Many industries stand in front of a significant shift as we have entered the 4th industrial revolution,and society is becoming digitalised to a higher degree. Autonomous and smart ships may be emergingin the coming future within the maritime industry. Previous research has tried understanding thecompetencies needed to work with the autonomous ship. This case study aims to understand a shoreand ship organisation as their company stands on the verge of smart ships arriving. To understandthis, the a) present work has been explored, b) potential changes to the work tasks because of theautomation and c) how the organisation and crew members can meet the changes have been explored.The methods used are interviews, observations, thematic analysis, and hierarchical task analysis. Thestudy’s major findings were the importance of clear communication and a good relationship betweenthe ship and shore organisation. / Drift och operation av smarta fartyg

<p dir="ltr">A Human-Machine Interaction (HMI) refers to a mechanism to support the direct interactions of humans and machines with the objective for the synthesis of machine intelligence and autonomy. The demand to advance in this field of study for intelligence controls is continuously growing. Brain-Computer Interface (BCI) is one type of HMIs that utilizes a human brain to enable direct communication of the human subject with a machine. This technology is widely explored in different fields to control external devices using brain signals.</p><p dir="ltr">This thesis is driven by two key observations. The first one is the limited number of Degrees of Freedom (DoF) that existing BCI controls can control in an external device; it becomes necessary to assess the controllability when choosing a control instrument. The second one is the differences of decision spaces of human and machine when both of them try to control an external device. To fill the gaps in these two aspects, there is a need to design an additional functional module that is able to translate the commands issued by human into high-frequency control commands that can be understood by machines. These two aspects has not been investigated thoroughly in literatures.</p><p dir="ltr">This study focuses on training, detecting, and using humans’ intents to control intelligent machines. It uses brain signals which will be trained and detected in form of Electroencephalography (EEG), brain signals will be used to extract and classify human intents. A selected instrument, Emotiv Epoc X, is used for pattern training and recognition based on its controllability and features among other instruments. A functional module is then developed to bridge the gap of frequency differences between human intents and motion commands of machine. A selected robot, TinkerKit Braccio, is then used to illustrate the feasibility of the developed module through fully controlling the robotic arm using human’s intents solely.</p><p dir="ltr">Multiple experiments were done on the prototyped system to prove the feasibility of the proposed model. The accuracy to send each command, and hence the accuracy of the system to extract each intent, exceeded 75%. Then, the feasibility of the proposed model was also tested through controlling the robot to follow pre-defined paths, which was obtained through designing a Graphical-User Interface (GUI). The accuracy of each experiment exceeded 90%, which validated the feasibility of the proposed control model.</p>

Purpose: The purpose of this study is to explore the expectations of different stakeholders regarding human-machine interaction. After finding the expected benefits and drawbacks to human-machine interaction, is it important to seek the causes that may lead to misalignment concerning human-machine interaction. This to find if there are any misalignment between stakeholders, and causes to why they are misaligned, to develop strategies to prevent these misalignments. To achieve the purpose of the study, these two research questions have been chosen: 1. What are the expected benefits and drawbacks to human-machine interaction from the perspectives of different stakeholders? 2. What are the causes of the stakeholder perspective misalignment concerning human-machine interaction? Method: The study was conducted at a case company at their newly opened warehouse south of Jönköping, the company is a well-established logistics company in Europe. The researchers had good communication with the supervisor at the case company and after discussion, it was deemed that this subject was interesting and useful to study. A theoretical framework was built to back up the study and to gain more knowledge about the subject. To fulfill the purpose and research questions, a qualitative data was collected through interviews. To answer the research questions, the theoretical framework and the collected data have been analyzed and discussed to draw conclusions. Findings: The study shows that different stakeholders have different expectations regarding human-machine interaction. The different expectations depend on what each stakeholder prioritize and other aspects such as, earlier experience. Another finding of the study is that a specific aspect cannot be named a benefit or a drawback, because that all aspects can both be a benefit and a drawback from different stakeholders’ perspectives. The study also shows that different stakeholders’ can be misaligned and that it depends on different aspects such as earlier experience, level of responsibility and different human behaviors. Implications: The study contributes to the existing literature by highlighting some of the expectations associated with human-machine interaction. The study also explored new subjects which have not yet been extensively explored in literature, such as financial and continuous improvements aspects. Limitations: The study is limited to one case company and focuses on what expectations different stakeholders can have before operating with a new machine. / Syfte: Syftet med denna studie är att utforska förväntningar hos olika intressenter kring ämnet människa-maskin interaktion. Efter att ha hittat de förväntade fördelarna och nackdelarna till människa-maskin interaktion, är det viktigt att söka efter orsaker som kan leda till oenighet angående människa-maskin interaktion. Detta för att undersöka om det finns någon oenighet mellan intressenterna och om det finns orsaker till att dem är oeniga, för att utveckla strategier för att förhindra dessa oenigheter. För att uppnå syftet med studien har dessa två frågeställningar valts: 1. Vilka är de förväntade fördelarna och nackdelarna med interaktionen mellan människa och maskin ur olika intressenters perspektiv? 2. Vilka är orsakerna till oenighet mellan intressenters perspektiv angående interaktionen mellan människa och maskin? Metod: Studien genomfördes på ett fall företag på deras nyöppnade lager i södra Jönköping, företaget är ett väl etablerat logistikföretag i Europa. Skribenterna har haft god kommunikation med handledaren på fall företaget och efter diskussioner ansågs det att detta ämne var intressant och användbart att studera. Ett teoretiskt ramverk har skrivits för att backa upp studien och för att få mer kunskap kring ämnet. För att uppnå studiens syfte och frågeställningar, samlas kvalitativa data in från intervjuer. För att svara på frågeställningarna analyseras det teoretiska ramverket och den insamlade data analyserats och diskuterats för att kunna dra slutsatser. Resultat: Studien visar att olika intressenter har olika förväntningar angående interaktionen mellan människa och maskin. De olika förväntningarna beror på vad varje intressent prioriterar och andra aspekter som, tidigare erfarenheter. Ett annat resultat från studien är att en specifik aspekt inte kan nämnas som en fördel eller nackdel på grund av att alla aspekter kan ses som både en fördel och en nackdel från olika intressenters perspektiv. Studien visar också att olika intressenter kan vara oeniga och att det kan bero på aspekter som tidigare erfarenheter, ansvarsnivå eller olika mänskliga beteenden. Implikationer: Studiens implikationer bidrar till den befintliga litteraturen genom att lyfta fram några av de förväntningar som är kopplade till interaktionen mellan människa och maskin. Studien utforskar också nya ämnen som ännu inte har utforskats i litteraturen, såsom ekonomiska aspekter och ständiga förbättringar. Begränsningar: Studiens begränsningar är att det är ett fall företag och fokuserar på vilka förväntningar olika intressenter kan ha innan de använder en ny maskin.

No description available.

As the forest industry experiences significant growth, the demand for enhanced operational efficiency becomes vital. Taigatech respond to this need by leveraging machine learning-powered smart cameras to optimize sawmill operations. Despite technological advancements, manual production monitoring remains a burden for operators, highlighting the need for a shift towards user-friendly solutions in production monitoring. This master thesis project aims to develop a conceptual prototype for improved process monitoring, aligning with Taigatech's expertise in machine-learning. Following the triple diamond approach, the project was divided into three phases. The learning phase involved a preliminary study to understand the operators work of the sawmill industry’s control room. This phase also included thorough need finding to comprehend the current state and establishing needs and requirements. The ideation phase involved internal ideation within the group and a workshop with stakeholders, exploring various approaches towards a solution while considering the needs and requirements established in previous phase. The prototype phase involved wireframe prototyping in Figma, building two interfaces tested in eight user tests to establish the interpretation of information for a sawmill operator. The prototype phase concluded with the evaluation of user tests and resulted in a final design called OperAid. OperAid integrates smart cameras to provide real-time alerts to operators, facilitating timely intervention and reducing cognitive strain. This approach enhances productivity and fosters a more efficient and user-friendly monitoring environment in sawmills control room. / I samband med att skogsindustrin genomgår en betydande tillväxt blir efterfrågan på förbättrad operationell effektivitet avgörande. Taigatech svar på detta behov är genom användningen av maskininlärda smarta kameror för att optimera sågverksproduktionen. Trots tekniska framsteg är den manuella produktionsövervakningen fortfarande en påfrestning för operatörer, vilket understryker behovet av en förändring till användarvänliga lösningar inom produktionsövervakningen. Detta examensarbete syftar till att utveckla en konceptuell prototyp för förbättrad processövervakning, i linje med Taigatechs expertis inom maskininlärning. I enlighet med den så kallade trippeldiamantmodellen delades projektet upp i tre faser. Lärandefasen innefattade en förstudie för att förstå operatörernas arbete i sågverksindustrins kontrollrum. Denna fas inkluderade också en genomgående behovsanalys för att förstå den aktuella situationen och etablera aktuella behov och krav. Idéfasen bestod av en intern idégenerering inom gruppen samt en workshop med intressenter, där olika tillvägagångssätt utforskades med hänsyn till de behov och krav som fastställts i den föregående fasen. Prototypfasen innefattade wireframe-prototyper i Figma, där två gränssnitt testades i åtta användartester för att fastställa tolkningen av information för en sågverksoperatör. Prototypfasen avslutades med utvärdering av användartester och resulterade i en slutgiltig design - OperAid. OperAid integrerar smarta kameror för att ge operatörer realtidsvarningar, vilket underlättar snabb intervention och minskar kognitiv belastning. Denna lösning förbättrar produktiviteten och främjar en mer effektiv och användarvänlig övervakningsmiljö i kontrollrummen på sågverk.

Im Projekt ArbeitsTeilung Entwickler Operateur (ATEO) wird die Funktionsteilung zwischen Mensch und Maschine erforscht, wobei der Entwickler von Automatiken stärker in den Vordergrund gerückt wird. Im Vergleich mit Operateuren wird seine Leistung bei der Steuerung komplexer dynamischer Prozesse durch die entwickelten Automatiken gemessen. Dabei entscheidet die Antizipationsleistung der Entwickler weit im Voraus über den Erfolg oder Misserfolg der Automatiken. Ein Operateur hat dagegen den Vorteil sehr schnell auf unerwartete Ereignisse zu reagieren, wenn er diese erkennt und die nötige Expertise besitzt, korrekt zu handeln. Für den Vergleich zwischen beiden Gruppen werden gemeinsame Ressourcen wie Zeit und Informationsquellen herangezogen, um so für beide optimale Bedingungen zu schaffen. Im Rahmen dieser Dissertation wurden zwei Studien durchgeführt. Für die erste Studie wurde studentischen Entwicklerteams im Rahmen von Lehrveranstaltungen an der Humboldt-Universität zu Berlin mehr Zeit gegeben als die für einen Vergleich herangezogene Studie von Saskia Kain mit professionellen Entwicklerteams aus Industrie und Forschung. Der Vergleich dieser beiden Gruppen von Entwicklerteams ergab keine signifikanten Unterschiede in der Qualität der entwickelten Automatikkonzepte. Für die zweite Studie wurde ein sehr gutes Automatikkonzept ausgewählt und seine Leistung im Labor getestet. Im Vergleich zur Leistung von Operateuren aus angesprochenen empirischen Studien des ATEO Projektes konnte durch die Automatiken nur die Genauigkeit verbessert werden. Der Unterschied weiterer Leistungsmerkmale wie Geschwindigkeit und Anstrengung der Versuchspersonen während der Durchführung war nicht signifikant. Im Übergang zwischen der eigenen Trackingleistung der Versuchspersonen und einer Leistung mit Unterstützung durch die Automatik zeigte sich eine signifikante Verschlechterung fast aller Leistungsmaße. / The project ‚ArbeitsTeilung Entwickler Operateur‘ (ATEO) (Division of Labour between Developers and Operators) investigated the function allocation between man and machines for designers of automation and operators. Compared with operators, the designer‘s achievements will be measured by the performance of the designed automation controlling complex and dynamic processes. In doing so, efficient anticipation of future events separates the good automation from the bad. The operator, on the other hand, has the advantage of quick reactions to unexpected events, if s/he recognizes them and is trained to act appropriately. Resources like time and amount of information, which are common to these two groups, were used for comparison under equal and optimal conditions. This thesis reports on two studies. In the first study, students of the Humboldt-University in Berlin designed concepts for automation during the course of the semester, while professional design teams from different companies and research facilities had only two hours for the conception phase in a comparable study conducted by Saskia Kain. When comparing these two groups, student and professional design teams, the quality and quantity of these concepts of automation did not show significant differences. For the second study, one of the best rated concepts of automation was tested with subjects, regarding its performance in optimizing the speed, accuracy and workload of test subjects, using SAM and compared with operators. Results showed a significant difference in increased accuracy during the tracking task by the designed automation. The effects of automation were insignificant for the performance indicators speed and workload. The transition from cooperative tracking with and without assistance of automation during the same experiment showed a significant decrease in almost all performance dimensions, when the automation should have supported the subjects.

The project has explored the topic Smart factory with main focus on the future production staff. The project aims to investigate how the production staff is affected by Volvo Cars Skövde Engine Plant (SkEP) becoming a Smart factory, in the era of Industry 4.0. The definition of the Smart factory is a demand of Mobile- and wireless technologies, Human-oriented, pursue a Flexible production with Sustainable manufacturing, as well as utilization of CPS (Cyber-Physical Systems), IoT (Internet-of-Things) and Cloud storage. The current situation and the future five to twenty years were examined in order to define the future production staff. This by conducting an observational study and several interviews. The studies’ results were that SkEP cannot be regarded as smart since several demands are inadequate by definition. Five years are considered too short of a time for the plant to fulfill the demands. However, according to the interviews and literature, SkEP are expected to become smart in twenty years after time refinement of existing technologies and implementation of new ones. The authors estimate Leadership, Information, IT and Production lay-out to be the areas that require the most effort. The future production staff are expected to be flexible with workplace, working hours and able to manage multiple variants. They should be included in self-supporting teams where every individual possesses an expertise, are motivated and participating. Production staff should perform complex, varied jobs with more responsibility by endorsement of decision support systems. The staffs’ competence should consist of technical education, high basic and lay-out knowledge and the ability to contribute to the collection of information and analyses. Interaction with technology is expected to expand and the personnel must therefore have a well-established comprehension of technology. The concept Smart factory is extensive and relatively new, which means that it is constantly evolving. Thus it is important for SkEP to be updated and adjust to the impact from the outside world.

Cette thèse s’inscrit dans le domaine de l’intelligence ambiante et de l’interaction homme-machine. Elle a pour thème la génération d’interfaces homme-machine adaptées au contexte d’interaction dans les environnements ambiants. Les travaux de recherche présentés traitent des problèmes rencontrés lors de la conception d’IHM dans l'ambiant et notamment de la réutilisation de techniques d’interaction multimodales et multi-périphériques. Ce travail se divise en trois phases. La première est une étude des problématiques de l’IHM spécifiques à l’Ambiant et des architectures logicielles adaptées à ce cadre théorique. Cette étude permet d’établir les limites des approches actuelles et de proposer, dans la seconde phase, une nouvelle approche pour la conception d’IHM ambiante appelée DAME. Cette approche repose sur l’association automatique de composants logiciels qui construisent dynamiquement une IHM. Nous proposons deux modèles complémentaires qui permettent de décrire les caractéristiques ergonomiques et architecturales des composants. La conception de ces derniers est guidée par une architecture logicielle composée de plusieurs couches qui permet d’identifier les différents niveaux d’abstraction réutilisables d’un langage d’interaction. Un troisième modèle, appelé modèle comportemental, permet de spécifier des recommandations quant à l’instanciation de ces composants. Nous proposons un algorithme permettant de générer des IHM adaptées au contexte et d’évaluer la qualité de celles-ci par rapport aux recommandations du modèle comportemental. Dans la troisième phase, nous avons implémenté une plateforme réalisant la vision soutenue par DAME. Cette implémentation est confrontée aux utilisateurs finaux dans une expérience de validation qualitative. De ces travaux ressortent des résultats encourageants, ouvrant la discussion sur de nouvelles perspectives de recherche dans le cadre de l’IHM en informatique ambiante. / This thesis deals with ambient intelligence and the design of Human-Computer Interaction (HCI). It studies the automatic generation of user interfaces that are adapted to the interaction context in ambient environments. This problem raises design issues that are specific to ambient HCI, particularly in the reuse of multimodal and multidevice interaction techniques. The present work falls into three parts. The first part is an analysis of state-of-the-art software architectures designed to solve those issues. This analysis outlines the limits of current approaches and enables us to propose, in the second part, a new approach for the design of ambient HCI called DAME. This approach relies on the automatic and dynamic association of software components that build a user interface. We propose and define two complementary models that allow the description of ergonomic and architectural properties of the software components. The design of such components is organized in a layered architecture that identifies reusable levels of abstraction of an interaction language. A third model, called behavioural model, allows the specification of recommendations about the runtime instantiation of components. We propose an algorithm that allows the generation of context-adapted user interfaces and the evaluation of their quality according to the recommendations issued from the behavioural model. In the third part, we detail our implementation of a platform that implements the DAME approach. This implementation is used in a qualitative experiment that involves end-users. Encouraging preliminary results have been obtained and open new perspectives on multi-devices and multimodal HCI in ambient computing.

Automation and digitalization are developing at a high pace and it is important to keep the focus on human-machine interaction. It is becoming more and more important that the usability in machines and lines is related to the development so that the performance and availability of the production processes in the industry are not adversely affected. It is a case of designing the equipment so that users can continue to handle them intuitively and with simplicity the more complex they become. AP&amp;T has in the last 50 years delivered world-leading production solutions for efficient sheet metal forming in the form of presses, automation solutions and press tools. Areas of focus are the automotive and climate and energy industries where they deliver solutions for products such as whitegoods, computer cases, heat exchanger plates and press hardened car parts. AP&amp;T’s goal is to help the customer achieve the highest productivity possible and a long-term and sustainable profitability with a focus on weight reduction, safety and energy efficiency. The project aimed to facilitate for the operator, setter and maintenance technician when handling AP&amp;T machines and lines. Running, installing, starting, and changing tools, products or materials in a machine and/or production line should be performed with simplicity. The objective of the project was to identify usability issues by analyzing the current situation from an operator, setter and maintenance technician point of view to develop a more intuitive handling of AP&amp;T’s presses, automation and production lines. A usability development project requires frequent feedback and therefore the iterative design process was chosen. Theories regarding usability, usability inspection methods, visual communication, user interfaces and human limitations were collected and used as a focal point in analyses, and when identifying usability issues and structuring the list of priority. Methods such as observations, interviews and documentation collection were used to form a Hierarchical Task Analysis (HTA) for operators, setters and maintenance technicians linked to the management of the machines ODEN-FT Press, Servo Hydraulic Press, SpeedFeeder, Multi-Layer Furnace and for the press hardening line. Mapping of handling the press tool and automation grippers was also carried out, as well as a study of today's software program used as interface. The devices analyzed were operator panels, mobile panels and terminal screens along with the documentation that accompanies the purchased machine. The results of the analyses gave a list of seventeen points in need of improvements according to the users. These were areas such as screens in the user interface of the terminals, icons on the panels, and management of the tools during tools and material changes. These were first structured according to the users and then developed into a priority list structured after implementation time with the fastest improvements with the greatest effect first. At the top of this list, the user interface, operator panels and the education of operators, setters, and maintenance technicians ended up. The recommendation, which is the conclusion of this Master thesis, is to start at the top in the list of priorities when developing the identified problems. Further investigation of the issues is necessary due to the time limitation which excluded companies based in America and Asia from the evaluation. The most important recommendation for further development is to continue to utilize the users. Usability inspections are carried out, but it is important that users are allowed to continue to participate during tests and further development of solutions. It is not possible to achieve flawless usability, however, it is always possible to further develop the handling and experience of a product. It is also suggested to simultaneously connect usability with the digital development that Industry 4.0 and Internet of Things implies to be able to identify and eliminate problems as they appear. / Automatisering och digitalisering utvecklas i hög hastighet och det är nu som det är viktigt att behålla fokuset på människa-maskin-interaktionen. Det blir allt viktigare att användarvänligheten i maskiner och produktionslösningar hänger med i utvecklingen så prestandan och tillgängligheten för produktionsprocesser i industrin inte påverkas negativt. Det gäller att forma utrustningen så att användarna kan fortsätta hantera dem intuitivt och med enkelhet ju mer komplexa de blir. AP&amp;T har de senaste 50 åren levererat världsledande produktionslösningar för effektiv plåtformning i form av pressar, automationslösningar och pressverktyg. Fokusområden är bil- och klimat och energiindustrin där de levererar lösningar för produkter så som vitvaror, datorskal, värmeväxlarplattor och presshärdade bildelar. AP&amp;Ts mål är att hjälpa kunden att uppnå högsta möjliga produktivitet och en långsiktig och hållbar lönsamhet med fokus på viktreduktion, säkerhet och energieffektivitet. Vid varje tillverkad lösning och produkt står användaren i centrum. Projektet syftade till att underlätta för användaren vid hantering av AP&amp;Ts maskiner och produktionslösningar. Att köra, installera, starta, byta verktyg, produkter eller material i en maskin och/eller produktionslinje ska kunna utföras med enkelhet. Målet i projektet var att identifiera användarproblem genom att analysera nuvarande situation för operatörer, installatörer och servicepersonal för att kunna utveckla en mer intuitiv hantering av AP&amp;Ts pressar, automation och produktionslinjer. Vid ett utvecklingsarbete krävs det återkommande återkoppling och därför valdes den iterativa designprocessen. Teorier om användarvänlighet, inspektionsmetoder, visuell kommunikation, användargränssnitt och människans begränsningar insamlades och användes som tyngdpunkt i analyser och vid identifiering av användarproblem samt strukturering av prioriteringslistan. Metoder så som observationer, intervjuer och dokumentationsinsamling användes för att kunna utgöra en hierarkisk uppgifts analys (HTA) för operatörer, installatörer och servicepersonal kopplat till hanteringen av maskinerna ODEN-FT press, Servo Hydraulic Press, SpeedFeeder, Multi-Layer Furnace och för presshärdningslinjen. Även en kartläggning av hanteringen av ett presshärdningsverktyg och automationsverktyg utfördes samt en djupare undersökning om dagens mjukvaruprogram som används i datasystemen utfördes. De fysiska apparaterna som analyserades var operatörspaneler, mobilpaneler och dataterminalskärmar som användaren brukar och dokumentationen som tillhör vardera maskin. Resultatet av analyserna gav en lista på 17 punkter som enligt användaren behöver utvecklas. Det var områden så som sidor i användargränssnittet i terminalerna, ikoner till panelerna och hanteringen av verktygen vid omställning och materialbyten. Dessa strukturerades först efter hur pass omtalade de var bland användarna och sedan utvecklades listan till en prioritetslista strukturerad efter implementeringstiden med de snabbaste förbättringarna med störst effekt överst. Högst upp på denna listan hamnade användargränssnittet, operatörspanelerna och utbildning av operatörer, installatörer och servicepersonal. Rekommendationen som är slutsatsen i denna examensrapport är att utgå ifrån prioriteringslistan vid utveckling av de identifierade problemen. Att göra vidare undersökningar gällande problemområdena är behövligt på grund av tidsbegränsningen som gjorde att företag baserade i Amerika och Asien ej kunde tas med i analyserna. Den viktigaste rekommendationen för vidare utveckling är att fortsätta använda brukarna. Användarvänlighetsinspektioner är utförda, men det är viktigt att användarna får fortsätta deltaga under tester och vidare arbeten med lösningarna. Det går inte att uppnå felfri användarvänlighet, utan det går alltid att vidareutveckla hantering och upplevelse av produkter. Att koppla samman användaren med den digitala utvecklingen som bland annat Industry 4.0 och Internet of Things medför är en viktig del inför framtiden så man enkelt kan identifiera och eliminera användarproblem direkt då de uppstår.

La réalité augmentée (Augmented Reality ou AR) peut potentiellement changer significativement l’expérience utilisateur. Au contraire les applications sur Smartphone ou tablette, les technologies d’affichage tête haute (Head Up Display ouHUD) aujourd’hui sont capables de projeter localement sur une zone du pare-brise ou globalement sur tout le pare-brise. Le conducteur peut alors percevoir l’information directement dans son champ de vision. Ce ne sont pas que les informations basiques comme vitesse ou navigation, le système peut aussi afficher des aides, des indicateurs qui guident l’attention du conducteur vers les dangers possibles. Il existe alors un chalenge scientifique qui est de concevoir des visualisations d’interactions qui s’adaptent en fonction de l’observation de la scène mais aussi en fonction de l’observation du conducteur. Dans le contexte des systèmes d’alerte de collision avec les piétons (Pedestrian Collision Warning System ou PCWS), l’efficacité de la détection du piéton a atteint un niveau élevé grâce à la technologie de vision. Pourtant, les systèmes d’alerte ne s’adaptent pas au conducteur et à la situation, ils deviennent alors une source de distraction et sont souvent négligés par le conducteur. Pour ces raisons, ce travail de thèse consiste à proposer un nouveau concept de PCWS avec l’AR (nommé the AR-PCW system). Premièrement, nous nous concentrons sur l’étude de la conscience de la situation (Situation Awareness ou SA) du conducteur lorsqu’il y a un piéton présent devant le véhicule. Nous proposons une approche expérimentale pour collecter les données qui représentent l’attention du conducteur vis-à-vis du piéton (Driver Awareness of Pedestrian ou DAP) et l’inattention du conducteur vis-à-vis de celui-ci (Driver Unawareness of Pedestrian ou DUP). Ensuite, les algorithmes basées sur les charactéristiques, les modèles d’apprentissage basés sur les modèles discriminants (ex, Support Vector Machine ou SVM) ou génératifs (Hidden Markov Model ou HMM) sont proposés pour estimer le DUP et le DAP. La décision de notre AR-PCW system est effectivement basée sur ce modèle. Deuxièmement, nous proposons les aides ARs pour améliorer le DAP après une étude de l’état de l’art sur les ARs dans le contexte de la conduite automobile. La boite englobante autour du piéton et le panneau d’alerte de danger sont utilisés. Finalement, nous étudions expérimentalement notre système AR-PCW en analysant les effets des aides AR sur le conducteur. Un simulateur de conduite est utilisé et la simulation d’une zone HUD dans la scène virtuelle sont proposés. Vingt-cinq conducteurs de 2 ans de permis de conduite ont participé à l’expérimentation. Les situations ambigües sont créées dans le scénario de conduite afin d’analyser le DAP. Le conducteur doit suivre un véhicule et les piétons apparaissent à différents moments. L’effet des aides AR sur le conducteur est analysé à travers ses performances à réaliser la tâche de poursuite et ses réactions qui engendrent le DAP. Les résultats objectifs et subjectifs montrent que les aides AR sont capables d’améliorer le DAP défini en trois niveaux : perception, vigilance et anticipation. Ce travail de thèse a été financé sur une bourse ministère et a été réalisé dans le cadre des projets FUI18 SERA et Labex MS2T qui sont financé par le Gouvernement Français, à travers le programme « Investissement pour l’avenir » géré par le ANR (Référence ANR-11-IDEX-0004-02). / Augmented reality (AR) can potentially change the driver’s user experience in significant ways. In contrast of the AR applications on smart phones or tablets, the Head-Up-Displays (HUD) technology based on a part or all wind-shield project information directly into the field of vision, so the driver does not have to look down at the instrument which maybe causes to the time-critical event misses. Until now, the HUD designers try to show not only basic information such as speed and navigation commands but also the aids and the annotations that help the driver to see potential dangers. However, what should be displayed and when it has to be displayed are still always the questions in critical driving context. In another context, the pedestrian safety becomes a serious society problem when half of traffic accidents around the world are among pedestrians and cyclists. Several advanced Pedestrian Collision Warning Systems (PCWS) have been proposed to detect pedestrians using the on-board sensors and to inform the driver of their presences. However, most of these systems do not adapt to the driver’s state and can become extremely distracting and annoying when they detect pedestrian. For those reasons, this thesis focuses on proposing a new concept for the PCWS using AR (so called the AR-PCW system). Firstly, for the «When» question, the display decision has to take into account the driver’s states and the critical situations. Therefore, we investigate the modelisation of the driver’s awareness of a pedestrian (DAP) and the driver’s unawareness of a pedestrian (DUP). In order to do that, an experimental approach is proposed to observe and to collect the driving data that present the DAP and the DUP. Then, the feature-based algorithms, the data-driven models based on the discriminative models (e.g. Support Vector Machine) or the generative models (e.g. Hidden Markov Model) are proposed to recognize the DAP and the DUP. Secondly, for the «What» question, our proposition is inspired by the state-of-the-art on the AR in the driving context. The dynamic bounding-box surrounding the pedestrian and the static danger panel are used as the visual aids. Finally, in this thesis, we study experimentally the benefits and the costs of the proposed AR-PCW system and the effects of the aids on the driver. A fixed-based driving simulator is used. A limited display zone on screen is proposed to simulate the HUD. Twenty five healthy middle-aged licensed drivers in ambiguous driving scenarios are explored. Indeed, the heading-car following is used as the main driving task whereas twenty three pedestrians appear in the circuit at different moment and with different behaviors. The car-follow task performance and the awareness of pedestrian are then accessed through the driver actions. The objective results as well as the subjective results show that the visual aids can enhance the driver’s awareness of a pedestrian which is defined with three levels: perception, vigilance and anticipation. This work has been funded by a Ministry scholarship and was carried out in the framework of the FUI18 SERA project, and the Labex MS2T which is funded by the French Government, through the program ”Investments for the future” managed by the National Agency for Research (Reference ANR-11-IDEX-0004-02).