdoor datasets in simulation and in the real-world. Beyond that, the corresponding developed software packages are open source available and have been released to easily reproduce the provided scientific results.

Considering the ever-growing global demand for raw materials and the complexity of the geological deposits that are still to be found, high-quality extensive mineralogical information is required. Mineral exploration remains a risk-prone process, with empirical approaches prevailing over data-driven strategy. Amongst the many ways to innovate, hyperspectral imaging sensors for drill-core mineral mapping are one of the disruptive technologies. This potential could be multiplied by implementing machine learning. This dissertation introduces a workflow that allows the use of supervised learning to map minerals by means of ancillary data commonly acquired during exploration campaigns (i.e., mineralogy, geochemistry and core photography). The fusion of hyperspectral with such ancillary data allows not only to upscale to complete boreholes information acquired locally, but also to enhance the spatial resolution of the mineral maps. Thus, the proposed approaches provide digitally archived objective maps that serve as vectors for exploration and support geologists in their decision making.:List of Figures xviii List of Tables xix List of Acronyms xxi 1 Introduction 1 1.1 Mineral resources and the need for innovation . . . . . . . . . . . . . 2 1.2 Spectroscopy and hyperspectral imaging . . . . . . . . . . . . . . . . 5 1.2.1 Imaging spectroscopy ....................... 6 1.2.2 Spectroscopy of minerals ..................... 8 1.2.3 Mineral mapping.......................... 12 1.2.4 Mineral mapping in exploration ................. 15 1.2.5 Drill-core mineral mapping.................... 16 1.3 Machine learning .............................. 19 1.3.1 Supervised learning for drill-core hyperspectral data . . . . . 20 1.4 Motivation and approach ......................... 22 2 Hyperspectral mineral mapping using supervised learning and mineralogical data 25 Preface ....................................... 25 Abstract....................................... 26 2.1 Introduction ................................. 27 2.2 Data acquisition............................... 30 2.2.1 Hyperspectral data......................... 30 2.2.2 High-resolution mineralogica ldata . . . . . . . . . . . . . . . 31 2.3 Proposed system architecture ....................... 33 2.3.1 Re-sampling and co-registration ................. 33 2.3.2 Classification ............................ 35 2.4 Experimental results ............................ 36 2.4.1 Data description .......................... 36 2.4.2 Experimental setup......................... 37 2.4.3 Quantitative and qualitative assessment . . . . . . . . . . . . . 37 2.5 Discussion.................................. 40 2.6 Conclusion.................................. 42 3 Geochemical and hyperspectral data integration 45 Preface ....................................... 45 Abstract....................................... 46 3.1 Introduction ................................. 47 3.2 Basis for the integration of geochemical and hyperspectral data . . . 50 3.3 Proposed approach ............................. 51 3.3.1 Geochemical data labeling..................... 51 3.3.2 Superpixel segmentation ..................... 53 3.3.3 Classification ............................ 53 3.4 Experimental results ............................ 54 3.4.1 Data description .......................... 54 3.4.2 Data acquisition........................... 55 3.4.3 Experimental setup......................... 55 3.4.4 Assessment of the geochemical data labeling . . . . . . . . . . 58 3.4.5 Quantitative and Qualitative Assessment . . . . . . . . . . . . 58 3.5 Discussion.................................. 61 3.6 Conclusion.................................. 63 4 Improved spatial resolution for mineral mapping 65 Preface ....................................... 65 Abstract....................................... 66 4.1 Introduction ................................. 67 4.2 Methods: Resolution Enhancement for Mineral Mapping . . . . . . . 69 4.2.1 Hyperspectral Resolution Enhancement . . . . . . . . . . . . . 69 4.2.2 Mineral Mapping.......................... 71 4.2.3 Supervised Classification ..................... 71 4.3 Case Study.................................. 72 4.3.1 Data Acquisition .......................... 72 4.3.2 Resolution Enhancement Application . . . . . . . . . . . . . . 74 4.3.3 Evaluation of the Resolution Enhancement . . . . . . . . . . . 75 4.4 Results .................................... 76 4.4.1 Mineral Mapping.......................... 76 4.4.2 Supervised Classification ..................... 77 4.4.3 Validation .............................. 80 4.5 Discussion.................................. 82 4.6 Conclusions ................................. 84 5 Bibliography 92

In unserem Vortrag stellen wir die verbesserte Version des vor zwei Jahren präsentierten Kanu KI Analysators vor. Die automatische Paddel- und Paddelwinkelerkennung ist mit einer Trefferquote von über 99% sehr robust geworden. Die Erkennung der Paddelposen des Technikleitbildes hat sich von 37% auf 60% verbessert. / In our presentation, we introduce the improved version of the Canoe AI Analyzer presented two years ago. The automatic paddle and paddle angle detection has become very robust with an accuracy rate of over 99%. The paddle pose detection of the technique guide has improved from 37% to 60%.

The text-guided diffusion model GLIDE (Guided Language to Image Diffusion for Generation and Editing) is the state of the art in text-to-image generative artificial intelligence (AI). GLIDE has rich representations, but medical applications of this model have not been systematically explored. If GLIDE had useful medical knowledge, it could be used for medical image analysis tasks, a domain in which AI systems are still highly engineered towards a single use-case. Here we show that the publicly available GLIDE model has reasonably strong representations of key topics in cancer research and oncology, in particular the general style of histopathology images and multiple facets of diseases, pathological processes and laboratory assays. However, GLIDE seems to lack useful representations of the style and content of radiology data. Our findings demonstrate that domain-agnostic generative AI models can learn relevant medical concepts without explicit training. Thus, GLIDE and similar models might be useful for medical image processing tasks in the future - particularly with additional domain-specific fine-tuning.

Stains and stained incipient lesions can be challenging to differentiate with established clinical tools. New diagnostic techniques are required for improved distinction to enable early noninvasive treatment. This in vitro study evaluates the performance of artificial intelligence (AI)-based classification of hyperspectral imaging data for early occlusal lesion detection and differentiation from stains. Sixty-five extracted permanent human maxillary and mandibular bicuspids and molars (International Caries Detection and Assessment System [ICDAS] II 0–4) were imaged with a hyperspectral camera (Diaspective Vision TIVITA® Tissue, Diaspective Vision, Pepelow, Germany) at a distance of 350 mm, acquiring spatial and spectral information in the wavelength range 505–1000 nm; 650 fissural spectra were used to train classification algorithms (models) for automated distinction between stained but sound enamel and stained lesions. Stratified 10-fold cross-validation was used. The model with the highest classification performance, a fine k-nearest neighbor classification algorithm, was used to classify five additional tooth fissural areas. Polarization microscopy of ground sections served as reference. Compared to stained lesions, stained intact enamel showed higher reflectance in the wavelength range 525–710 nm but lower reflectance in the wavelength range 710–1000 nm. A fine k-nearest neighbor classification algorithm achieved the highest performance with a Matthews correlation coefficient (MCC) of 0.75, a sensitivity of 0.95 and a specificity of 0.80 when distinguishing between intact stained and stained lesion spectra. The superposition of color-coded classification results on further tooth occlusal projections enabled qualitative assessment of the entire fissure’s enamel health. AI-based evaluation of hyperspectral images is highly promising as a complementary method to visual and radiographic examination for early occlusal lesion detection.

Moderne Präzisionsgartenbaulicheproduktion schließt hoch technifizierte Gewächshäuser, deren Einsatz in großem Maße von der Qualität der Sensorik- und Regelungstechnik abhängt, mit ein. Zu den Regelungsstrategien gehören unter anderem Methoden der Künstlichen Intelligenz, wie z.B. Künstliche Neuronale Netze (KNN, aus dem Englischen). Die vorliegende Arbeit befasst sich mit der Eignung KNN-basierter Modelle als Bauelemente von Klimaregelungstrategien in Gewächshäusern. Es werden zwei Modelle vorgestellt: Ein Modell zur kurzzeitigen Voraussage des Gewächshausklimas (Lufttemperatur und relative Feuchtigkeit, in Minuten-Zeiträumen), und Modell zur Einschätzung von phytometrischen Signalen (Blatttemperatur, Transpirationsrate und Photosyntheserate). Eine Datenbank, die drei Kulturjahre umfasste (Kultur: Tomato), wurde zur Modellbildung bzw. -test benutzt. Es wurde festgestellt, dass die ANN-basierte Modelle sehr stark auf die Auswahl der Metaparameter und Netzarchitektur reagieren, und dass sie auch mit derselben Architektur verschiedene Kalkulationsergebnisse liefern können. Nichtsdestotrotz, hat sich diese Art von Modellen als geeignet zur Einschätzung komplexer Pflanzensignalen sowie zur Mikroklimavoraussage erwiesen. Zwei zusätzliche Möglichkeiten zur Erstellung von komplexen Simulationen sind in der Arbeit enthalten, und zwar zur Klimavoraussage in längerer Perioden und zur Voraussage der Photosyntheserate. Die Arbeit kommt zum Ergebnis, dass die Verwendung von KNN-Modellen für neue Gewächshaussteuerungstrategien geeignet ist, da sie robust sind und mit der Systemskomplexität gut zurechtkommen. Allerdings muss beachtet werden, dass Probleme und Schwierigkeiten auftreten können. Diese Arbeit weist auf die Relevanz der Netzarchitektur, die erforderlichen großen Datenmengen zur Modellbildung und Probleme mit verschiedenen Zeitkonstanten im Gewächshaus hin. / One facet of the current developments in precision horticulture is the highly technified production under cover. The intensive production in modern greenhouses heavily relies on instrumentation and control techniques to automate many tasks. Among these techniques are control strategies, which can also include some methods developed within the field of Artificial Intelligence. This document presents research on Artificial Neural Networks (ANN), a technique derived from Artificial Intelligence, and aims to shed light on their applicability in greenhouse vegetable production. In particular, this work focuses on the suitability of ANN-based models for greenhouse environmental control. To this end, two models were built: A short-term climate prediction model (air temperature and relative humidity in time scale of minutes), and a model of the plant response to the climate, the latter regarding phytometric measurements of leaf temperature, transpiration rate and photosynthesis rate. A dataset comprising three years of tomato cultivation was used to build and test the models. It was found that this kind of models is very sensitive to the fine-tuning of the metaparameters and that they can produce different results even with the same architecture. Nevertheless, it was shown that ANN are useful to simulate complex biological signals and to estimate future microclimate trends. Furthermore, two connection schemes are proposed to assemble several models in order to generate more complex simulations, like long-term prediction chains and photosynthesis forecasts. It was concluded that ANN could be used in greenhouse automation systems as part of the control strategy, as they are robust and can cope with the complexity of the system. However, a number of problems and difficulties are pointed out, including the importance of the architecture, the need for large datasets to build the models and problems arising from different time constants in the whole greenhouse system.

This research project centers around cinematic and societal representation of the automobile in post-war Swedish cinema and television. Due to political neutrality during World War II, Sweden’s economy benefited from an extensive surplus immediately after Germany’s capitulation in 1945. Economic prosperity was in return transferred onto Swedish society, which enabled an already high degree of motorization of Swedes in mid-1950s, while neighboring European countries struggled rebuilding overall infrastructures, basic food supply lines and often entire cities. Naturally, this would conclude that Swedes presumably had a favorable attitude towards cars from the beginning, ultimately being reflected in some sort of cultural memory. However, Stig Dagerman’s 1948 short story “To Kill a Child” (Att döda ett barn), later on realized as short film in 1953, outlines a rather suspicious and cautious attitude towards automobiles. Cars’ mass-media portrayal in Swedish cinema and television was analyzed with current AI-techniques, therewith observing notable changes in imagery, themes and attitudes surrounding cars over 30 years in history. Filmarkivet.se served as main source with 114 currently available media artifacts from 1950 to 1980, including a wide spectrum of footage i.e., weekly newsreels, private filmmakers’ collections, television commercials, movie trailers, political campaigns and documentary formats. This source material proved diversified in nature as well as redrawing accurately representations of Swedish mass media of its time as it varied between cinema and television, whilst focusing in on daily life of individuals or daily life in Sweden’s cities. While artificial intelligence object recognition helped identifying pertinent sections within a large corpus of film data, subsequently, a qualitative tf-idf-analysis of selected films based on speech-to-text output was conducted, counterbalancing quantitative research approaches.

Visual attention is an important cognitive concept for the daily life of humans, but still not fully understood. Due to this, it is also rarely utilized in computer vision systems. However, understanding visual attention is challenging as it has many and seemingly-different aspects, both at neuronal and behavioral level. Thus, it is very hard to give a uniform explanation of visual attention that can account for all aspects. To tackle this problem, this thesis has the goal to identify a common set of neuronal mechanisms, which underlie both neuronal and behavioral aspects. The mechanisms are simulated by neuro-computational models, thus, resulting in a single modeling approach to explain a wide range of phenomena at once. In the thesis, the chosen aspects are multiple neurophysiological effects, real-world object localization, and a visual masking paradigm (OSM). In each of the considered fields, the work also advances the current state-of-the-art to better understand this aspect of attention itself. The three chosen aspects highlight that the approach can account for crucial neurophysiological, functional, and behavioral properties, thus the mechanisms might constitute the general neuronal substrate of visual attention in the cortex. As outlook, our work provides for computer vision a deeper understanding and a concrete prototype of attention to incorporate this crucial aspect of human perception in future systems.:1. General introduction 2. The state-of-the-art in modeling visual attention 3. Microcircuit model of attention 4. Object localization with a model of visual attention 5. Object substitution masking 6. General conclusion / Visuelle Aufmerksamkeit ist ein wichtiges kognitives Konzept für das tägliche Leben des Menschen. Es ist aber immer noch nicht komplett verstanden, so dass es ein langjähriges Ziel der Neurowissenschaften ist, das Phänomen grundlegend zu durchdringen. Gleichzeitig wird es aufgrund des mangelnden Verständnisses nur selten in maschinellen Sehsystemen in der Informatik eingesetzt. Das Verständnis von visueller Aufmerksamkeit ist jedoch eine komplexe Herausforderung, da Aufmerksamkeit äußerst vielfältige und scheinbar unterschiedliche Aspekte besitzt. Sie verändert multipel sowohl die neuronalen Feuerraten als auch das menschliche Verhalten. Daher ist es sehr schwierig, eine einheitliche Erklärung von visueller Aufmerksamkeit zu finden, welche für alle Aspekte gleichermaßen gilt. Um dieses Problem anzugehen, hat diese Arbeit das Ziel, einen gemeinsamen Satz neuronaler Mechanismen zu identifizieren, welche sowohl den neuronalen als auch den verhaltenstechnischen Aspekten zugrunde liegen. Die Mechanismen werden in neuro-computationalen Modellen simuliert, wodurch ein einzelnes Modellierungsframework entsteht, welches zum ersten Mal viele und verschiedenste Phänomene von visueller Aufmerksamkeit auf einmal erklären kann. Als Aspekte wurden in dieser Dissertation multiple neurophysiologische Effekte, Realwelt Objektlokalisation und ein visuelles Maskierungsparadigma (OSM) gewählt. In jedem dieser betrachteten Felder wird gleichzeitig der State-of-the-Art verbessert, um auch diesen Teilbereich von Aufmerksamkeit selbst besser zu verstehen. Die drei gewählten Gebiete zeigen, dass der Ansatz grundlegende neurophysiologische, funktionale und verhaltensbezogene Eigenschaften von visueller Aufmerksamkeit erklären kann. Da die gefundenen Mechanismen somit ausreichend sind, das Phänomen so umfassend zu erklären, könnten die Mechanismen vielleicht sogar das essentielle neuronale Substrat von visueller Aufmerksamkeit im Cortex darstellen. Für die Informatik stellt die Arbeit damit ein tiefergehendes Verständnis von visueller Aufmerksamkeit dar. Darüber hinaus liefert das Framework mit seinen neuronalen Mechanismen sogar eine Referenzimplementierung um Aufmerksamkeit in zukünftige Systeme integrieren zu können. Aufmerksamkeit könnte laut der vorliegenden Forschung sehr nützlich für diese sein, da es im Gehirn eine Aufgabenspezifische Optimierung des visuellen Systems bereitstellt. Dieser Aspekt menschlicher Wahrnehmung fehlt meist in den aktuellen, starken Computervisionssystemen, so dass eine Integration in aktuelle Systeme deren Leistung sprunghaft erhöhen und eine neue Klasse definieren dürfte.:1. General introduction 2. The state-of-the-art in modeling visual attention 3. Microcircuit model of attention 4. Object localization with a model of visual attention 5. Object substitution masking 6. General conclusion