Avec le développement de la robotique cognitive, le besoin d’outils avancés pour représenter, manipuler, raisonner sur les connaissances acquises par un robot a clairement été mis en avant. Mais stocker et manipuler des connaissances requiert tout d’abord d’éclaircir ce que l’on nomme connaissance pour un robot, et comment celle-ci peut-elle être représentée de manière intelligible pour une machine. Ce travail s’efforce dans un premier temps d’identifier de manière systématique les besoins en terme de représentation de connaissance des applications robotiques modernes, dans le contexte spécifique de la robotique de service et des interactions homme-robot. Nous proposons une typologie originale des caractéristiques souhaitables des systèmes de représentation des connaissances, appuyée sur un état de l’art détaillé des outils existants dans notre communauté. Dans un second temps, nous présentons en profondeur ORO, une instanciation particulière d’un système de représentation et manipulation des connaissances, conçu et implémenté durant la préparation de cette thèse. Nous détaillons le fonctionnement interne du système, ainsi que son intégration dans plusieurs architectures robotiques complètes. Un éclairage particulier est donné sur la modélisation de la prise de perspective dans le contexte de l’interaction, et de son interprétation en terme de théorie de l’esprit. La troisième partie de l’étude porte sur une application importante des systèmes de représentation des connaissances dans ce contexte de l’interaction homme-robot : le traitement du dialogue situé. Notre approche et les algorithmes qui amènent à l’ancrage interactif de la communication verbale non contrainte sont présentés, suivis de plusieurs expériences menées au Laboratoire d’Analyse et d’Architecture des Systèmes au CNRS à Toulouse, et au groupe Intelligent Autonomous System de l’université technique de Munich. Nous concluons cette thèse sur un certain nombre de considérations sur la viabilité et l’importance d’une gestion explicite des connaissances des agents, ainsi que par une réflexion sur les éléments encore manquant pour réaliser le programme d’une robotique “de niveau humain” / With the rise of the so-called cognitive robotics, the need of advanced tools to store, manipulate, reason about the knowledge acquired by the robot has been made clear. But storing and manipulating knowledge requires first to understand what the knowledge itself means to the robot and how to represent it in a machine-processable way. This work strives first at providing a systematic study of the knowledge requirements of modern robotic applications in the context of service robotics and human-robot interaction. What are the expressiveness requirement for a robot? what are its needs in term of reasoning techniques? what are the requirement on the robot's knowledge processing structure induced by other cognitive functions like perception or decision making? We propose a novel typology of desirable features for knowledge representation systems supported by an extensive review of existing tools in our community. In a second part, the thesis presents in depth a particular instantiation of a knowledge representation and manipulation system called ORO, that has been designed and implemented during the preparation of the thesis. We elaborate on the inner working of this system, as well as its integration into several complete robot control stacks. A particular focus is given to the modelling of agent-dependent symbolic perspectives and their relations to theories of mind. The third part of the study is focused on the presentation of one important application of knowledge representation systems in the human-robot interaction context: situated dialogue. Our approach and associated algorithms leading to the interactive grounding of unconstrained verbal communication are presented, followed by several experiments that have taken place both at the Laboratoire d'Analyse et d'Architecture des Systèmes at CNRS, Toulouse and at the Intelligent Autonomous System group at Munich Technical University. The thesis concludes on considerations regarding the viability and importance of an explicit management of the agent's knowledge, along with a reflection on the missing bricks in our research community on the way towards "human level robots"

<div>The widespread and growing usage of machine learning models, especially in highly critical areas such as law, predicate the need for interpretable models. Models that cannot be audited are vulnerable to inheriting biases from the dataset. Even locally interpretable models are vulnerable to adversarial attack. To address this issue a new methodology is proposed to translate any existing machine learning model into a globally interpretable one.</div><div>This methodology, MTRE-PAN, is designed as a hybrid SVM-decision tree model and leverages the interpretability of linear hyperplanes. MTRE-PAN uses this hybrid model to create polygons that act as intermediates for the decision boundary. MTRE-PAN is compared to a previously proposed model, TRE-PAN, on three non-synthetic datasets: Abalone, Census and Diabetes data. TRE-PAN translates a machine learning model to a 2-3 decision tree in</div><div>order to provide global interpretability for the target model. The datasets are each used to train a Neural Network that represents the non-interpretable model. For all target models, the results show that MTRE-PAN generates interpretable decision trees that have a lower</div><div>number of leaves and higher parity compared to TRE-PAN.</div>

Beschreibungslogiken (Description logics, DLs) sind eine Klasse von Wissensrepraesentationsformalismen mit wohldefinierter, logik-basierter Semantik und entscheidbaren Schlussfolgerungsproblemen, wie z.B. dem Erfuellbarkeitsproblem. Zwei wichtige Entscheidungsverfahren fuer das Erfuellbarkeitsproblem von DL-Ausdruecken sind Tableau- und Automaten-basierte Algorithmen. Diese haben aufgrund ihrer unterschiedlichen Arbeitsweise komplementaere Eigenschaften: Tableau-Algorithmen eignen sich fuer Implementierungen und fuer den Nachweis von PSPACE- und NEXPTIME-Resultaten, waehrend Automaten sich besonders fuer EXPTIME-Resultate anbieten. Zudem ermoeglichen sie eine vom Standpunkt der Theorie aus elegantere Handhabung von unendlichen Strukturen, eignen sich aber wesentlich schlechter fuer eine Implementierung. Ziel der Dissertation ist es, die Gruende fuer diese Unterschiede zu analysieren und Moeglichkeiten aufzuzeigen, wie Eigenschaften von einem Ansatz auf den anderen uebertragen werden koennen, um so die positiven Eigenschaften von beiden Ansaetzen miteinander zu verbinden. Unter Anderem werden Methoden entwickelt, mit Hilfe von Automaten PSPACE-Resultate zu zeigen, und von einem Tableau-Algorithmus automatisch ein EXPTIME-Resultat abzuleiten. / Description Logics (DLs) are a family of knowledge representation languages with well-defined logic-based semantics and decidable inference problems, e.g. satisfiability. Two of the most widely used decision procedures for the satisfiability problem are tableau- and automata-based algorithms. Due to their different operation, these two classes have complementary properties: tableau algorithms are well-suited for implementation and for showing PSPACE and NEXPTIME complexity results, whereas automata algorithms are particularly useful for showing EXPTIME results. Additionally, they allow for an elegant handling of infinite structures, but they are not suited for implementation. The aim of this thesis is to analyse the reasons for these differences and to find ways of transferring properties between the two approaches in order to reconcile the positive properties of both. For this purpose, we develop methods that enable us to show PSPACE results with the help of automata and to automatically derive an EXPTIME result from a tableau algorithm.

In previous work, we have investigated privacy-preserving publishing of Description Logic (DL) ontologies in a setting where the knowledge about individuals to be published is an EL instance store, and both the privacy policy and the possible background knowledge of an attacker are represented by concepts of the DL EL. We have introduced the notions of compliance of a concept with a policy and of safety of a concept for a policy, and have shown how, in the context mentioned above, optimal compliant (safe) generalizations of a given EL concept can be computed. In the present paper, we consider a modified setting where we assume that the background knowledge of the attacker is given by a DL different from the one in which the knowledge to be published and the safety policies are formulated. In particular, we investigate the situations where the attacker’s knowledge is given by an FL0 or an FLE concept. In both cases, we show how optimal safe generalizations can be computed. Whereas the complexity of this computation is the same (ExpTime) as in our previous results for the case of FL0, it turns out to be actually lower (polynomial) for the more expressive DL FLE.

<p> The dramatic improvement in information and communication technology (ICT) has made an evolution in learning management systems (LMS). The rapid growth in LMSs has caused users to demand more advanced, automated, and intelligent services. CourseNetworking is a next-generation LMS adopting machine learning to add personalization, gamification, and more dynamics to the system. This work tries to come up with two recommender systems that can help improve CourseNetworking services. The first one is a social recommender system helping CourseNetworking to track user interests and give more relevant recommendations. Recently, graph neural network (GNN) techniques have been employed in social recommender systems due to their high success in graph representation learning, including social network graphs. Despite the rapid advances in recommender systems performance, dealing with the dynamic property of the social network data is one of the key challenges that is remained to be addressed. In this research, a novel method is presented that provides social recommendations by incorporating the dynamic property of social network data in a heterogeneous graph by supplementing the graph with time span nodes that are used to define users long-term and short-term preferences over time. The second service that is proposed to add to Rumi services is a hashtag recommendation system that can help users label their posts quickly resulting in improved searchability of content. In recent years, several hashtag recommendation methods are proposed and developed to speed up processing of the texts and quickly find out the critical phrases. The methods use different approaches and techniques to obtain critical information from a large amount of data. This work investigates the efficiency of unsupervised keyword extraction methods for hashtag recommendation and recommends the one with the best performance to use in a hashtag recommender system. </p>

Modern science is turning to progressively more complex and data-rich subjects, which challenges the existing methods of data analysis and interpretation. Consequently, there is a pressing need for development of ever more powerful methods of extracting order from complex data and for automation of all steps of the scientific process. Virtual Scientist is a set of computational procedures that automate the method of inductive inference to derive a theory from observational data dominated by nonlinear regularities. The procedures utilize SINBAD – a novel computational method of nonlinear factor analysis that is based on the principle of maximization of mutual information among non-overlapping sources (Imax), yielding higherorder features of the data that reveal hidden causal factors controlling the observed phenomena. One major advantage of this approach is that it is not dependent on a particular choice of learning algorithm to use for the computations. The procedures build a theory of the studied subject by finding inferentially useful hidden factors, learning interdependencies among its variables, reconstructing its functional organization, and describing it by a concise graph of inferential relations among its variables. The graph is a quantitative model of the studied subject, capable of performing elaborate deductive inferences and explaining behaviors of the observed variables by behaviors of other such variables and discovered hidden factors. The set of Virtual Scientist procedures is a powerful analytical and theory-building tool designed to be used in research of complex scientific problems characterized by multivariate and nonlinear relations.

Many applications of neural linguistic models rely on their use as pre-trained features for downstream tasks such as dialog modeling, machine translation, and question answering. This work presents an alternate paradigm: Rather than treating linguistic embeddings as input features, we treat them as common sense knowledge repositories that can be queried using simple mathematical operations within the embedding space, without the need for additional training. Because current state-of-the-art embedding models were not optimized for this purpose, this work presents a novel embedding model designed and trained specifically for the purpose of "reasoning in the linguistic domain".Our model jointly represents single words, multi-word phrases, and complex sentences in a unified embedding space. To facilitate common-sense reasoning beyond straightforward semantic associations, the embeddings produced by our model exhibit carefully curated properties including analogical coherence and polarity displacement. In other words, rather than training the model on a smorgaspord of tasks and hoping that the resulting embeddings will serve our purposes, we have instead crafted training tasks and placed constraints on the system that are explicitly designed to induce the properties we seek. The resulting embeddings perform competitively on the SemEval 2013 benchmark and outperform state-of- the-art models on two key semantic discernment tasks introduced in Chapter 8.The ultimate goal of this research is to empower agents to reason about low level behaviors in order to fulfill abstract natural language instructions in an autonomous fashion. An agent equipped with an embedding space of sucient caliber could potentially reason about new situations based on their similarity to past experience, facilitating knowledge transfer and one-shot learning. As our embedding model continues to improve, we hope to see these and other abilities become a reality.

[ES] La monitorización de la ejecución de un plan es crucial para un agente autónomo que realiza su labor en un entorno dinámico, pues influye en su capacidad de reaccionar ante los cambios. Mientras ejecuta su plan puede sufrir un fallo y, en su esfuerzo por solucionarlo, puede interferir sin saberlo con otros agentes que operan en su mismo entorno. Por otra parte, para actuar racionalmente es necesario que el agente sea consciente del contexto y pueda recopilar y ampliar su información a partir de lo que percibe para poder compensar su conocimiento previo parcial o incorrecto del problema y lograr el mejor resultado posible ante las nuevas situaciones que aparecen. El trabajo realizado en esta tesis permite a los agentes autónomos ejecutar sus planes en un entorno dinámico y adaptarse a eventos inesperados y circunstancias desconocidas. Pueden utilizar su percepción del contexto para proporcionar respuestas deliberativas conscientes y ser capaces así de aprovechar las oportunidades que surgen o reparar los fallos sin perturbar a otros agentes. Este trabajo se centra en el desarrollo de una arquitectura independiente del dominio capaz de manejar las necesidades de agentes con este tipo de comportamiento autónomo. Los tres pilares de la arquitectura propuesta los forman el sistema inteligente para la simulación de la ejecución en entornos dinámicos, la adquisición de conocimiento consciente del contexto para ampliar la base de datos del agente y la reparación de planes ante fallos u oportunidades tratando de interferir lo mínimo con los planes de otros agentes. El sistema inteligente de simulación de la ejecución permite al agente representar el plan en una línea de tiempo, actualizar periódicamente su estado interno con información del mundo real y disparar nuevos eventos en momentos concretos. Los eventos se procesan en el contexto del plan; si se detecta un error, el simulador reformula el problema de planificación, invoca de nuevo al planificador y reanuda la ejecución. El simulador es una aplicación de consola y ofrece una interfaz gráfica diseñada específicamente para una aplicación inteligente de turismo. El módulo de adquisición de conocimiento sensible al contexto utiliza operaciones semánticas para aumentar dinámicamente la lista predefinida de tipos de objetos de la tarea de planificación con nuevos tipos relevantes. Esto permite que el agente sea consciente de su entorno, enriquezca el modelo de su tarea y pueda razonar a partir de un conocimiento incompleto. Con todo esto se consigue potenciar la autonomía del sistema y la conciencia del contexto. La novedosa estrategia de reparación de planes le permite a un agente reparar su plan al detectar un fallo de manera responsable con el resto de agentes que comparten su mismo entorno de ejecución. El agente utiliza una nueva métrica, el compromiso del plan, como función heurística para guiar la búsqueda hacia un plan solución comprometido con el plan original, en el sentido de que se trata de respetar los compromisos adquiridos con otros agentes al mismo tiempo que se alcanzan los objetivos originales. En consecuencia, la comunidad de agentes sufrirá menos fallos por cambios bruscos en el entorno o requerirá menos tiempo para ejecutar las acciones correctoras si el fallo es inevitable. Estos tres módulos han sido desarrollados y evaluados en varias aplicaciones como un asistente turístico, una agencia de reparación de electrodomésticos y un asistente del hogar. / [CA] El monitoratge de l'execució d'un pla és crucial per a un agent autònom que realitza la seua labor en un entorn dinàmic, perquè influeix en la seua capacitat de reaccionar davant els canvis. Mentre executa el seu pla pot patir una fallada i, en el seu esforç per solucionar-lo, pot interferir sense saber-ho amb altres agents que operen en el seu mateix entorn. D'altra banda, per a actuar racionalment és necessari que l'agent siga conscient del context i puga recopilar i ampliar la seua informació a partir del que percep per a poder compensar el seu coneixement previ parcial o incorrecte del problema i aconseguir el millor resultat possible davant les noves situacions que apareixen. El treball realitzat en aquesta tesi permet als agents autònoms executar els seus plans en un entorn dinàmic i adaptar-se a esdeveniments inesperats i circumstàncies desconegudes. Poden utilitzar la seua percepció del context per a proporcionar respostes deliberatives conscients i ser capaces així d'aprofitar les oportunitats que sorgeixen o reparar les fallades sense pertorbar a altres agents. Aquest treball se centra en el desenvolupament d'una arquitectura independent del domini capaç de manejar les necessitats d'agents amb aquesta mena de comportament autònom. Els tres pilars de l'arquitectura proposada els formen el sistema intel·ligent per a la simulació de l'execució en entorns dinàmics, l'adquisició de coneixement conscient del context per a ampliar la base de dades de l'agent i la reparació de plans davant fallades o oportunitats tractant d'interferir el mínim amb els plans d'altres agents. El sistema intel·ligent de simulació de l'execució permet a l'agent representar el pla en una línia de temps, actualitzar periòdicament el seu estat intern amb informació del món real i disparar nous esdeveniments en moments concrets. Els esdeveniments es processen en el context del pla; si es detecta un error, el simulador reformula el problema de planificació, invoca de nou al planificador i reprén l'execució. El simulador és una aplicació de consola i ofereix una interfície gràfica dissenyada específicament per a una aplicació intel·ligent de turisme. El mòdul d'adquisició de coneixement sensible al context utilitza operacions semàntiques per a augmentar dinàmicament la llista predefinida de tipus d'objectes de la tasca de planificació amb nous tipus rellevants. Això permet que l'agent siga conscient del seu entorn, enriquisca el model de la seua tasca i puga raonar a partir d'un coneixement incomplet. Amb tot això s'aconsegueix potenciar l'autonomia del sistema i la consciència del context. La nova estratègia de reparació de plans li permet a un agent reparar el seu pla en detectar una fallada de manera responsable amb la resta d'agents que comparteixen el seu mateix entorn d'execució. L'agent utilitza una nova mètrica, el compromís del pla, com a funció heurística per a guiar la cerca cap a un pla solució compromés amb el pla original, en el sentit que es tracta de respectar els compromisos adquirits amb altres agents al mateix temps que s'aconsegueixen els objectius originals. En conseqüència, la comunitat d'agents patirà menys fallades per canvis bruscos en l'entorn o requerirà menys temps per a executar les accions correctores si la fallada és inevitable. Aquests tres mòduls han sigut desenvolupats i avaluats en diverses aplicacions com un assistent turístic, una agència de reparació d'electrodomèstics i un assistent de la llar. / [EN] Execution Monitoring is crucial for the success of an autonomous agent executing a plan in a dynamic environment as it influences its ability to react to changes. While executing its plan in a dynamic world, it may suffer a failure and, in its endeavour to fix the problem, it may unknowingly disrupt other agents operating in the same environment. Additionally, being rational requires the agent to be context-aware, gather information and extend what is known from what is perceived to compensate for partial or incorrect prior knowledge and achieve the best possible outcome in various novel situations. The work carried out in this PhD thesis allows the autonomous agents executing a plan in a dynamic environment to adapt to unexpected events and unfamiliar circumstances, utilise their perception of context and provide context-aware deliberative responses for seizing an opportunity or repairing a failure without disrupting other agents. This work is focused on developing a domain-independent architecture capable of handling the requirements of such autonomous behaviour. The architecture pillars are the intelligent system for execution simulation in a dynamic environment, the context-aware knowledge acquisition for planning applications and the plan commitment repair. The intelligent system for execution simulation in a dynamic environment allows the agent to transform the plan into a timeline, periodically update its internal state with real-world information and create timed events. Events are processed in the context of the plan; if a failure occurs, the simulator reformulates the planning problem, reinvokes a planner and resumes the execution. The simulator is a console application and has a GUI designed specifically for smart tourism. The context-aware knowledge acquisition module utilises semantic operations to dynamically augment the predefined list of object types of the planning task with relevant new object types. This allows the agent to be context-aware of the environment and the task and reason with incomplete knowledge, boosting the system's autonomy and context-awareness. The novel plan commitment repair strategy among multiple agents sharing the same execution environment allows the agent to repair its plan responsibly when a failure is detected. The agent utilises a new metric, plan commitment, as a heuristic to guide the search for the most committed repair plan to the original plan from the perspective of commitments made to other agents whilst achieving the original goals. Consequently, the community of agents will suffer fewer failures due to the sudden changes or will have less lost time if the failure is inevitable. All these developed modules were investigated and evaluated in several applications, such as a tourist assistant, a kitchen appliance repair agency and a living home assistant. / Babli, M. (2023). Context-aware Plan Repair in Environments shared by Multiple Agents [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/198683

One group of games studied within game theory are grid-based pursuit evasion games of imperfect information. A pursuit evasion game is in essence a game where there exists a set of pursuers which have as their objective to capture a set of evaders. This thesis aims to develop a formalisation of this type of games as well as describing and integrating vital game theoretical concepts such as order of knowledge into this game. With the developed formalism at hand, the concept of knowledge-based strategies is then introduced, which is essential when searching for the way to play the game most efficiently. The formalisation of the game is then followed by a simulation, measuring the performance of some older and some newly developed knowledge-based strategies. The thesis concludes that the formalisation is applicable on a more general class of pursuit evasion games and enables a wider study of the game. The simulation results indicate that knowledge-based strategies of higher order do not always perform better compared to simpler strategies of lower order of knowledge. Furthermore, strategies which allow for communication between agents are found to be superior to communication-less strategies. / En typ av spel som studeras inom spelteori är rutnätsbaserade jakt-flykt-spel med ofullständig information. Ett jakt-flykt-spel går ut på att det existerar en samling jagande aktörer som försöker fånga en samling flyende aktörer. Denna uppsats söker utveckla en formalism för denna typ av spel såväl som att beskriva och integrera ett antal nyckelkoncept inom spelteori såsom kunskapsordning. Med hjälp av den utvecklade formalismen, framställs så kallade kunskapsbaserade strategier, vilka är av fundamental vikt i sökandet efter sätt att spela spelet på det effektivaste sättet. Kapitlet om formalismen följs sedan av simuleringar där några äldre och några nyare kunskapsbaserade strategier prövas. Slutsatsen dras att den nya formalismen kan vara applicerbar på en bredare samling jakt-flykt-spel än den initialt påtänkta. Vidare underlättar formalismen en generalisering till andra sätt att beskriva spel. Simulationsresultaten indikerar att kunskapsbaserade strategier av högre ordning inte alltid presterar bättre än enklare strategier av lägre ordning. Till yttermera visso visar sig kommunikationslösa strategier vara underlägsna strategier som tillåter kommunikation. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

Argumentation framework is a common technique in Artificial Intelligence and related fields. It is a good way of formalizing, resolving conflicts and helping with defeasible reasoning. This thesis discusses the exploration of the quantitative bipolar argumentation framework applied in multi-agent systems. Different agents in a multi-agent systems have various capabilities, and they contribute in different ways to the system goal. The purpose of this study is to explore approaches of explaining the overall behavior and output from a multi-agent system and enable explainability in the multi-agent systems. By exploring the properties of the quantitative bipolar argumentation framework using some techniques from explainable Artificial Intelligence (AI), the system will generate output with explanations given by the argumentation framework. This thesis gives a general overview of argumentation frameworks and common techniques from explainable AI. The study mainly focuses on the exploration of properties and interactive algorithms of quantitative bipolar argumentation framework. It introduces explanation techniques to the quantitative bipolar argumentation framework. A Graphical User Interface (GUI) application is included in order to present the results of the explanation. / Argumentationsramar är en vanlig teknik inom artificiell intelligens och relaterade områden. Det är ett bra sätt att formalisera, lösa konflikter och hjälpa till med defekta resonemang. I den här avhandlingen diskuteras utforskningen av den kvantitativa bipolära argumentationsramen som tillämpas i fleragentsystem. Olika agenter i ett system med flera agenter har olika kapacitet och bidrar på olika sätt till systemets mål. Syftet med den här studien är att utforska metoder för att förklara det övergripande beteendet och resultatet från ett system med flera agenter och möjliggöra förklarbarhet i systemen med flera agenter. Genom att utforska egenskaperna hos den kvantitativa bipolära argumentationsramen med hjälp av vissa tekniker från förklaringsbara AI kommer systemet att generera utdata med förklaringar som ges av argumentationsramen. Denna avhandling ger en allmän översikt över argumentationsramar och vanliga tekniker från förklaringsbara AI. Studien fokuserar främst på utforskandet av egenskaper och interaktiva algoritmer för det kvantitativa bipolära argumentationsramverket och introducerar tillämpningen av förklaringstekniker på det kvantitativa bipolära argumentationsramverket. En GUI-applikation ingår för att presentera resultaten av förklaringen.