To see the other types of publications on this topic, follow the link: Interaction with AI.
Dissertations / Theses on the topic 'Interaction with AI'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Interaction with AI.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Uga, Brenda. "Towards Trustworthy AI : A proposed set of design guidelines for understandable, trustworthy and actionable AI." Thesis, Uppsala universitet, Institutionen för informatik och media, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-385392.
Full textAbstract:
Artificial intelligence is used today in both everyday applications and specialised expert systems. In situations where relying on the output of the AI brings about the risk of negative consequences, it becomes important to understand why the AI system has produced its output. Previous research in human-computer trust has identified trust antecedents that contribute to formation of trust in an AI artifact, understanding of the system being one of them. In the context of Pipedrive, a sales management system, this thesis investigates how can AI predictions be designed as understandable and trustworthy, and by extension which explanatory aspects provide guidance towards actions to take, and which presentation formats support for- mation of trust. Using a research-through design approach, multiple designs for displaying AI predictions are explored for Pipedrive, leading to a proposal for a set of design guidelines that support understandability, trustworthiness and actionability of AI. Both the designs and the guidelines have been iteratively developed in collaboration with users and design practitioners.<br>Artificiell intelligens används idag både i vardagliga applikationer och expertsystem. I situationer då förtroendet för utdata från AI innebär en risk för negativa konsekvenser blir det viktigt att förstå varför AI-systemet har producerat dess utdata. Tidigare forskning inom människa-datorförtroende har identifierat förtroendeföregångare som bidrar till att skapa förtroende för en AI-artefakt, varav förståelse för systemet är en av dem. Inom ramen för Pipedrive, ett säljhanteringssystem, utreder denna avhandling hur AI-förut-sägelser kan designas på ett förståeligt och pålitligt sätt, och i förlängningen vilka förklarande aspekter som kan ge vägledning gällande de åtgärder som ska vidtas, samt vilka presentationsformat som stödjer skapande av förtroende. Med hjälp av en metod för forskning genom design undersöks flera utföranden för att visa AI-förutsägelser för Pipedrive, vilket leder till ett förslag till en uppsättning riktlinjer för design som stödjer förståelse, pålitlighet och funktionsduglighet. Både design och riktlinjer har utvecklats iterativt i samarbete med användare och designutövare.
2
Strineholm, Philippe. "Exploring Human-Robot Interaction Through Explainable AI Poetry Generation." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-54606.
Full textAbstract:
As the field of Artificial Intelligence continues to evolve into a tool of societal impact, a need of breaking its initial boundaries as a computer science discipline arises to also include different humanistic fields. The work presented in this thesis revolves around the role that explainable artificial intelligence has in human-robot interaction through the study of poetry generators. To better understand the scope of the project, a poetry generators study presents the steps involved in the development process and the evaluation methods. In the algorithmic development of poetry generators, the shift from traditional disciplines to transdisciplinarity is identified. In collaboration with researchers from the Research Institutes of Sweden, state-of-the-art generators are tested to showcase the power of artificially enhanced artifacts. A development plateau is discovered and with the inclusion of Design Thinking methods potential future human-robot interaction development is identified. A physical prototype capable of verbal interaction on top of a poetry generator is created with the new feature of changing the corpora to any given audio input. Lastly, the strengths of transdisciplinarity are connected with the open-sourced community in regards to creativity and self-expression, producing an online tool to address future work improvements and introduce nonexperts to the steps required to self-build an intelligent robotic companion, thus also encouraging public technological literacy. Explainable AI is shown to help with user involvement in the process of creation, alteration and deployment of AI enhanced applications.
3
Houtsma, Meile Jacob. "Perceived AI Performance and Intended Future Use in AI-based Applications." Thesis, Uppsala universitet, Institutionen för informatik och media, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-414835.
Full textAbstract:
This case study explored perceived artificial intelligence (AI) performance and intended future use (IFU) in users of AI-based applications. Users could become less motivated to use these applications if AIs do not clearly communicate their actions. A prototype, a user test, and a structured interview were iteratively developed. Eight students participated in the final iteration, which was thematically analyzed. The results indicate that an AI-based application that shows recommendations can positively affect perceived AI performance and IFU. Possibly, the recommendations increased users’ understanding of AI decisions, as well as their satisfaction. Therefore, recommendations could be a potential design element for increasing perceived AI performance and IFU. Finally, time-saving functionality is a design element that could lead to higher IFU in AI-based applications, possibly only for other tasks than examining recommendations. Further research needs to test these findings under different circumstances.
4
Axelsson, Mattis, and Sara Larsson. "Utvecklande AI : En studie i hur man skapar ett system för lärande AI." Thesis, Blekinge Tekniska Högskola, Sektionen för planering och mediedesign, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4587.
Full textAbstract:
AI är något som blir allt viktigare inom dagens spel och får allt högre krav på att agera mänskligt och intelligent. Detta kandidatarbete undersöker vilken metod som är att föredra för att skapa en AI som kan lära sig av sina tidigare erfarenheter. Några av de metoder som undersöks är trädstrukturer, Artificial Neural Network och GoCap. Genom att skapa en applikation med en av metoderna samt göra en undersökning på hur AI:n i applikationen upplevdes fick vi resultat om denna metod var användbar. Utifrån detta diskuteras det ifall andra metoder hade varit mer effektiva, hur man hade kunnat förbättra AI:n samt hur framtiden för spel-AI skulle kunna se ut.<br>AI is something that has become more important in today’s games and gets higher pressure to act human and intelligent. This thesis examines which methods are preferred when creating an AI that can learn from its previous experiences. Some of the methods that are examined are tree structures, Artificial Neural Network and GoCap. By creating an application with one of the methods and a survey of how the AI in the application was perceived we got a result that showed us if the method was functional. From this we discuss if the other methods would have been more effective, how we could have improved the AI and what the future for game-AI holds.
5
Borgstrand, Richard, and Patrik Servin. "Reinforcement Learning AI till Fightingspel." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-3113.
Full textAbstract:
Utförandet av projektet har varit att implementera två stycken fightingspels Artificiell Intelligens (kommer att förkortas AI). En oadaptiv och mer deterministisk AI och en adaptiv dynamisk AI som använder reinforcement learning. Detta har utförts med att skripta beteendet av AI:n i en gratis 2D fightingsspels motor som heter ”MUGEN”. AI:n använder sig utav skriptade sekvenser som utförs med MUGEN’s egna trigger och state system. Detta system kollar om de skriptade specifierade kraven är uppfyllda för AI:n att ska ”trigga”, utföra den bestämda handlingen. Den mer statiska AI:n har blivit uppbyggd med egen skapade sekvenser och regler som utförs delvis situationsmässigt och delvis slumpmässigt. För att försöka uppnå en reinforcement learning AI så har sekvenserna tilldelats en variabel som procentuellt ökar chansen för utförandet av handlingen när handlingen har givit något positivt och det motsatta minskar när handlingen har orsakat något negativt.
6
Karlsson, Simon, and Christopher Jensen. "Jämförelse mellan neurala nätverk baserad AI och state-of-the-art AI i racing spel." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4831.
Full textAbstract:
Denna rapport jämför prestandan mellan state-of-the-art AI-botar i racing spelet TORCS och en AI-bot som kör med hjälp av ett artificiellt neuralt nätverk (ANN-bot). ANN-boten, som implementerades som en del av arbetet, använder en feedforward arkitektur och backpropagation för inlärning. Ett separat program som användes för att träna det neurala nätverket med träningdata som spelats in från TORCS implementerades också. Som state-of-the-art AI-botar användes AI-botar som har använts i en tävling. De fyra AI-botarna testades på åtta olika banor och data om hur lång tid varje varv tog och hur snabbt AI-botarna körde sparades och sammanställdes. Resultaten visar att på banorna som ANN-boten klarar av att köra runt så är ANN-boten snabbare än en den långsamaste state-of-the-art boten, men ANNboten klara inte av majoriteten av banorna som den testades på. Anledning till detta var antagligen brist på varierande träningsdata.
7
Nordling, Rasmus, and Robin Rietz Berntsson. "AI in Neverwinter Nights using Dynamic Scripting." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-3911.
Full textAbstract:
In this paper research about dynamic scripting and the top culling difficulty scaling enhancement in the game Neverwinter Nights is investigated. A comparison between both a static and a dynamic opponent is made. The human opinion about dynamic scripting is also highlighted. To get an understanding of what the players think about and how they approach an opponent, two experiments were made. One where tests are made on a static opponent and a dynamic opponent, then a second where differences in behavior of the dynamic opponent using top culling and an ordinary dynamic opponent are analyzed. Results from the first test shows the static opponent is more preferable whereas the dynamic opponent using top culling is preferred in the second experiment. Since comparing the two experiments the results are ambiguous. The conclusion is that further investigation is needed in order to answer the question if human players prefer static or dynamic opponents when playing computer games.<br>I detta arbete undersöks tekniken "Dynamic Scripting" och en metod för att skala svårigheten hos motståndare, kallad "Top Culling". Detta har testats i spelet "Neverwinter Nights". En jämförelse mellan en statisk och en dynamisk motståndare har gjorts där den mänskliga synen på dynamic scripting är en huvudfaktor. För att få förståelse hur spelare tänker och bemöter olika motstånd gjordes två experiment. I ett av experimenten testas en statisk och en dynamisk motståndare. I ett annat experiment görs en analys av skillnaderna i beteende mellan en dynamisk motståndare med svårighetsskalning och en dynamisk motståndare utan. Det första experimentet gav resultat som visar att den statiska motståndaren föredras medan i det andra experimentet föredras den dynamiska motståndaren som skalade sin svårighetsgrad. Slutsatsen är att vidare undersökning krävs för att kunna besvara frågan huruvida en spelare hellre vill möta en statisk eller en dynamisk motståndare.
8
Ryrberg, Tobias. "Hur påverkar AI-rekommendationer beslutsfattandet? : En kvantitativ studie om hur AI-rekommendationer påverkar mänskligt beslutsfattande under osäkerhet." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-176265.
Full textAbstract:
Människor fattar varje dag olika beslut. Dessa beslut sker oftast under situationer med osäkerhet, där sannolikheterna och konsekvenserna inte är kända. Med den nya tekniken och ständiga samhällsutvecklingen ställs människor inför beslut i allt mer komplexa situationer. Det finns därför en efterfrågan på beslutsstöd till människor. Ett av dessa beslutsstöd som har utvecklas är med hjälp av artificiell intelligens (AI) och då i form av AI-rekommendationer. Dessa AI-rekommendationer finns redan i situationer som exempelvis i trafiken, sjukvården och finansmarknaden. Det som dock inte har undersökts är hur AI-rekommendationer faktiskt påverkar det mänskliga beslutsfattandet, vilket denna studie syftade till att göra. Studien genomfördes genom ett osäkerhetstest på deltagare som antingen fick rekommendationer från en AI (N=99) eller rekommendationer från en människa (N=85). Det som undersöktes var om det fanns någon skillnad mellan hur människor tar beslut och i deras informationsinsamling, samt i människors säkerhet till sina beslut beroende på om de fick rekommendationer från en AI eller människa. Vidare undersöktes hur AI och mänskliga rekommendationers stödjande och motstridiga information påverkar det mänskliga beslutsfattandet samt människors säkerhet till sina beslut. Slutligen undersöktes om det fanns ett samband mellan människors generella attityder mot AI till deras beslutsfattande, informationsinsamling och säkerhet till sina beslut. Studiens resultat både bekräftar och dementerar tidigare forskning. Framtida forskning bör därför fortsätta undersöka AI-rekommendationers påverkan på det mänskliga beslutsfattandet för att de ska kunna användas på bästa sätt och då samtidigt förhoppningsvis fortsätta utveckla samhället.
9
Cornwell, Jeffrey M. "The Interaction of Sire Fertility and Timing of AI in a Synchronization Protocol." Thesis, Virginia Tech, 2005. http://hdl.handle.net/10919/42357.
Full textAbstract:
The objectives of this study were to determine if fixed-timed artificial insemination (FTAI) at two different times, 0 or 24 h after GnRH administration, in a Presynch-Ovsynch protocol influenced the pregnancy rate (PR) when average and high fertility sires were used. Additionally, a second experiment was conducted to determine the effectiveness of CIDR inserts to allow for resynchronization of estrus in cows that did not conceive or maintain the conceptus at FTAI. Lactating Holstein cows (n = 1,457) from two well-managed dairy herds located in the piedmont region of North Carolina were utilized for 12 mo. First artificial insemination (AI) PR differed for fertility group and was 24.1 and 29.2% for average and high fertility group, respectively. Timing of AI did not influence first AI PR and there was no interaction of fertility group and timing of AI. Cows that received a CIDR insert were detected more frequently in estrus during a 4 d period, d 21 to 24, than control cows, 92.5 and 62.0%, respectively. However, the CIDR insert did not increase the detection of estrus compared to control cows over a normal estrus return interval of 7 d, 18 to 24 d after GnRH administration of a FTAI protocol, 28.8 and 34.2% respectively. In conclusion, the use of high fertility sires is a practical recommendation for improving first AI PR and CIDR inserts allowed more cows to be detected in estrus during a shorter interval, but did not increase the estrus detection rate during a normal estrus return interval.<br>Master of Science
10
Kory-Westlund, Jacqueline M. (Jacqueline Marie). "Relational AI : creating long-term interpersonal interaction, rapport, and relationships with social robots." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/123627.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2019<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 266-294).<br>Children are now growing up with Al-enabled, socially interactive technology. As such, we need to deeply understand how children perceive, interact, and relate to this kind of technology, especially given the many ethical concerns that arise in the context of human-machine interactions, most of which are most contentious with children. To this end, I explore questions about young children's interactions and relationships with one such technology--social robots-during language learning activities. Language learning is a ripe area for exploring these questions because of the social, interactive, interpersonal nature of the activity. In addition, literacy, language, and interpersonal skills are some of the most important skills any child will learn, as they can greatly impact children's later educational and life success.<br>Through a series of 9 empirical child-robot interaction studies with 347 children and using both teleoperated and autonomous robots, I establish the role of social robots as relational technology-that is, technology that can build long-term, social-emotional relationships with users. I hypothesize that a key aspect of why social robots can benefit children's learning is their social and relational nature. To that end, I demonstrate the capabilities of social robots as learning companions for young children that afford opportunities for social engagement and reciprocal interaction, particularly peer-to-peer mirroring. I discuss how we can understand children's conceptualizations of social robots as relational agents and measure children's relationships over time. I introduce the term relational AI to refer to autonomous relational technologies.<br>I develop a computational relational Al system to examine how using relational Al in a social robot can impact child-robot learning interactions. Through testing the autonomous system in a longitudinal study with 49 children, I explore connections between children's relationship and rapport with the robot and their engagement and learning. I discuss the ethical use and design implications of relational AL. I show that relational AI is a new, powerful educational tool, unlike any other existing technology, that we can leverage to support children's early education and development.<br>"Supported by a MIT Media Lab Learning Innovation Fellowship, and by the National Science Foundation (NSF) under Grants CCF-1 3 89 86, IIS-1122886, IIS-11228 4 5, IIS-112308 5 , IIS-1523118, and Graduate Research Fellowship Grant No. 1122374"--Page 6<br>by Jacqueline M. Kory-Westlund.<br>Ph. D.<br>Ph.D. Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences
11
Zhu, Jichen. "Intentional systems and the artificial intelligence (AI) hermeneutic network: agency and intentionality in expressive computational systems." Diss., Georgia Institute of Technology, 2009. http://hdl.handle.net/1853/34730.
Full textAbstract:
Human interaction with technical artifacts is often mediated by treating them as if they are alive. We exclaim "my car doesn't want to start," or "my computer loves to crash." Of increasing cultural importance are software systems designed explicitly to perform tasks and/or exhibit complex behaviors usually deemed as intentional human phenomena, including creating, improvising, and learning. Compared to the instrumental programs (e.g., Adobe Photoshop), these intentional systems (e.g., George Lewis' musical system Voyager) seem to produce output that is "about" certain things in the world rather than the mere execution of algorithmic rules. This dissertation investigates such phenomena with two central research questions: (1) How is system intentionality formed? and (2) What are the design implications for building systems that utilize such intentionality as an expressive resource.
In the discourse of artificial intelligence (AI) practice, system intentionality is typically seen as a technical and ontological property of a computer program, emerging from its underlying algorithms and knowledge engineering. Distilling from the areas of hermeneutics, actor-network theory, cognitive semantics theory, and philosophy of mind, this dissertation proposes a humanistic and interpretive framework called the AI hermeneutic network. It accentuates that system intentionality is narrated and interpreted by its human creators and users in their socio-cultural settings. Special attention is paid to system authors' discursive strategies, a constitutive component of AI, embedded in their source code and technical literature. The utility of the framework is demonstrated by a close analytical reading of a full-scale AI system, Copycat.
The theoretical discovery leads to new design strategies, namely scale of intentionality and agency play. They provide insights for using system intentionality and agency as expressive resources that can be used to convey meanings and express ideas. The fruits of these insights are illustrated by a stream of consciousness literature inspired interactive narrative project Memory, Reverie Machine, co-developed using Harrell's GRIOT system. It portrays a protagonist whose intentionality and agency vary dynamically in service of narrative needs.
12
Olsson, Linn. "AI-systems möjligheter i enavancerad support- och industrikontext." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-159309.
Full textAbstract:
En fallstudie för Siemens i deras supportorganisation där deras arbeteundersöks och dess möjligheter att nyttja ett AI-system för förbättringar.Detta undersöks med hjälp av teorier inom distribuerad kognitionsamt vad som finns tillgängligt inom AI-system likt chatbotar.Genom kontextuella intervjuer inom ramarna för Kontextuell design skapasaffinitetsdiagram och DiCoT analys av datan för att ge en omfattandebild. Detta används för att diskutera de konsekvenser för design av ettAI-system som deras distribuerade kunskapsarbete behöver. Genom resultatetåskådliggörs de många system supportteknikerna använder ochhur de tar hjälp av varandra för att lösa det svårigheter de stöter på. Islutsatsen lyfts det fram förslag på införande av AI-system för supportteknikernamen även en alternativ lösning som är kundorienterad.<br>A case studie at Siemens supportorganisation is studied and the possibilities to use an AI-system for improvements. This is studied with theories in distributed cognition and what is available in AI-systems such as chatbots. Through contextual inquiry, which is a part of the method Contextual Design, affinity diagrams were made and a analysis through DiCoT to create a relevant image. This is used to discuss consequences for the design of an AI-system that the supporttechnicians need. Through the result the many systems that the supporttechnicians use are illustrated and how they depend on eachother to solve difficulties. In the conclusion different suggestions are made about a AI-system for the support technicians but also an alternative that is customer related.
13
Svensson, Viktor. "Navigating an AI-bot within Game-like Environments using Genetic Algorithms." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2723.
Full textAbstract:
Genetic Algorithms is a field of computer science that have many applications, ranging from teaching robots how to overcome a problem, to improving designs and optimizing solutions. Genetic Algorithms is a perfect tool for optimization of an AI’s thought process. In this thesis, I explore one way of how to make an AI-bot move through an area with obstacles and try to get to a goal somewhere on that playing field. Genetic Algorithms will be used to improve how the AI reacts when faced with obstacles and getting better at it with each generation. The thesis shows that it is possible to use Genetic Algorithms to optimize an AI at a specific task and a notion that the more resistance it encounters, the the better it gets.<br>Arbetet handlar om hur man kan använda Genetiska Algoritmer för att lära en AI att röra sig igenom ett område med hinder för att hitta ett mål.
14
Butt, Rehman. "Performance Comparison of AI Algorithms : Anytime Algorithms." Thesis, Blekinge Tekniska Högskola, Avdelningen för programvarusystem, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-5845.
Full textAbstract:
Commercial computer gaming is a large growing industry that already has its major contributions in the entertainment industry of the world. One of the most important among different types of computer games are Real Time Strategy (RTS) based games. RTS games are considered being the major research subject for Artificial Intelligence (AI). But still the performance of AI in these games is poor by human standards due to some fundamental AI problems those require more research to be better solved for the RTS games. There also exist some AI algorithms those can help us solve these AI problems. Anytime- Algorithms (AA) are algorithms those can optimize their memory and time resources and are considered best for the RTS games. We believe that by making AI algorithms anytime we can optimize their behavior to better solve the AI problems. Although many anytime algorithms are available to solve various kinds of AI problems, but according to our research no such study is been done to compare the performances of different anytime algorithms for an AI problem in RTS games. This study will take care of that by building our own research platform specifically design for comparing performances of our selected anytime algorithms for an AI problem.<br>Address: NaN Mob. +46 - 737 - 40 19 17
15
Karlsson, Fredrik. "User-centered Visualizations of Transcription Uncertainty in AI-generated Subtitles of News Broadcast." Thesis, Uppsala universitet, Människa-datorinteraktion, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-415658.
Full textAbstract:
AI-generated subtitles have recently started to automate the process of subtitling with automatic speech recognition. However, people may not perceive that the transcription is based on probabilities and may entail errors. For news that is broadcast live may this be controversial and cause misinterpretation. A user-centered design approach was performed investigating three possible solutions towards visualizing transcription uncertainties in real-time presentation. Based on the user needs, one proposed solution was used in a qualitative comparison with AI- generated subtitles without visualizations. The results suggest that visualization of uncertainties support users’ interpretation of AI-generated subtitles and helps to identify possible errors. However, it does not improve the transcription intelligibility. The result also suggests that unnoticed transcription errors during news broadcast is perceived as critical and decrease trust towards the news. Uncertainty visualizations may increase trust and prevent the risk of misinterpretation with important information.
16
Papworth, Sofia. "Storytelling through Gameplay : Dimensions of AI Design for Narrative Purposes." Thesis, Umeå universitet, Institutionen för tillämpad fysik och elektronik, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-115769.
Full textAbstract:
A vast number of game developers long for and seek to create games that impact and emotionally engages their players. However, it has proven to be a tough challenge to overcome, as a lot of narrative games today completely separate their emotional stories from their engaging gameplay. Extending this insight, this paper proposes the theoretical basis intendedto contribute to the understanding of how to create expressive AI agents, by answering the following question: How can developers tell stories through an AI agent's behaviour? A further key element in this paper is the creation of a conceptual framework, based on a literature study, exemplifying how AI agents can be designed to contribute and support the narrative in a game. The framework suggests that creating these types of AI agents is an iterative process of defining the core themes within a game, deriving an agent's purpose from these and building its behaviours from that purpose. Also, defining how to communicate these behaviours to the player. The framework also emphasizes the importance of user testing during the design process, as a way of evaluating the balance of transparency and emergence within the AI system of the game. The framework is exemplified with a case study conducted on an AI agent, designed and developed for the game Shelter 2: Paws by game studio Might and Delight. The results of the study shows that AI agent has a close connection to the narrative through the main themes of friendship, cooperation and growing up in the game. Finally, the AI agent design is evaluated through user tests, which shows that players interact with the agent as expected and share the game experience that is intended by the developers.
17
Lindborg, PerMagnus. "Le dialogue musicien-machine : Aspects des systèmes d'interactivité musicale." Licentiate thesis, Université de Paris IV Sorbonne, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-177670.
Full textAbstract:
Ce texte a comme sujet la confluence entre la création musicale et les sciences cognitives. Le but principal du travail a été de faire de la reconnaissance sur le terrain. Le présent texte est donc forcément incomplet, et ne servira que de point de départ pour une recherche substantielle. J’ai choisi comme thématique l’interactivité musicale, qui sera définie comme le dialogue musicien–machine. Je vais tenter d’approcher ce phénomène par multiples chemins, qui se superposent. Le thème restera au centre, et autour de lui, j’esquisserai sa relation avec plusieurs faits et phénomènes liés, en particulier : les langages naturels et formels, la question de l’interface à la création, l’intelligence artificielle, et les notions de mémoire et de sens. Ces approches mises ensemble constitueront l’étude des aspects des systèmes d’interactivité. Le vaste sujet de l’interactivité musicale est incrusté dans l’histoire de la musique d’ordinateur, une histoire qui date déjà d’un demi-siècle au moins. Par conséquent il sera nécessaire de cerner le cœur du sujet et de parcourir des cercles concentriques ou en spirale, pour gagner des connaissances qui nous permettent de comprendre mieux le phénomène. La procédure est un peu comme quand on observe une étoile avec l’œil nu : si on la regarde tout droit elle disparaît… La rétine est plus sensible à la lumière dans les côtés. Le texte est donc fatalement un collage consistant de plusieurs études d’envergure limitée. Malgré cela, il faut respecter les aspects importants propres au sujet, essayer d’esquiver le superflu et faire le plus possible de liens. La recherche est guidée par trois thématiques. Quelle est la matière, en d’autres termes, les composants et les processus qui constituent le système de proprement dit, utilisé dans la situation de performance musicale ? Deuxièmement, quelle est la relation entre recherche cognitive et outils technologiques à disposition ? Troisièmement, quelles implications est-ce que les technologies ont eues et auront d’autant plus à l’avenir sur la créativité musicale ? Depuis plusieurs années, les concepts qui sous-tiennent ce texte ont influencé mon travail de compositeur et performeur. J’ai fait des expériences en la matière au travers d’œuvres employant des dispositifs électroacoustiques de configuration variable : “Beda+” (1995), “Tusalava” (1999), “Leçons pour un apprenti sourd-muet” (1998-9), “gin/gub” (2000), “Manifest”[1] (2000), “Project Time”[2] (2001), “sxfxs” (2001), “Extra Quality” (2001-2), ”D!sturbances 350–500”[3]… Ces morceaux de musique sont nés d'une curiosité pour le fondement théorique de la cognition et le fonctionnement du cerveau humain. En particulier, je me suis consacré à analyser la situation de jeu dans laquelle a lieu un échange d’informations et d’initiatives musicales entre musicien et machine, qui agissent sur un degré équivalent de participation dans un système complexe. J’éprouve que cette situation ludique peut également servir d’outil de recherche ; elle est un peu comme un laboratoire, ou un banc d’essai, pour tester des hypothèses, qu’elles soient des propos limités à la musique, ou bien plus étendues, élargissant vers des terrains inhabituels. Étant compositeur, j’ai essayé de rendre l’étude ni trop limitée, ni strictement descriptive. J’ai ressenti le besoin d’analyser des travaux contemporains, ayant des composants scientifiques : les trois projets étudiés sont effectivement en cours de développement. Il s’agissait dans cette étude de capter plutôt leur raison d’être que de montrer leurs formes respectives dans un état finalisé, qui de toute façon n’est pas leur destin. Si la musicologie se contentait de démontrer des structures dans des œuvres de répertoire connues depuis longtemps, ou si elle s’enfermait dans un académisme technocrate développant des modèles n’expliquant que des choses qui sont évidentes pour les musiciens, alors elle souffrirait d’anémie. En proposant une hypothèse, elle doit comporter des aspects prédictifs. Ce serait encore mieux si des modèles développés en support à l’hypothèse étaient facilement accessibles et pouvaient servir au développement de nouveaux outils innovants. Cela est souhaitable, non seulement pour stimuler la production créative, mais également pour aider à mieux comprendre le fonctionnement de la créativité lui-même. L’activité musicale, au sens général, pour ceux qui la produisent autant que pour ceux qui l’apprécient, est un exercice essentiellement non-verbal dont le but est l’émergence d'une compréhension de la créativité humaine d’un ordre autre que verbal ou écrit. En étudiant la créativité, et surtout sa formalisation, ne risquerait-on pas de la dénaturer ? Peut-être la créativité ne risque-t-elle pas de s’effondrer dans la recherche ? Que restera-t-il de la création musicale le jour où une machine aura composé une œuvre capable d’émouvoir les auditeurs ignorant tout de son mode de fabrication ? Néanmoins, en suivant l’appel de William Faulkner, “kill your darlings”, espérons transcender la créativité telle qu’on la connaît et aller vers des pays musicaux inouïs.<br><p>QC 20151217</p>
18
Olivieri, Emily, and Loredana Isacsson. "Exploring guidelines for human-centred design in the wake of AI capabilities : A qualitative study." Thesis, Tekniska Högskolan, Jönköping University, JTH, Datateknik och informatik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-48072.
Full textAbstract:
Purpose – Artificial Intelligence has seen important growth in the digital area in recent years. Our aim is to explore possible guidelines that make use of AI advances to design good user experiences for digital products. Method – The proposed methods to gather the necessary qualitative data to support our claim involve open-ended interviews with UX/UI Designers working in the industry, in order to gain a deeper understanding of their thoughts and experiences. In addition, a literature review is conducted to identify the knowledge gap and build the base of our new theory. Findings – Our findings suggest a need to embrace new technological developments in favour of enhancing UX designers’ workflow. Additionally, basic AI and ML knowledge is needed to utilise these capabilities to their full potential. Indeed, a crucial area of impact where AI can augment a designer’s reach is personalization. Together with smart algorithms, designers may target their creations to specific user needs and demands. UX designers even have the opportunity for innovation as mundane tasks are automated by intelligent assistants, which broadens the possibility of acquiring further skills to enhance their work. One result, that is both innovative and unexpected, is the notion that AI and ML can augment a designer’s creativity by taking over mundane tasks, as well as, providing assistance with certain graphics and inputs. Implications – These results indicate that AI and ML may potentially impact the UX industry in a positive manner, as long as designers make use of the technology for the benefit of the user in true human-centred practice. Limitations – Nevertheless, our study presents its own unique limitations due to the scope and time frame of this dissertation, we are bound to the knowledge gathered from a small sample of professionals in Sweden. Presented guidelines are a suggestion based on our research and not a definitive workflow.
19
Pinnaka, Sumanth. "Negative Attitude Towards AI and Its Relationship with the Cultural Dimension of Power Distance." Thesis, Uppsala universitet, Institutionen för informatik och media, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-420372.
Full textAbstract:
Earlier studies have focused on the relationship between negative attitudes towards AI and collective culture of the country (country of origin). These differences may be because of sizeable differences in the power distance index (PDI) on the population level between different countries. We investigated the relationship between power distance index (PDI) of individuals; and their attitudes towards AI through a survey of participants from two countries, India and Sweden, where there are large differences in PDI on the population level. Results of the correlation test showed that power distance correlates positively with negative attitudes towards interactions with AI and the social influence of AI i.e. higher PDI means more of a negative attitude towards AI. However, power distance correlates positively to the acceptance of AI in a workplace environment, i.e. higher PDI means higher acceptance of AI in the workplace. The latter result was contradictory to our expectations and contradicted an earlier study [8], wherein high PDI showed hindrance in acceptance of the technology at workplace.
20
Saveh, Diana. "Anpassning av mobilnotifikationer med hjälp av maskininlärning." Thesis, Mittuniversitetet, Institutionen för informationssystem och –teknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-36451.
Full textAbstract:
The aim of this study has been to answer the question whether it is possible to obtain notifications that work with the user, instead of against, which can be experienced as stressful and bothersome. To decrease the stressful notifications an application was created which acted as a notification control. The application used machine learning to predict when the user wanted to receive their notifications. For an artificial intelligence to work there needs to be a pattern recognition. In this case the pattern recognition that was used is called the association rule analysis. The association rule analysis used a tree called fp-growth. After the application was made, a usability test was made before and after the installation of the application. The usability test was testing if the user experienced stress and how the application worked. The study showed that screen time decreased by one hour and the number of times the mobile was opened was also reduced. This survey requires more data as it may be that the user was not affected by the application but only randomly used the mobile phone less.<br>Denna studie handlade om att försöka minska störande notifikationer som kan upplevas som stressande och irriterande. Det som skapades var en applikation som agerade som en notifikationskontroll. Denna applikation fungerar med hjälp av maskininlärning som ska förutse när användaren ville ta emot sina notifikationer. Den mönsterigenkännande artificiella intelligensen som användes kallas associationsregelanalys. Associationsregelanalysen använde sig av ett träd som kallas fp-growth. Det gjordes ett användartest före installation av applikationen och ett användartest efter för att se hur användaren upplevde stress men även själva applikationen. Studien visade att skärmtiden minskade med en timme och antalet gånger som mobilen öppnades minskades också. Denna undersökning kräver mer data då det kan vara så att användaren inte blev påverkad av applikationen utan endast slumpmässigt använde mobiltelefonen mindre.
21
Södergren, Gunnar. "Exploring Need-based AI Behaviour and its Effect on the Game Experience of Neverwinter Nights." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2699.
Full textAbstract:
Single Player Roleplaying Game (SPRPG) is a popular genre among players as well as developers, with recent blockbuster titles such as Skyrim by Bethesda and Mass E↵ect 3 by Bioware. In recent years, an occurrence that have been gaining a lot of attention is the development of more advanced and vivid Artificial Intelligence (AI) within these SPRPG and a lot of progress has been made towards making the Non-player Character (NPC) more vivacious and life-like. It is, however, still a common occurrence that NPCs wait around for the player to interact with them; never having a plan or agenda of their own. Their purpose seem to be to wait for the player and provide him or her with information, bartering or a quest. This could result in a game environment that feels static and lifeless to some players and, thus, possibly become detrimental to the game experience. The main objective of this thesis was to implement a need-based system, resembling, to some degree, the one used in The Sims by Maxis, where NPCs get hungry, thirsty, sleepy and similar, and to test whether this system will enhance the game experience. If the NPCs of a SPRPG have needs of their own and therefore can not just wait around for the player to come to them, it may make the game experience more life-like and dynamic. A need-based system that allows the designer to define a set of needs for each NPC, was implemented using the Aurora Toolset for Neverwinter Nights by Bioware. The system was then tested by allowing a number of people play a custom module for Neverwinter Nights twice: once with the system in place and once without, then answering questionnaires regarding their experience. The results show, unanimously, that this prototype did enhance the game experience. Though this was a small module and only a prototype, it does indicates that the use of a need-based system might indeed enhance the dynamic and vivacity of a SPRPG.<br>Singleplayer-rollspel är en populär genre bland såväl spelare som utvecklare, med stora titlar såsom Skyrim av Bethesda och Mass Effect 3 av Bioware. På senare tid har utvcklandet av levande och avancerad AI erhållit mycket fokus inom denna typ av spel och stora framsteg har tagits vad gäller att skapa levnadslika och realistiska icke-spelarkaraktärer. Det är dock fortfarande en vanlig förekomst att ickespelarkaraktärer i denna typ av spel saknar en egen agenda eller plan och därför endast står och väntar på att spelaren ska interagera med dem. Denna uppsats har syftat till att implementera ett behovsbaserat system som till viss del liknar det som används i The Sims av Maxis, där icke-spelarkaraktärer blir hungriga, trötta och liknande, och att testa huruvida detta system förhöjer spelupplevelsen. Systemet har implementerats med hjälp av Aurora Toolset till Neverwinter Nights av Bioware och har testats av ett antal personer i en egenskapad modul till spelet. Resultatet har visat, entydigt, att implementationen av detta behovsbaserade system förhöjde spelupplevelsen. Även om systemet, i denna version, är en prototyp, ger det en indikation på att användandet av ett behovsbaserat system kan förhöja spelupplvelsen i ett singeplayer-rollspel.
22
Allawerdi, Rabii. "Gamers and non-gamers preferences ofcrossmodal AI assistants : A remote explorative study on the uncanny." Thesis, Karlstads universitet, Handelshögskolan (from 2013), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-86021.
Full textAbstract:
Technological advancements have allowed the design of more realistic virtual characters, for example, in-game development; meanwhile, researchers argue that more realism is not always suitable. As an explorative pilot study, this thesis investigates the uncanny among human-like agents and intelligent systems with human-like attributes. The thesis focuses on the uncanny theories to understand whether Mori's Uncanny Valley (UV) or Tinwell's Uncanny wall (UW) is more suitable when designing with a user-centred approach. The study facilitated two remote focus group workshops consisting of seven participants to understand the participant's expectations, needs and desires of existing and future AI technology. The participants consisted of two target groups, gamers and non-gamers, in order to understand if exposure to AI leads to adoptability of the technology. The participants described their perspectives and needs of existing AI assistants, and their preferences of human-like cross modality such as voice and avatar for future assistants. The research activities resulted in insights and four themes: rejection of existing assistant technology, productivity and task management, expectations of future AI assistants and balancing human-likeness. Findings show that participants reject existing assistant technologies, as old tangible habits, social norms, and incompatibility prevent the adoption of existing assistant technology. While both gamers and non-gamers seek a balance between generic robotics and pure human likeness, none of the participants fully adopted the idea of human likeness as it generates uncanny feelings.
23
Edberg, Emelie, and Lea Beck. "Adoption of AI in Digital Design : A qualitative study about the effects on the profession." Thesis, Jönköping University, Tekniska Högskolan, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-48126.
Full textAbstract:
The development of new technology plays a major role in today's society and several different industries. While some technologies have more or less an impact upon the whole working sector, one of the more recent and controversial technologies is Artificial Intelligence (AI). In recent years, this technology has evolved continuously and is spreading across several different industries. As it is clear that AI is reshaping the workplace, it is relevant to examine how and to what extent it is affecting the digital design profession. Purpose The purpose of this study is to gain insight into the current state of adoption of AI within digital design, including graphic design and web design. Furthermore, to explore the effects of AI on the nature of the profession, from the perspectives of professionals in the industry. While focusing on the creative process and the development of digital products, it investigates how the industry is experiencing the effects of AI in daily tasks and workflows. Furthermore, it examines if the implementation of AI has lead to the development of new work processes, or if traditional tasks remain but are carried out with AI tools as assistance. Method The research method is qualitative. Through literature reviews and by carrying out interviews with relevant designers currently working in the industry, the appropriate data is collected and analyzed. The interviews focus on understanding the participant’s perspective on the topic, their experiences of AI and what effect it has on their work. Through the interviews, the study identifies to what extent AI is used in creative processes, and sheds light on the general feelings towards AI, including expectations and concerns. Conclusions The findings show that the overall awareness surrounding AI is rather divided. AI is already implemented in various design processes and software, whether the designer is aware of it or not. It can thus be concluded that AI has affected the nature of the digital design profession. However, the effects vary depending on the specific role and the related tasks. Most are interested in learning more about it but natural skepticism and lack of knowledge about the technology remain an obstacle for implementing more AI in companies.
24
Förster, Frank. "Robots that say 'no' : acquisition of linguistic behaviour in interaction games with humans." Thesis, University of Hertfordshire, 2013. http://hdl.handle.net/2299/20781.
Full textAbstract:
Negation is a part of language that humans engage in pretty much from the onset of speech. Negation appears at first glance to be harder to grasp than object or action labels, yet this thesis explores how this family of ‘concepts’ could be acquired in a meaningful way by a humanoid robot based solely on the unconstrained dialogue with a human conversation partner. The earliest forms of negation appear to be linked to the affective or motivational state of the speaker. Therefore we developed a behavioural architecture which contains a motivational system. This motivational system feeds its state simultaneously to other subsystems for the purpose of symbol-grounding but also leads to the expression of the robot’s motivational state via a facial display of emotions and motivationally congruent body behaviours. In order to achieve the grounding of negative words we will examine two different mechanisms which provide an alternative to the established grounding via ostension with or without joint attention. Two large experiments were conducted to test these two mechanisms. One of these mechanisms is so called negative intent interpretation, the other one is a combination of physical and linguistic prohibition. Both mechanisms have been described in the literature on early child language development but have never been used in human-robot-interaction for the purpose of symbol grounding. As we will show, both mechanisms may operate simultaneously and we can exclude none of them as potential ontogenetic origin of negation.
25
Edlund, Mattias. "Artificial Intelligence in Games : Faking Human Behavior." Thesis, Uppsala universitet, Institutionen för speldesign, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-258222.
Full textAbstract:
This paper examines the possibilities of faking human behavior with artificial intelligence in computer games, by using efficient methods that save valuable development time and also creates a more rich experience for the players of a game. The specific implementation of artificial intelligence created and discussed is a neural network controlling a finite-state machine. The objective was to mimic human behavior rather than simulating true intelligence. A 2D shooter game is developed and used for experiments performed with human and artificial intelligence controlled players. The game sessions played were recorded in order for other humans to replay. Both players and spectators of the game sessions left feedbacks and reports that could later be analyzed. The data collected from these experiments was then analyzed, and reflections were made on the entire project. Tips and ideas are proposed to developers of shooter games who are interested in making human-like artificial intelligence. Conclusions are made and extra information is provided in order to further iterate on this research.<br>Denna rapport undersöker möjligheterna att förfalska mänskligt beteende genom artificiell intelligens i datorspel, med hjälp av effektiva metoder som sparar värdefull utvecklingstid och som även skapar en rikare upplevelse för spelare. Den specifika implementationen av artificiell intelligens som utvecklas och diskuteras är ett neuralt nätverk som kontrollerar en finite-state machine. Målet var att efterlikna mänskligt beteende snarare än att simulera verklig intelligens. Ett 2D shooter-spel utvecklas och används för utförda experiment med mänskliga och artificiell intelligens-kontrollerade spelare. De sessioner som spelades under experimenten spelades in, för att sedan låta andra människor titta på inspelningarna. Både spelare och åskådare av spelsessionerna lämnade återkoppling och rapporter för senare analysering. Datan som samlats in från experimenten analyserades, och reflektioner utfördes på hela projektet. Tips och idéer presenteras till utvecklare av shooter-spel som är intresserade av en mer människolik artificiell intelligens. Slutsatser läggs fram och extra information presenteras för att kunna fortsätta iterera vidare på denna undersökning.
26
Sircoglou, Marie. "Etude des modes de coordination des ligands ambiphiles PE (E=B,AI,Ga)." Toulouse 3, 2009. http://thesesups.ups-tlse.fr/606/.
Full textAbstract:
Ce travail porte sur la chimie de coordination des ligands ambiphiles combinant une base et un acide de Lewis. Le rôle que peut jouer l'acide de Lewis dans la sphère de coordination du métal est en particulier étudié par le biais d'une approche expérimentale et théorique. Le premier chapitre introduit le contexte et les principaux objectifs de ce travail. Le deuxième chapitre propose une étude des interactions métal->borane supportées par des ligands ambiphiles. Une description précise de l'interaction Au->B est proposée dans le cadre de la coordination de ligand diphosphine boranes. L'influence du fragment métallique sur la force de l'interaction M->B est également évaluée à travers l'étude d'une série isoélectronique de 7 complexes de triphosphine borane des métaux des groupes X et XI. Le troisième chapitre aborde les limites d'existence de ce type d'interaction en combinant ligands flexibles et métal peu basique. Un mode de coordination multi-centre est mis en évidence au sein d'une famille de complexes de Cuivre de mono-et di- phosphine boranes. Ce résultat met en lumière la capacité de ces ligands à adapter leur coordination en fonction de la demande électronique du métal. Le quatrième chapitre vise à déterminer l'influence du fragment acide de Lewis sur le mode de coordination des ligands ambiphiles. De façon inattendue, la complexation des ligands di- et tri- phosphine alanes conduit à des espèces zwittérioniques résultant d'une activation " totale " de la liaison M-X par l'acide de Lewis. La complexation des ligands phosphine gallanes conduit quant à elle à deux isomères de coordination, neutres et zwittérioniques, obtenus séparément ou en équilibre suivant le nombre de groupements donneurs du ligand<br>The present contribution deals with the coordination chemistry of ambiphilic ligands, featuring both Lewis base and Lewis acid sites. In particular, the role that can play the Lewis acid within the coordination sphere of the metal is investigated, thanks to combined experimental and computational analyses. The first chapter introduces the context and main goals of this work. The second chapter focuses on the study of metal->Lewis acid interactions supported by ambiphilic ligands. A description of the very nature of the Au->B interaction is proposed in the case of diphosphine borane complexes. The influence of the nature of the metallic fragment on the M->B interaction strength is also assessed through in depth study of seven isoelectronic triphosphine borane complexes. The third chapter tackled the limit of existence of M?B interactions by combining a weakly basic metal with flexible ligands. Multi-centre coordination modes are evidenced within a family of copper mono- and di- phosphine borane complexes. This study demonstrates the ability of ambiphilic ligands to adapt their coordination to the electronic demand of the metal centre. In the forth chapter, the influence of the Lewis acid nature on the coordination mode of ambiphilic ligands is investigated. Unexpectedly, the complexation of di- and tri- phosphine alane ligands to gold leads to zwitterionic complexes, resulting from the internal activation of the M-X bond by the Lewis acid. In contrast, the complexation of phosphine gallane ligands affords both neutral and zwitterionic coordination isomers, isolable or exchanging depending on the number of donor buttresses
27
Rukanskaitė, Julija. "Tuning into uncertainty : A material exploration of object detection through play." Thesis, Malmö universitet, Institutionen för konst, kultur och kommunikation (K3), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-44239.
Full textAbstract:
The ubiquitous yet opaque logic of machine learning complicates both the design process and end-use. Because of this, much of Interaction Design and HCI now focus on making this logic transparent through human-like explanations and tight control while disregarding other, non-normative human-AI interactions as technical failures. In this thesis I re-frame such interactions as generative for both material exploration and user experience in non-purpose-driven applications. By expanding on the notion of machine learning uncertainty with play, queering, and more-than human design, I try to understand them in a designerly way. This re-framing is followed by a material-centred Research through Design process that concludes with Object Detection Radio: a ludic device that sonifies Tensorflow.js Object Detection API’s prediction probabilities. The design process suggests ways of making machine learning uncertainty explicit in human-AI interaction. In addition, I propose play as an alternative way of relating to and understanding the agency of machine learning technology.
28
Nitz, Pettersson Hannes, and Samuel Vikström. "VISION-BASED ROBOT CONTROLLER FOR HUMAN-ROBOT INTERACTION USING PREDICTIVE ALGORITHMS." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-54609.
Full textAbstract:
The demand for robots to work in environments together with humans is growing. This calls for new requirements on robots systems, such as the need to be perceived as responsive and accurate in human interactions. This thesis explores the possibility of using AI methods to predict the movement of a human and evaluating if that information can assist a robot with human interactions. The AI methods that were used is a Long Short Term Memory(LSTM) network and an artificial neural network(ANN). Both networks were trained on data from a motion capture dataset and on four different prediction times: 1/2, 1/4, 1/8 and a 1/16 second. The evaluation was performed directly on the dataset to determine the prediction error. The neural networks were also evaluated on a robotic arm in a simulated environment, to show if the prediction methods would be suitable for a real-life system. Both methods show promising results when comparing the prediction error. From the simulated system, it could be concluded that with the LSTM prediction the robotic arm would generally precede the actual position. The results indicate that the methods described in this thesis report could be used as a stepping stone for a human-robot interactive system.
29
Holmberg, Lars. "Human In Command Machine Learning." Licentiate thesis, Malmö universitet, Malmö högskola, Institutionen för datavetenskap och medieteknik (DVMT), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-42576.
Full textAbstract:
Machine Learning (ML) and Artificial Intelligence (AI) impact many aspects of human life, from recommending a significant other to assist the search for extraterrestrial life. The area develops rapidly and exiting unexplored design spaces are constantly laid bare. The focus in this work is one of these areas; ML systems where decisions concerning ML model training, usage and selection of target domain lay in the hands of domain experts. This work is then on ML systems that function as a tool that augments and/or enhance human capabilities. The approach presented is denoted Human In Command ML (HIC-ML) systems. To enquire into this research domain design experiments of varying fidelity were used. Two of these experiments focus on augmenting human capabilities and targets the domains commuting and sorting batteries. One experiment focuses on enhancing human capabilities by identifying similar hand-painted plates. The experiments are used as illustrative examples to explore settings where domain experts potentially can: independently train an ML model and in an iterative fashion, interact with it and interpret and understand its decisions. HIC-ML should be seen as a governance principle that focuses on adding value and meaning to users. In this work, concrete application areas are presented and discussed. To open up for designing ML-based products for the area an abstract model for HIC-ML is constructed and design guidelines are proposed. In addition, terminology and abstractions useful when designing for explicability are presented by imposing structure and rigidity derived from scientific explanations. Together, this opens up for a contextual shift in ML and makes new application areas probable, areas that naturally couples the usage of AI technology to human virtues and potentially, as a consequence, can result in a democratisation of the usage and knowledge concerning this powerful technology.
30
Eklund, Joakim, and Fred Isaksson. "Identifying & Evaluating SystemComponents for Cognitive Trustin AI-Automated Service Encounters : Trusting a Study- & Vocational Chatbot." Thesis, Uppsala universitet, Avdelningen för systemteknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-386044.
Full textAbstract:
The intensifying idea that AI soon will be a part of our everyday life allows for dreams about the complex relationship we one day could have with non-biological social intelligence. However, establishing societal and individual acceptance of AI-powered autonomy in disciplines built upon to the reliance to human competence raises a number of pressing challenges. One of them being, what system components will engender respectively counteract cognitive trust in socially oriented AI-automated processes? This masters thesis tackles the seemingly ambiguous concept of trust in automation by identifying and evaluating system components that affect trust in a confined and contextualised setting. Practically, we design, construct and test an AI-powered chatbot, Ava, that contains socially oriented questions and feedback about study- and vocational guidance. Through a comparative study of different system versions, including both quantitative and qualitative data, we contribute to the framework for identifying and evaluating human trust in AI-Automated service encounters. We show how targeted alterations to design choices constituting the system components transparency, unbiasses and system performance, identified to affect trust, has consequences on the perception of the cognitive trust concepts integrity, benevolence and ability. Our results display a way of conduct for practitioners looking to prioritise and develop trustworthy autonomy. More specifically, we account for how cognitive trust is decreased when system opacity is increased. Moreover, we display even more concerning effects on trust due to micking contextual bias in the conversation agent.
31
Magnusson, Matteus, and Suresh Balsasubramaniyan. "A Communicating and Controllable Teammate Bot for RTS Games." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4360.
Full textAbstract:
Communication in team games between human player is important, but has been disregarded in teammate bots for Real-Time Strategy (RTS) games. Control over the team-mate bots have existed for a while in other genres than RTS and if implemented correctly it adds another dimension to the game. In this study we investigate whether players think it is more fun to play with an RTS bot that communicates its intentions and reasons and is controllable by the human player. But also what features are liked, disliked, missed to provide guidelines to future researchers and companies. For this we create a StarCraft RTS bot with communication and control abilities. The experiment consists of four scenarios, turning on/o communication and control, to conclude what players think is fun. All testers agreed on communication being important and more fun to play with. Beginners did, however, not like the control feature as they already had enough on their mind whereas experienced players preferred having some control over the bot We conclude that communication is an important role in team games, including RTS games. More work needs to be done how to integrate control so that beginners do not feel overwhelmed and at the same time experienced players do not feel restrained by too simple control commands.
32
Hérail, Philippe. "Apprentissage de Modèles Hiérarchiques par Démonstration pour la Planification et l'Action Délibérée." Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSEI006.
Full textAbstract:
Le développement d'agents autonomes, en particulier d'agents physiques tels que les robots, nécessite des architectures complexes fonctionnant à différents niveaux d'abstraction. Compte tenu de la complexité des environnements réels, l'élaboration manuelle des modèles utilisés pour les différents niveaux devient rapidement difficile. Ces dernières années, de plus en plus de travaux se sont concentrés sur l'apprentissage de modèles au niveau sensorimoteur, c'est-à-dire pour la perception et les capacités motrices de base.L'apprentissage de modèles de plus haut niveau permettant les fonctions délibératives n'a pas bénéficié de la même attention.Parmi ces modèles de haut niveau, nous nous intéresserons aux réseaux de tâches hiérarchiques (Hierarchical Task Networks, HTN), qui constituent un formalisme de planification communément utilisé dans de nombreuses applications pratiques, des jeux vidéo aux robots. Actuellement, la conception de modèles HTN reste une tâche essentiellement manuelle, qui nécessite une expertise à la fois du domaine d'application et des systèmes utilisés pour la planification hiérarchique. Bien que certaines approches existent pour l'apprentissage des HTN, elles souffrent de certaines limitations, principalement au niveau de la structure des domaines qui peuvent être appris ou des annotations requises au niveau des données d'entrée.Dans cette thèse, nous proposerons une technique d'apprentissage pour des HTN à plusieurs niveaux hiérarchiques avec un minimum d'annotation des données d'entrée. Pour cela, nous proposerons deux contributions principales : une procédure d'apprentissage des structures HTN à partir de démonstrations et une procédure d'apprentissage de leurs paramètres à partir de ces démonstrations.L'approche d'apprentissage des structures s'appuiera sur des techniques d'extraction de motifs fréquents pour détecter des blocs intéressants à abstraire dans les démonstrations. Nous associerons cette extraction à un algorithme d'apprentissage de HTN existant. La qualité d'une structure HTN donnée sera évaluée, au cours de la recherche, au moyen d'une nouvelle métrique basée sur le principe de la longueur de description minimale (Minimum Description Length, MDL), qui servira de substitut à une couteuse évaluation des performances de planification.En outre, nous proposons une nouvelle méthode d'identification d'un ensemble pertinent de paramètres pour les HTN, reposant sur une approche MAX-SMT, qui peut être appliquée à la plupart des modèles HTN. L'association de nos contributions pour l'apprentissage d'une structure de modèle HTN et l'identification de ses paramètres nous permet de produire des modèles HTN complets que nous évaluons sur des domaines standard de la communauté de planification hiérarchique<br>The development of autonomous agents, especially embodied agents such as robots, requires complex architectures operating at different levels of abstractions. Given the complexity of real environments, hand-crafting all the models used at the different levels quickly becomes impractical. In recent years, there has been a growing body of work focusing on learning such models at the sensorimotor level, i.e. for perception and basic motor capabilities. However, thesame cannot be said for high-level models enabling deliberative functions.Among such high-level models, we will focus our attention on Hierarchical Task Networks (HTNs), which are a common planning formalism used in many practical applications, from video-games to robotic agents. Presently, designing HTN models remains a mostly manual task, which requires expertise both of the application domain and of the systems used for hierarchical planning. While some approaches do exist for learning HTNs, they suffer from some limitations, mainly in the structure of the domains that can be learned or in the required data annotation.In this thesis, we will propose a technique for learning HTNs with multiple hierarchy levels with minimal annotation work required. To this end, we will propose two main contributions: a procedure for learning HTN structures from demonstrations and one for learning their parameters from these demonstrations.The structure learning approach will leverage frequent pattern mining to detect interesting behavioural patterns to abstract in the demonstrations, which we couple with an existing goal regression algorithm. The quality of a given HTN structure during the search will be evaluated through a novel metric based on the Minimum Description Length (MDL) principle to use as an efficient proxy for planning performance.In addition, we propose a new method for identifying a sensible set of parameters for HTNs, relying on a MAX-SMT approach, which can be applied to most HTN models. Coupling our contributions for learning an HTN model structure and the identification of its parameters allows us to produces complete HTN models which we evaluate on standard benchmarks of the HTN planning community
33
Dang, Mihn Huy. "Is seeing still believing?" Thesis, Umeå universitet, Designhögskolan vid Umeå universitet, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-182464.
Full textAbstract:
Social media content moderators perform a critical function of modern civic society: they act as first responders on social media platforms, getting confronted with harmful digital content on a daily basis.Without them, the Internet would be at the mercy of the unpredictable, global social climate, likely making the Internet a less safe, less peaceful place to be. Nevertheless, disturbing content screening cannot easily be addressed with the future’s planned full integration of artificial intelligence. Content moderation is not a technical challenge that can be solved by employing artificial intelligence as the solution to the content moderation related issues. Automated tools, for example, which are built to recognise creative permutations of language, fail their job. Cultural nuances and linguistic specificities are challenging to algorithms. For this reason, it is important to keep content moderation as a human process, because algorithms are not infallible in the content screening workflow and despite all the struggles content moderators face with screening content. The design concept explores how the emergence of deep fakes can be tackled by social media content moderators without relying too much on algorithms and computer power, but on human skills.
34
Erik, Cambria. "Application of common sense computing for the development of a novel knowledge-based opinion mining engine." Thesis, University of Stirling, 2011. http://hdl.handle.net/1893/6497.
Full textAbstract:
The ways people express their opinions and sentiments have radically changed in the past few years thanks to the advent of social networks, web communities, blogs, wikis and other online collaborative media. The distillation of knowledge from this huge amount of unstructured information can be a key factor for marketers who want to create an image or identity in the minds of their customers for their product, brand, or organisation. These online social data, however, remain hardly accessible to computers, as they are specifically meant for human consumption. The automatic analysis of online opinions, in fact, involves a deep understanding of natural language text by machines, from which we are still very far. Hitherto, online information retrieval has been mainly based on algorithms relying on the textual representation of web-pages. Such algorithms are very good at retrieving texts, splitting them into parts, checking the spelling and counting their words. But when it comes to interpreting sentences and extracting meaningful information, their capabilities are known to be very limited. Existing approaches to opinion mining and sentiment analysis, in particular, can be grouped into three main categories: keyword spotting, in which text is classified into categories based on the presence of fairly unambiguous affect words; lexical affinity, which assigns arbitrary words a probabilistic affinity for a particular emotion; statistical methods, which calculate the valence of affective keywords and word co-occurrence frequencies on the base of a large training corpus. Early works aimed to classify entire documents as containing overall positive or negative polarity, or rating scores of reviews. Such systems were mainly based on supervised approaches relying on manually labelled samples, such as movie or product reviews where the opinionist’s overall positive or negative attitude was explicitly indicated. However, opinions and sentiments do not occur only at document level, nor they are limited to a single valence or target. Contrary or complementary attitudes toward the same topic or multiple topics can be present across the span of a document. In more recent works, text analysis granularity has been taken down to segment and sentence level, e.g., by using presence of opinion-bearing lexical items (single words or n-grams) to detect subjective sentences, or by exploiting association rule mining for a feature-based analysis of product reviews. These approaches, however, are still far from being able to infer the cognitive and affective information associated with natural language as they mainly rely on knowledge bases that are still too limited to efficiently process text at sentence level. In this thesis, common sense computing techniques are further developed and applied to bridge the semantic gap between word-level natural language data and the concept-level opinions conveyed by these. In particular, the ensemble application of graph mining and multi-dimensionality reduction techniques on two common sense knowledge bases was exploited to develop a novel intelligent engine for open-domain opinion mining and sentiment analysis. The proposed approach, termed sentic computing, performs a clause-level semantic analysis of text, which allows the inference of both the conceptual and emotional information associated with natural language opinions and, hence, a more efficient passage from (unstructured) textual information to (structured) machine-processable data. The engine was tested on three different resources, namely a Twitter hashtag repository, a LiveJournal database and a PatientOpinion dataset, and its performance compared both with results obtained using standard sentiment analysis techniques and using different state-of-the-art knowledge bases such as Princeton’s WordNet, MIT’s ConceptNet and Microsoft’s Probase. Differently from most currently available opinion mining services, the developed engine does not base its analysis on a limited set of affect words and their co-occurrence frequencies, but rather on common sense concepts and the cognitive and affective valence conveyed by these. This allows the engine to be domain-independent and, hence, to be embedded in any opinion mining system for the development of intelligent applications in multiple fields such as Social Web, HCI and e-health. Looking ahead, the combined novel use of different knowledge bases and of common sense reasoning techniques for opinion mining proposed in this work, will, eventually, pave the way for development of more bio-inspired approaches to the design of natural language processing systems capable of handling knowledge, retrieving it when necessary, making analogies and learning from experience.
35
Akins, Leighannah. "Understanding the relationship between bacterial community composition and the morphology of bloom-forming Microcystis." Kent State University / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=kent1543502274681124.
Full text
36
Vereschak, Oleksandra. "Understanding Human-AI Trust in the Context of Decision Making through the Lenses of Academia and Industry : Definitions, Factors, and Evaluation." Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS552.
Full textAbstract:
Avec l'essor des systèmes d'aide à la décision intégrant l'intelligence artificielle (AI) dans le domaine médical, judiciaire ou du recrutement, la confiance entre l'humain et l'IA est devenue une priorité dans la conception de ces systèmes. De nombreux gouvernements et grandes entreprises ainsi que des chercheurs proposent diverses stratégies pour favoriser la confiance dans les systèmes intégrant l'IA. Cependant, la confiance est un concept complexe et multidimensionnel, et la confiance entre l'humain et l'IA, qui est un sujet de recherche récent, fait face à plusieurs défis. Sur le plan théorique, la différence entre la confiance et d'autres concepts théoriques proches (par exemple, la conformité) doit être comprise, de même que les facteurs affectant la confiance entre l'humain et l'IA. Sur le plan méthodologique, la confiance est difficile à évaluer, et il est nécessaire de définir des protocoles appropriés. Dans cette thèse, je traite de ces défis de manière empirique à travers deux perspectives : académique et industrielle. J'effectue d'abord une revue systématique de la littérature des études empiriques sur la confiance entre l'humain et l'IA dans le contexte de la prise de décision afin d'obtenir une vue globale de la façon dont la confiance est définie et évaluée dans le monde académique. Cependant, comme la plupart de ces études sont en laboratoire et avec des maquettes d'IA, je poursuis cette analyse pour savoir dans quelle mesure ces résultats sont valables sur le terrain avec des vrais systèmes intégrant l'IA et différentes parties prenantes. Pour cela, je mène une série d'entretiens semi-structurés autour de la définition et de l'évaluation de la confiance entre l'humain et l'IA. Les participants sont soit des personnes qui développent ou conçoivent des systèmes intégrant l'IA pour l'aide à la prise de décision ou bien des personnes qui sont affectées par ces décisions. Je soutiens que la compréhension théorique de la confiance entre l'humain et l'IA influence directement le choix des protocoles expérimentaux et des mesures utilisés pour les études empiriques. En m'inspirant de la littérature en sciences sociales, je propose des recommandations pour améliorer ces protocoles expérimentaux. Je démontre également que la discussion de concepts théoriques, tels que la confiance entre l'humain et l'IA, avec des personnes ordinaires de différents profils peut non seulement valider les théories académiques, mais aussi contribuer à l'avancement de la théorie. Enfin, je donne un aperçu des facteurs qui peuvent affecter la confiance entre l'humain et l'IA dans le contexte de la prise de décision. En comparant les résultats provenant du monde académique avec ceux provenant de l'industrie, je souligne les opportunités pour la recherche pour les chercheurs académiques et des implications pour la conception pour les professionnels de l'IA. Cette thèse fournit des preuves théoriques et empiriques sur la confiance entre l'humain et l'IA dans le contexte de la prise de décision et ouvre des voies pour promouvoir la confiance dans l'interaction entre l'humain et l'IA<br>With the rise of AI-embedded systems assisting decisions in the context of medicine, justice, recruiting, Human-AI trust has become an utmost design priority. Numerous governments and large enterprises as well as researchers propose various strategies on how to foster trust in AI-embedded systems. However, trust is a complex, multifaceted concept, and Human-AI trust, being a recent research avenue, faces several challenges. On the theoretical level, the difference between trust and other related theoretical concepts (e.g. reliance, compliance, and trustworthiness) needs to be understood as well as the factors affecting Human-AI trust. On the methodological level, trust is difficult to assess, and appropriate protocols have to be understood. In this thesis, I tackle these challenges empirically through two lenses - academia and industry. I first conduct a systematic literature review of empirical studies on Human-AI trust in the context of decision making to get an overview of how trust is defined and evaluated in academia. However, as most studies are focusing on users' trust investigated in the controlled lab setting with AI mock-ups, I go further to investigate to which extent these findings hold true for other stakeholders with AI-embedded systems deployed in the market. To do so, I conduct a series of semi-structured interviews on the topic of Human-AI trust definitions and evaluation with people who develop and design AI-embedded systems assisting decision making and with people who are affected by these decisions. I argue that theoretical understanding of Human-AI trust directly affects experimental protocol and measures choices. Drawing from the social sciences literature, I propose guidelines on improving experimental protocols for studying Human-AI trust in the context of decision making. I also demonstrate that discussing theoretical concepts, such as Human-AI trust, with laypeople of different backgrounds not only can validate the academic theories, but also potentially contribute to theoretical advancement. Lastly, I provide an overview of factors that can affect Human-AI trust in the context of decision making and, based on the comparison between the findings of academia and industry, I highlight research opportunities and design implications for academic researchers and AI practitioners. This thesis provides theoretical and empirical evidence on Human-AI trust in the context of decision making and opens the ways to support trust in Human-AI interaction
37
Westblad, Joakim, and Jonathan Wising. "Trippelnarrativ." Thesis, Blekinge Tekniska Högskola, Institutionen för teknik och estetik, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2262.
Full textAbstract:
Detta kandidatarbete undersöker hur narrativa strukturer inom spel fungerar i kombination med varandra, hur dessa kan användas tillsammans och vad som förändras i en spelproduktion. Syftet är att undersöka trippelnarrativ som metod för användande av flera narrativa strukturer i ett och samma spel och att ta reda på hur det kan tillämpas i en spelproduktion. Vi genomförde en undersökande produktion där vi utvecklade en prototyp av ett spel med en trippelnarrativ struktur för att sedan diskutera och resonera kring användandet i spel.<br>Vi har försökt utföra en omstrukturering av berättande i spel med hjälp av olika tekniska och något filosofiska metoder. Vi utvecklade något vi vill kalla för ett trippelnarrativ som är en kombination av tre olika narrativstrukturer.<br>Detta är en reflektionsdel till en digital medieproduktion.
38
Ljungren, Joakim. "Data-driven design for sustainable behavior : A case study in using data and conversational interfaces to influence corporate settlement." Thesis, Umeå universitet, Institutionen för tillämpad fysik och elektronik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-139199.
Full textAbstract:
Interaction with digital products and interfaces concern more and more of human decision-making and the problems regarding environmental, financial and social sustainability are consequences much due to our behavior. The issues and goals of sustainable development therefore implies how we have to think differently about digital design. In this paper, we examine the adequacy of influencing sustainable behavior with a data-driven design approach, applying a conversational user interface. A case study regarding the United Nation’s goals of technological development and economic distribution was conducted, to see if a hypothetical business with a proof-of-concept digital product could be effective in influencing where companies base their operations. The test results showed a lack of usability and influence, but still suggested a potential with language-based interfaces. Even though the results could not prove anything, we argue that leveraging data analysis to design for sustainable behavior could be a very valuable strategy. A data-driven approach could enable ambitions of profit and user experience to coincide with those of sustainability, within a business organization.
39
Melsion, Perez Gaspar Isaac. "Leveraging Explainable Machine Learning to Raise Awareness among Preadolescents about Gender Bias in Supervised Learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-287554.
Full textAbstract:
Machine learning systems have become ubiquitous into our society. This has raised concerns about the potential discrimination that these systems might exert due to unconscious bias present in the data, for example regarding gender and race. Whilst this issue has been proposed as an essential subject to be included in the new AI curricula for schools, research has shown that it is a difficult topic to grasp by students. This thesis aims to develop an educational platform tailored to raise the awareness of the societal implications of gender bias in supervised learning. It assesses whether using an explainable model has a positive effect in teaching the impacts of gender bias to preadolescents from 10 to 13 years old. A study was carried out at a school in Stockholm employing an online platform with a classifier incorporating Grad-CAM as the explainability technique that enables it to visually explain its own predictions. The students were divided into two groups differentiated by the use of the explainable model or not. Analysis of the answers demonstrates that preadolescents significantly improve their understanding of the concept of bias in terms of gender discrimination when they interact with the explainable model, highlighting its suitability for educational programs.<br>Maskininlärningssystemen har blivit allmänt förekommande i vårt samhälle, vilket har lett till oro över den potentiella diskriminering som dessa system kan utöva när det gäller kön och ras. Detta med orsak av det bias som finns i datan. Även om detta problem har föreslagits som ett viktigt ämne som ska ingå i de nya AI-läroplanerna för skolor, har forskning visat att det är ett svårt ämne att förstå för studenter. Detta examensarbete syftar till att utveckla en utbildningsplattform för att öka medvetenhet om de samhälleliga konsekvenserna av könsbias inom övervakad maskinlärning. Det utvärderar huruvida användning av en förklaringsbar modell har en positiv effekt vid inlärning hos ungdomar mellan 10 och 13 år när det kommer till konsekvenserna av könsbias. En studie genomfördes på en skola i Stockholm med hjälp av en onlineplattform som använder en klassificeringsalgoritm med Grad-CAM förklaringsbar teknik som gör det möjligt för den att visuellt förklara sina egna förutsägelser. Eleverna delades in i två grupper som åtskiljdes genom att den ena gruppen använde den förklarbara modellen medan den andra inte gjorde det. Analysen av svaren visar att ungdomar markant förbättrar sin förståelse av könsdiskrimineringsbias när de interagerar med den förklarbara modellen, vilket lyfter fram dess lämplighet för användning inom utbildningsprogram.
40
Thorarinsson, Johann Sigurdur. "Navigating in a dynamic world : Predicting the movements of others." Thesis, University of Skövde, School of Humanities and Informatics, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-3146.
Full textAbstract:
<p>The human brain is always trying to predict ahead in time. Many say that it is possible to take actions only based on internal simulations of the brain. A recent trend in the field of Artificial Intelligence is to provide agents with an “inner world” or internal simulations. This inner world can then be used instead of the real world, making it possible to operate without any inputs from the real world.</p><p>This final year project explores the possibility to navigate collision-free in a dynamic environment, using only internal simulation of sensor input instead of real input. Three scenarios will be presented that show how internal simulation operates in a dynamic environment. The results show that it is possible to navigate entirely based on predictions without a collision.</p>
41
Staberg, Helena. "Multiple and weighted Potential Fields in arena games." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2899.
Full textAbstract:
Potential Fields is an obstacle avoidance and general path-finding technique that has only quite recently started to be used in AI for video games. It has previously mainly been used in robotics for robot navigation. Although quite unexplored, Potential Fields have so far worked well in video games. Previous research has mainly focused on RTS (Real-Time Strategy) games. This research explores the use of Potential Fields in another genre called arena games (which is a quite unexplored genre as well). In the implementation, multiple Potential Fields have been used together, where each field had a different task. Also, weights were used on the different Potential Fields to give them different importance depending on some factors that are dynamic through the game, hence the use of the word weighted. The main focus of the user studies conducted was the impact the weights had on the computer controlled unit's general behaviour. The user studies conducted showed that it was hard to determine who was a computer controlled character and who was human controlled, therefore telling that multiple Potential Fields worked well for movement. The test participants became better at determining this the second match they played, no matter the properties of the match. However, the user studies did not show that the weights made a remarkable difference; there was no significant improvement on the situation adaptation and team cooperation, but no deterioration either. The concept of using weights needs to be explored further.
42
Dobrucki, Mikołaj. "Applications of Artificial Intelligence in Lighting Systems for Home Environments." Thesis, Malmö universitet, Fakulteten för kultur och samhälle (KS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-23548.
Full textAbstract:
Artificial Intelligence, being recently one of the most popular topics in technology, has been in a spotlight of Interaction Design for a long time. Despite its success in software and business-oriented cases, the adoption of Artificial Intelligence solutions in home environments still remains relatively low. This study reflects on the key reasons for the low penetration of AI-based solutions in private households and formulates design considerations for possible further developments in this area with a focus on artificial light sources. The design considerations are based on literature review and studies of multiple home environments gathered through qualitative interviews and context mapping exercises. Health influence of lighting, multi-user interactions, and privacy-related and ethical concerns are taken into account as the key factors. The considerations have been validated with participants of the study through user testing sessions of a digital prototype that virtualises a home environment and explores some of the common light usage scenarios. The study argues that despite multiple efforts in this direction during the past three decades, the future of Artificial Intelligence in connected, intelligent homes does not lie in smart, autonomous systems. Instead, Artificial Intelligence can be arguably used to simplify and contextualise interactions between humans and their home environments as well as foster the development of parametric solutions for private households.
43
Magnusson, Matteus, and Tobias Hall. "Adaptive goal oriented action planning for RTS games." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4361.
Full textAbstract:
This thesis describes the architecture of an adaptive goal-oriented AI system that can be used for Real-Time Strategy games. The system is at the end tested against a single opponent on three different maps with different sizes to test the ability of the AI opposed to the 'standard' Finite State Machines and the likes in Real-Time Strategy games. The system consists of a task handler agent that manages all the active and halted tasks. A task is either low-level; used for ordering units, or high-level that can form advanced strategies. The General forms plans that are most beneficial at the moment. For creating effective units against the opponent a priority system is used; where the unit priorities are calculated dynamically.<br>Den här uppsatsen beskriver en adaptiv målorienterad AI-arkitektur som kan tillämpas på "Real-Time Strategy" spel. Systemet testat mot en annan AI som använder mer traditionella "Finite State Machines" in sin arkitekture. Testet utförs på tre olika banor som är olika stora. Systemet består utav en "Uppgiftshanterare" som har hand om alla aktiva och inaktiva uppgifter. En uppgift kan antingen vara utav låg-nivå, som används för att skicka kommandon till enheterna, eller utav hög-nivå för att göra mer avancerade strategier. Generalen planerar och skapar uppgifter som är mest fördelaktig för tillfället. För att skapa enheter som är effektiva mot fiendens enheter används ett prioritetssystem, där enhetens prioritet kalkyleras ut dynamiskt under spelets gång.
44
Bertrand, Astrid. "Misplaced trust in AI : the explanation paradox and the human-centric path. A characterisation of the cognitive challenges to appropriately trust algorithmic decisions and applications in the financial sector." Electronic Thesis or Diss., Institut polytechnique de Paris, 2024. http://www.theses.fr/2024IPPAT012.
Full textAbstract:
L'IA devenant de plus en plus présente dans nos vies, nous sommes soucieux de comprendrele fonctionnement de ces structures opaques. Pour répondre à cette demande, le domaine de la recherche en explicabilité (XAI) s'est considérablement développé au cours des dernières années. Cependant, peu de travaux ont étudié le besoin en explicabilité des régulateurs ou des consommateurs à la lumière d'exigences légales en matière d'explications. Cette thèse s'attache à comprendre le rôle des explications pour permettre la conformité réglementaire des systèmes améliorés par l'IA dans des applications financières. La première partie passe en revue le défi de prendre en compte les biais cognitifs de l'homme dans les explications des systèmes d'IA. L'analyse fournit plusieurs pistes pour mieux aligner les solutions d'explicabilité sur les processus cognitifs des individus, notamment en concevant des explications plus interactives. Elle présente ensuite une taxonomie des différentes façons d'interagir avec les solutions d'explicabilité. La deuxième partie se concentre sur des contextes financiers précis. Une étude porte sur les systèmes de recommandation et de souscription en ligne de contrats d'assurance-vie. L'étude souligne que les explications présentées dans ce contexte n'améliorent pas de manière significative la compréhension de la recommandation par les utilisateurs non experts. Elles ne suscitent pas davantage la confiance des utilisateurs que si aucune explication n'était fournie. Une autre étude analyse les besoins des régulateurs en matière d'explication dans le cadre de la lutte contre le blanchiment d'argent et le financement du terrorisme. Elle constate que les autorités de contrôle ont besoin d'explications pour établir le caractère répréhensible des cas de défaillance échantillonnés, ou pour vérifier et contester la bonne compréhension de l'IA par les banques<br>As AI is becoming more widespread in our everyday lives, concerns have been raised about comprehending how these opaque structures operate. In response, the research field of explainability (XAI) has developed considerably in recent years. However, little work has studied regulators' need for explainability or considered effects of explanations on users in light of legal requirements for explanations. This thesis focuses on understanding the role of AI explanations to enable regulatory compliance of AI-enhanced systems in financial applications. The first part reviews the challenge of taking into account human cognitive biases in the explanations of AI systems. The analysis provides several directions to better align explainability solutions with people's cognitive processes, including designing more interactive explanations. It then presents a taxonomy of the different ways to interact with explainability solutions. The second part focuses on specific financial contexts. One study takes place in the domain of online recommender systems for life insurance contracts. The study highlights that feature based explanations do not significantly improve non expert users' understanding of the recommendation, nor lead to more appropriate reliance compared to having no explanation at all. Another study analyzes the needs of regulators for explainability in anti-money laundering and financing of terrorism. It finds that supervisors need explanations to establish the reprehensibility of sampled failure cases, or to verify and challenge banks' correct understanding of the AI
45
Uusitalo, Tim. "A first approach in applying Artificial Potential Fields in Car Games." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2480.
Full textAbstract:
In car racing simulation games, finishing first is the main goal. To reach that goal, it is required to go around a racing track, competing against other cars aiming for the same goal. Implementing a bot for doing so may have its difficulties, although using a technique called multi-agent systems combined with artificial potential field, let- ting the agents take care of subtasks like keeping the car on the track, minimize how much the car turns in a curvature and basics in navigation around the track, has showed that artificial potential fields very well fit the problem of driving a car in simulated car racing in a competitive way.<br>Mobiltelefon: 0707422666
46
Viswavarapu, Lokesh Kumar. "Real-Time Finger Spelling American Sign Language Recognition Using Deep Convolutional Neural Networks." Thesis, University of North Texas, 2018. https://digital.library.unt.edu/ark:/67531/metadc1404616/.
Full textAbstract:
This thesis presents design and development of a gesture recognition system to recognize finger spelling American Sign Language hand gestures. We developed this solution using the latest deep learning technique called convolutional neural networks. This system uses blink detection to initiate the recognition process, Convex Hull-based hand segmentation with adaptive skin color filtering to segment hand region, and a convolutional neural network to perform gesture recognition. An ensemble of four convolutional neural networks are trained with a dataset of 25254 images for gesture recognition and a feedback unit called head pose estimation is implemented to validate the correctness of predicted gestures. This entire system was developed using Python programming language and other supporting libraries like OpenCV, Tensor flow and Dlib to perform various image processing and machine learning tasks. This entire application can be deployed as a web application using Flask to make it operating system independent.
47
Erhard, Annalena. "The Cost of Algorithmic decisions : A Systematic Literature Review." Thesis, Luleå tekniska universitet, Institutionen för system- och rymdteknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-85526.
Full textAbstract:
Decisions have been automated since the early days. Ever since the rise of AI, ML and DataAnalytics, algorithmic decision-making has experienced a boom time. Nowadays, using AI withina company is said to be critical to the success of a company. Considering the point that it can bequite costly to develop AI/ ML and integrating it into decision-making, it is striking how littleresearch was put into the identification and analysis of its cost drivers by now. This thesis is acontribution to raise and the awareness of possible cost drivers to algorithmic decisions. Thetopic was divided in two subgroups. That is solely algorithms and hybrid decision-making. Asystematic literature review was conducted to create a theoretical base for further research. Thecost drivers for algorithms to make decisions without human interaction, the identified costdrivers identified can be found at Data Storage (including initial, floor rent, energy, service,disposal, and environmental costs), Data Processing, Transferring and Migrating. Additionally,social costs and the ones related to fairness as well as the ones related to algorithms themselves(Implementation and Design, Execution and Maintenance) could be found. Business Intelligenceused for decision making raises costs in Data quality, Update delays of cloud systems, Personneland Personnel training, Hardware, Software, Maintenance and Data Storage. Moreover, it isimportant to say that the recurrence of some costs was detected. Further research should go inthe direction of applicability of the theoretical costs in practice.
48
Yannakakis, Georgios N. "AI in computer games : generating interesting interactive opponents by the use of evolutionary computation." Thesis, University of Edinburgh, 2005. http://hdl.handle.net/1842/879.
Full textAbstract:
Which features of a computer game contribute to the player’s enjoyment of it? How can we automatically generate interesting and satisfying playing experiences for a given game? These are the two key questions addressed in this dissertation. Player satisfaction in computer games depends on a variety of factors; here the focus is on the contribution of the behaviour and strategy of game opponents in predator/prey games. A quantitative metric of the ‘interestingness’ of opponent behaviours is defined based on qualitative considerations of what is enjoyable in such games, and a mathematical formulation grounded in observable data is derived. Using this metric, neural-network opponent controllers are evolved for dynamic game environments where limited inter-agent communication is used to drive spatial coordination of opponent teams. Given the complexity of the predator task, cooperative team behaviours are investigated. Initial candidates are generated using off-line learning procedures operating on minimal neural controllers with the aim of maximising opponent performance. These example controllers are then adapted using on-line (i.e. during play) learning techniques to yield opponents that provide games of high interest. The on-line learning methodology is evaluated using two dissimilar predator/prey games with a number of different computer player strategies. It exhibits generality across the two game test-beds and robustness to changes of player, initial opponent controller selected, and complexity of the game field. The interest metric is also evaluated by comparison with human judgement of game satisfaction in an experimental survey. A statistically significant number of players were asked to rank game experiences with a test-bed game using perceived interestingness and their ranking was compared with that of the proposed interest metric. The results show that the interest metric is consistent with human judgement of game satisfaction. Finally, the generality, limitations and potential of the proposed methodology and techniques are discussed, and other factors affecting the player’s satisfaction, such as the player’s own strategy, are briefly considered. Future directions building on the work described herein are presented and discussed.
49
Firdaus. "Interactions H-AI-P dans la rhizosphère du mai͏̈s en sols acides tropicaux." Montpellier, ENSA, 2001. http://www.theses.fr/2001ENSA0013.
Full text
50
Rosén, Carl-Johan. "An AI Engine for Behavioural Animation in a Real Time Interactive Installation." Thesis, Linköpings universitet, Institutionen för teknik och naturvetenskap, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-96247.
Full textAbstract:
This thesis presents the implementation of the AI model and the behaviors of the interactive art installation and guidance system Source.Code developed by Ars Electronica Futurelab. The AI model is built on a hybrid control system with a rule hierarchy tree describing the intelligent characters of the installation. This thesis describes the entire real time AI model implementation from the decision model down to the navigation system and the collision detection. The thesis also positions the AI part of Source.Code in an interactive storytelling context.