Yes / Cooperative Systems of Systems (CSoS) including Autonomous systems (AS), such as autonomous cars and related smart traffic infrastructures form a new technological frontier for their enormous economic and societal potentials in various domains. CSoS are often safety-critical systems, therefore, they are expected to have a high level of dependability. Due to the open and adaptive nature of the CSoS, the conventional methods used to provide safety assurance for traditional systems cannot be applied directly to these systems. Potential configurations and scenarios during the evolving operation are infinite and cannot be exhaustively analysed to provide guarantees a priori. This paper presents a novel framework for dynamic safety assurance of CSoS, which integrates design time models and runtime techniques to provide continuous assurance for a CSoS and its systems during operation. / Dependability Engineering Innovation for Cyber Physical Systems (DEIS) H2020 Project under Grant 732242.

Being able to accurately measure distances in depth images is important for accurately reconstructing objects. But the measurement of depth is a noisy process and depth sensors could use additional correction even after factory calibration. We regard the pair of depth sensor and image sensor to be one single unit, returning complete 3D information. The 3D information is combined by relying on the more accurate image sensor for everything except the depth measurement. We present a new linear method of correcting depth distortion, using an empirical model based around the constraint of only modifying depth data, while keeping planes planar. The depth distortion model is implemented and tested on the Intel RealSense SR300 camera. The results show that the model is viable and generally decreases depth measurement errors after calibrating, with an average improvement in the 50 percent range on the tested data sets. / Att noggrant kunna mäta avstånd i djupbilder är viktigt för att kunna göra bra rekonstruktioner av objekt. Men denna mätprocess är brusig och dagens djupsensorer tjänar på ytterligare korrektion efter fabrikskalibrering. Vi betraktar paret av en djupsensor och en bildsensor som en enda enhet som returnerar komplett 3D information. 3D informationen byggs upp från de två sensorerna genom att lita på den mer precisa bildsensorn för allt förutom djupmätningen. Vi presenterar en ny linjär metod för att korrigera djupdistorsion med hjälp av en empirisk modell, baserad kring att enbart förändra djupdatan medan plana ytor behålls plana. Djupdistortionsmodellen implementerades och testades på kameratypen Intel RealSense SR300. Resultaten visar att modellen fungerar och i regel minskar mätfelet i djupled efter kalibrering, med en genomsnittlig förbättring kring 50 procent för de testade dataseten.

Yes / Digital transformation fundamentally changes established practices in public and private sector. Hence, it represents an opportunity to improve the value creation processes (e.g., “industry 4.0”) and to rethink how to address customers’ needs such as “data-driven business models” and “Mobility-as-a-Service”. Dependable, collaborative and autono-mous systems are playing a central role in this transformation process. Furthermore, the emergence of data-driven approaches combined with autonomous systems will lead to new business models and market dynamics. Innovative approaches to re-organise the value creation ecosystem, to enable distributed engineering of dependable systems and to answer urgent questions such as liability will be required. Consequently, digital transformation requires a comprehensive multi-stakeholder approach which properly balances technology, ecosystem and business innovation. Targets of this paper are (a) to introduce digital transformation and the role of / opportunities provided by autonomous systems, (b) to introduce Digital Depednability Identities (DDI) - a technology for dependability engineering of collaborative, autonomous CPS, and (c) to propose an appropriate agile approach for innovation management based on business model innovation and co-entrepreneurship. / Science Foundation Ireland grant 13/RC/2094, by the Horizon 2020 programme within the OpenInnoTrain project (grant agreement 823971) ; H2020 SESAME project (grant agreement 101017258).

Visual search is the perceptual task of locating a target in a visual environment. Due to applications in areas like search and rescue, surveillance, and home assistance, it is of great interest to automate visual search. An autonomous system can potentially search more efficiently than a manually controlled one and has the advantages of reduced risk and cost of labor. In many environments, there is structure that can be utilized to find targets quicker. However, manually designing search algorithms that properly utilize structure to search efficiently is not trivial. Different environments may exhibit vastly different characteristics, and visual cues may be difficult to pick up. A learning system has the advantage of being applicable to any environment where there is a sufficient number of samples to learn from. In this thesis, we investigate how an agent that learns to search can be implemented with deep reinforcement learning. Our approach jointly learns control of visual attention, recognition, and localization from a set of sample search scenarios. A recurrent convolutional neural network takes an image of the visible region and the agent's position as input. Its outputs indicate whether a target is visible and control where the agent looks next. The recurrent step serves as a memory that lets the agent utilize features of the explored environment when searching. We compare two memory architectures: an LSTM, and a spatial memory that remembers structured visual information. Through experimentation in three simulated environments, we find that the spatial memory architecture achieves superior search performance. It also searches more efficiently than a set of baselines that do not utilize the appearance of the environment and achieves similar performance to that of a human searcher. Finally, the spatial memory scales to larger search spaces and is better at generalizing from a limited number of training samples.

This thesis is about appearance-based topological mapping for mobile robots using vision and laser. Our goal is life-long continual operation in outdoor unstruc- tured workspaces. We present a new probabilistic framework for appearance-based mapping and navigation incorporating spatial and visual appearance. Locations are encoded prob- abilistically as random graphs possessing latent distributions over visual features and pair-wise euclidean distances generating observations modeled as 3D constellations of features observed via noisy range and visual detectors. Multi-modal distributions over inter-feature distances are learnt using non-parametric kernel density estima- tion. Inference is accelerated by executing a Delaunay tessellation of the observed graph with minimal loss in performance, scaling log-linearly with scene complexity. Next, we demonstrate how a robot can, through introspection and then targeted data retrieval, improve its own place recognition performance. We introduce the idea of a dynamic sampling set, the onboard workspace representation, that adapts with increasing visual experience of continually operating robot. Based on a topic based probabilistic model of images, we use a measure of perplexity to evaluate how well a working set of background images explains the robot’s online view of the world. O/ine, the robot then searches an external resource to seek additional background images that bolster its ability to localize in its environment when used next. Finally, we present an online and incremental approach allowing an exploring robot to generate apt and compact summaries of its life experience using canon- ical images that capture the essence of the robot’s visual experience-illustrating both what was ordinary and what was extraordinary. Leveraging probabilistic topic models and an incremental graph clustering technique we present an algorithm that scales well with time and variation of experience, generating a summary that evolves incrementally with the novelty of data.

An increased focus on the development of autonomous safety-critical systems requiresmore attention at ensuring safety of humans and the environment. The mainobjective of this thesis is to explore the state of the art and to identify the safetyrelatedchallenges being addressed for using autonomy in safety-critical systems. Inparticular, the thesis explores the nature of these challenges, the different autonomylevels they address and the type of safety measures as proposed solutions. Above all,we focus on the safety measures by a degree of adaptiveness, time of being activeand their ability of decision making. Collection of this information is performedby conducting a Systematic Literature Review of publications from the past 9 years.The results showed an increase in publications addressing challenges related to theuse of autonomy in safety-critical systems. We managed to identify four high-levelclasses of safety challenges. The results also indicate that the focus of research wason finding solutions for challenges related to full autonomous systems as well assolutions that are independent of the level of autonomy. Furthermore, consideringthe amount of publications, results show that non-learning solutions addressing theidentified safety challenges prevail over learning ones, active over passive solutionsand decisive over supportive solutions.

In this thesis we present a detect-tracking algorithm (see figure 3.1) that combines the detection robustness of static region proposal based object detectors, like the faster region convolutional neural network (R-CNN) and the region-based fully convolutional networks (R-FCN) model, with the tracking prediction strength of extended Kalman filters, by using, what we have called, a translating and non-rigid user input region of interest (RoI-) mapping. This so-called RoI-mapping maps a region, which includes the object that one is interested in tracking, to a featureless three-channeled image. The detection part of our proposed algorithm is then performed on the image that includes only the RoI features (see figure 3.2). After the detection step, our model re-maps the RoI features to the original frame, and translates the RoI to the center of the prediction. If no prediction occurs, our proposed model integrates a temporal dependence through a Kalman filter as a predictor; this filter is continuously corrected when detections do occur. To train the region proposal based object detectors that we integrate into our detect-tracking model, we used TensorFlow®’s object detection api, with a random search hyperparameter tuning, where we fine-tuned, all models from TensorFlow® slim base network classification checkpoints. The trained region proposal based object detectors used the inception V2 base network for the faster R-CNN model and the R-FCN model, while the inception V3 base network only was applied to the faster R-CNN model. This was made to compare the two base networks and their corresponding affects on the detection models. In addition to the deep learning part of this thesis, for the implementation part of our detect-tracking model, like for the extended Kalman filter, we used Python and OpenCV® . The results show that, with a stationary camera reference frame, our proposed detect-tracking algorithm, combined with region proposal based object detectors on images of size 414 × 740 × 3, can detect and track a small object in real-time, like a tennis ball, moving along a horizontal trajectory with an average velocity v ≈ 50 km/h at a distance d = 25 m, with a combined detect-tracking frequency of about 13 to 14 Hz. The largest measured state error between the actual state and the predicted state from the Kalman filter, at the aforementioned horizontal velocity, have been measured to be a maximum of 10-15 pixels, see table 5.1, but in certain frames where many detections occur this error has been shown to be much smaller (3-5 pixels). Additionally, our combined detect-tracking model has also been shown to be able to handle obstacles and two learnable features that overlap, thanks to the integrated extended Kalman filter. Lastly, our detect-tracking model also was applied on a set of infra-red images, where the goal was to detect and track a moving truck moving along a semi-horizontal path. Our results show that a faster R-CNN inception V2 model was able to extract features from a sequence of infra-red frames, and that our proposed RoI-mapping method worked relatively well at detecting only one truck in a short test-sequence (see figure 5.22).

Este trabalho trata da aplicação de técnicas de identificação de sistemas dinâmicos a ensaios com veículos submarinos não tripulados ou com modelos em escala auto-propelidos de veículos submarinos. Complementa-se, desta forma as investigações que vêm sendo realizadas no Laboratório de Veículos Não Tripulados, LVNT, voltadas à estimativa de parâmetros hidrodinâmicos de veículos autônomos submarinos, AUVs. Estas têm utilizado os métodos pertencentes a outras classes de abordagens para a estimativa de modelos de manobras para veículos submarinos como os métodos CFD e ASE (de BARROS, et. al., 2004, 2006, 2008a, 2008b; de BARROS e DANTAS, 2012). Outras atribuições deste trabalho dizem respeito à compreensão e desenvolvimento na modelagem linear da dinâmica de manobra de veículos submarinos, teoria e implementação de métodos de identificação de sistemas aplicados a resultados de ensaios com modelos auto-propelidos. As atividades de estudo foram divididas de acordo com os temas relativos à dinâmica de veículos submarinos, conceitos físicos envolvidos nas derivadas hidrodinâmicas de estabilidade, técnicas de identificação de sistemas e aspectos tecnológicos e experimentais da utilização de ensaios com modelos auto-propelidos. As atividades voltadas ao atendimento de tais metas envolveram, durante o programa de pesquisa, estudos de modelos analíticos, simulação numérica do movimento, realização de experimentos em piscina e campo com um AUV, e a implementação de ferramentas numéricas de análise de dados e estimação de parâmetros de manobra. / This paper is related to the application of techniques for identifying dynamic systems testing scale models of underwater vehicles or even unmanned underwater vehicles in real scale. Complementing in this way the investigations that have been conducted in the Laboratory of Unmanned Vehicles, LVNT, aimed to estimate the hydrodynamic parameters of autonomous underwater vehicles, AUVs. They have used the methods belonging to the three other classes mentioned (of Barros, et. Al., 2004, 2006, 2008a, 2008b; Barros and the DANTAS, 2012). Other tasks of this work relates to the understanding and development in modeling linear dynamic manoeuvring underwater vehicles, theory and implementation of identification methods applied to systems test results with self-propelled models. The study activities were divided according to themes related to the dynamics of underwater vehicles, physical concepts derived in the hydrodynamic stability, system identification techniques and technological aspects and experimental trials with use of self-propelled models. The activities aimed at meeting those goals involved during the research program, studies of analytical models, numerical simulation of the movement, performing experiments with a swimming pool and AUV, and implementation of numerical tools for data analysis and parameter estimation maneuver.

I examensarbetet jämförs undvikande av kollision och tidsefektivitet mellan det två metoderna hastighetshinder och partikelseparation i spelgenren Twin stick shooter. Arbetet försöker besvara frågan: Hur skiljer sig undvikandet av kollision och tidseffektiviteten mellan metoderna hastighetshinder och partikelseparation, i spelgenren twin stick shooter med flockbeteende? För att besvara frågan har en artefakt skapats. I artefakten jagar agenter en spelare medan agenterna undviker kollision med andra agenter, dock eftersträvar agenterna att kollidera med spelaren. I artefakten körs olika experiment baserat på parametrar som har ställts in. Varje experiment körs en bestämd tid och all data om kollisioner och exekveringstid för respektive metod sparas i en textfil.   Resultatet av experimenten pekar på att partikelseparation lämpar sig bättre för twin stick shooters.  Hastighetshinder kolliderar mindre men tidsberäkningen är för hög och skalar dåligt med antal agenter. Det passar inte twinstick shooter då det oftast är många agenter på skärmen.  Metoderna för undvikandet av kollision har användning till radiostyrda billar och robotar, samt simulation av folkmassa.

Este trabalho trata da aplicação de técnicas de identificação de sistemas dinâmicos a ensaios com veículos submarinos não tripulados ou com modelos em escala auto-propelidos de veículos submarinos. Complementa-se, desta forma as investigações que vêm sendo realizadas no Laboratório de Veículos Não Tripulados, LVNT, voltadas à estimativa de parâmetros hidrodinâmicos de veículos autônomos submarinos, AUVs. Estas têm utilizado os métodos pertencentes a outras classes de abordagens para a estimativa de modelos de manobras para veículos submarinos como os métodos CFD e ASE (de BARROS, et. al., 2004, 2006, 2008a, 2008b; de BARROS e DANTAS, 2012). Outras atribuições deste trabalho dizem respeito à compreensão e desenvolvimento na modelagem linear da dinâmica de manobra de veículos submarinos, teoria e implementação de métodos de identificação de sistemas aplicados a resultados de ensaios com modelos auto-propelidos. As atividades de estudo foram divididas de acordo com os temas relativos à dinâmica de veículos submarinos, conceitos físicos envolvidos nas derivadas hidrodinâmicas de estabilidade, técnicas de identificação de sistemas e aspectos tecnológicos e experimentais da utilização de ensaios com modelos auto-propelidos. As atividades voltadas ao atendimento de tais metas envolveram, durante o programa de pesquisa, estudos de modelos analíticos, simulação numérica do movimento, realização de experimentos em piscina e campo com um AUV, e a implementação de ferramentas numéricas de análise de dados e estimação de parâmetros de manobra. / This paper is related to the application of techniques for identifying dynamic systems testing scale models of underwater vehicles or even unmanned underwater vehicles in real scale. Complementing in this way the investigations that have been conducted in the Laboratory of Unmanned Vehicles, LVNT, aimed to estimate the hydrodynamic parameters of autonomous underwater vehicles, AUVs. They have used the methods belonging to the three other classes mentioned (of Barros, et. Al., 2004, 2006, 2008a, 2008b; Barros and the DANTAS, 2012). Other tasks of this work relates to the understanding and development in modeling linear dynamic manoeuvring underwater vehicles, theory and implementation of identification methods applied to systems test results with self-propelled models. The study activities were divided according to themes related to the dynamics of underwater vehicles, physical concepts derived in the hydrodynamic stability, system identification techniques and technological aspects and experimental trials with use of self-propelled models. The activities aimed at meeting those goals involved during the research program, studies of analytical models, numerical simulation of the movement, performing experiments with a swimming pool and AUV, and implementation of numerical tools for data analysis and parameter estimation maneuver.