With Home Virtual Assistant (HVA) becoming popular, it has entered many families. This study aims to understand how novice users explore the capabilities of HVAs and the factors influence the users’ discovery process. The researcher used a study inspired by diary study, combining survey and interview to collect the data, along with dialogue history that contains all the activities between the user and the device. The results reveal the activities the users engage in and the factors of the HVA device and the users that influence the discovery process. Three themes emerged from the data, they are: the activities participant engaged to learn the capabilities of Echo Dot, the influence of Echo Dot being screen-less and factors of participants that influenced the initial use. Based on the results, the researcher discusses the current issues of the Echo Dot’s design and suggests potential improvement for the HVAs.

"As artificially intelligent agents become more advanced, they will require corresponding advances in social capability. In particular, they will require an understanding of the development of relationships. This work is intended to aid in addressing this need. We have developed a model of the development of relationships, designed and implemented a planning module based on this model, and performed an evaluation study verifying the functionality of the model and implementation. This should provide a foundation for future work in developing artificially intelligent agents capable of appropriately dealing with the development of social relationships."

<p>This report proposes a modular Application Programmer's Interface (API) for handling the mental layer of intelligent virtual agents for a wide range of application types, with the aim of reducing the work required to program a completely new AI engine, and describes its implementation. One of the key elements and major difficulties in its design is the need to make it general enough to suit most types of applications, while preserving its usefulness and keeping it both efficient and reliable. A sample application interfacing with the API is created to demonstrate its capabilities, various AI algorithms are looked into and their respective suitability for the API is evaluated, and some techniques are implemented as modules in the API.</p>

To help online trip planners, some online travel agencies and travel service providers have adopted travel recommender systems. Although these systems are expected to support travelers in complex decision-making processes, they are not used efficiently by travelers due to a lack of confidence in the recommendations they provide. It is important to examine factors that can influence the likelihood of recommendations to be accepted and integrated into decision-making processes. The persuasion literature suggests that people are more likely to accept recommendations from credible and likable sources. It has also been found that technologies can be more credible and likable when they give a variety of social cues that elicit social responses from their human users. Thus, it is argued that enhancing the social aspects of travel recommender systems is important to create more persuasive systems. One approach to enhancing the social presence of recommender systems is to use a virtual agent. Current travel recommender systems use various types of virtual agents. However, it is still not clear how those virtual agents are perceived by travel recommender system users and influence users' system evaluations and interactions with these systems. Consequently, this dissertation aimed to investigate the influence of virtual agents presented in travel recommender systems on system users' perceptions. Specifically, the virtual agents' anthropomorphism as well as similarity and authority cues on system users' perceptions of system credibility and liking were examined. For this purpose, two experiments were conducted. For Study 1, the impacts of anthropomorphism of the virtual agents on users' perceptions of virtual agents as well as recommender systems in terms of credibility and attractiveness/liking were examined. Anthropomorphism was manipulated with visual human appearance and voice output. Study 2 tested the influence of virtual agents? similarity and authority on travel recommender system users' perceptions of virtual agents and system credibility and attractiveness/liking. Similarity and authority of the virtual agent were tested by manipulating nonverbal cues (age and outfit) of the agent. The results showed that the characteristics of virtual agents have some influences on system users' perceptions of virtual agents as well as recommender systems. Specifically, a human-like appearance of the virtual agent is found to positively influence users' perceived attractiveness of the virtual agent while voice outputs were found to enhance users' liking of the system (Study 1). Findings also indicate that RS users' perceptions of virtual agent expertise are increased when virtual agents wear a uniform rather than a casual outfit (Study 2). In addition, system users' perceptions of the virtual agent's credibility are found to have a significant influence on users' perceived credibility and liking of the overall system, which implies an important role of virtual agents in recommender system evaluations. Further, perceived credibility and liking of recommender systems lead to favorable evaluations of the recommendations, which, in turn, increase users' intentions to travel to the recommended destination. Past travel recommender system studies have largely neglected the social role of recommender systems as advice givers. Also, it is not clear whether the specific characteristics of virtual agents presented as a part of the system interface influence system users' perceptions. This dissertation sought to close this knowledge gap. By applying classic interpersonal communication theories to human and system relationships, this dissertation expands the scope of traditional theories used in the context of studying recommender systems. Further, the results of the research presented in this dissertation provide insights for tourism marketing as well as practical implications for travel recommender system design.

One of the fundamental aspects of a virtual environment is the virtual agents that inhabit them. In many applications, virtual agents are required to perceive input information from their environment and make decisions appropriate to their task based on their programmed reaction to those inputs. The research presented in this thesis focuses on the reactive behaviour of the agents. We propose a new control architecture to allow agents to behave autonomously in navigation tasks in unknown environments. Our behaviour-based architecture uses fuzzy logic to solve problems of agent control and action selection and which can coordinate conflicts among different operations of reactive behaviours. A Fuzzy Associative Memory (FAM) is used as the process of encoding and mapping the input fuzzy sets to the output fuzzy set and to optimise the fuzzy rules. Our action selection algorithm is based on the fuzzy α-level method with the Hurwicz criterion. The main objective of the thesis was to implement agent navigation from point to point by a coordination of planning, sensing and control. However, we believe that the reactive architecture emerging from this research is sufficiently general that it could be applied to many applications in widely differing domains where real-time decision making under uncertainty is required. To illustrate this generality, we show how the architecture is applied to a different domain. We chose the example of a computer game since it clearly demonstrates the attributes of our architecture: real-time action selection and handling uncertainty. Experimental results are presented for both implementations which show how the fuzzy method is applied, its generality and that it is robust enough to handle different uncertainties in different environments. In summary, the proposed reactive architecture is shown to solve aspects of behaviour control for autonomous virtual agents in virtual environments and can be applied to various application domains.

This report proposes a modular Application Programmer's Interface (API) for handling the mental layer of intelligent virtual agents for a wide range of application types, with the aim of reducing the work required to program a completely new AI engine, and describes its implementation. One of the key elements and major difficulties in its design is the need to make it general enough to suit most types of applications, while preserving its usefulness and keeping it both efficient and reliable. A sample application interfacing with the API is created to demonstrate its capabilities, various AI algorithms are looked into and their respective suitability for the API is evaluated, and some techniques are implemented as modules in the API.

Les recherches menées par le travail de thèse visent à proposer une nouvelle architecture multi-agent pour la conception d’applications sur de nouvelles plateformes de communication telles que les tables interactives. Les systèmes Multi-Agents sont utilisés depuis de nombreuses années et peuvent répondre aux problématiques de telles plateformes. Dans notre contexte, nous avons défini les interactions et les comportements d’agents hétérogènes (virtuels et tangibles), qui évoluent simultanément sur une même surface interactive.Nous avons défini une typologie des agents, utilisés dans le cadre de plateformes interactives, en fonction d’un ensemble de critères permettant d’analyser les caractéristiques logicielles et technologiques (système de capture, affichage, etc.) employées sur ces nouveaux supports. Nous proposons de modéliser les comportements élémentaires nécessaires à la description du problème (interactions éventuelles de plusieurs utilisateurs, utilisation d’objets, visualisation de l’environnement et des agents simulés, traitement des messageséchangés, etc.), lesquels sont représentés par des rôles joués simultanément par un ou plusieurs agents selon un ensemble de prérequis. La réflexion proposée a conduit à la construction d’une architecture multi-agent, laquelle a été appliquée sur la table interactive TangiSense (intégrant une technologie RFID). Nous illustrons et nous validons notre propos à l’aide d’une application, un simulateur de trafic routier. / Research done in this thesis aims to propose a new multiagent architecture to design applications for the new communication platforms like the interactive tables. Multiagent systems are used for many years and can respond to the challenges of such platforms. The motivation of our work is to manage the interactions and the behavior of several heterogeneous entities (virtual and tangible) evolving simultaneously on a single interactive surface. We caracterized the agents typology and their interactions for interactive platforms.We consider a set of criteria to analyze software and technological (e.g. capture system, display, etc.) characteristics used on these new platforms. We proposed to modelize basic behaviors needed to describe the problem (potential interactions between multiple users, tangible objects use, visualization of the environment and simulated agents, treatment of exchanged messages, etc.), which are represented by roles played simultaneously by one or several agents according to a set of prerequisites. With these elements, we propose to apply our multiagent architecture on the interactive table TangiSense (equipped with RFID technology). We illustrate and validate our purpose with an application, a traffic simulator.

Goal of the work is to improve the SPOSH planner and its developement tools. SPOSH is a reactive planner of virtual agents similar to behavior trees that is used in the Pogamut platform, which is used to develop virtual agents. SPOSH itself suffers from several problems, especially excessive duplication of primitives (actions and senses) in different agents and unnatural execution of primitives. This work aims to remove these problems. Nearly all behavior tree planners are not public and developement tools are not usually available. Absence of such tools, especially of debugger, is major problem for users. Part of this work are tools for easy creation and debugging of SPOSH plans. Improved planner and created tools are demonstrated using an agent in game Unreal Tournament 2004.

The requirements for virtual agents are more and more demanding. In order to manage the complex behavior of the agent, it's possible to take advantage of cognitive architectures which arised on the field neuroscience and artificial intelligence. This work examines PoJACTR library which links Pogamut library for developing intelligent agents in Unreal Tournament 2004 and jACT-R library which is Java implementation of one of the leading cognitive architectures ACTR. This work also studies certain agent implementation problems in PoJACTR and proposes a solution for them in form of debugging tools, which were subsequently implemented on an Eclipse IDE platform. In addition, it expands PoJACTR navigation and communication library modules for the game - Capture The Flag. As a validation, two agents (bots) were developed to play game, one in standard Pogamut and one in PoJACTR. When matched against each other in battle, Po- JACTR bot had comparable performance to a Pogamut bot. The results showed that debugging tools facilitated development process of PoJACTR agents.

Development of intelligent virtual agents is a complex task. One of the im- portant sub-tasks is creation of behaviors. It is highly desirable to test behaviors of intelligent virtual agents in an actual virtual world, not in a simplified sub- stitute. Over the past several years the Pogamut platform has been developed, which allows intelligent virtual agent behaviors to be tested in several gaming worlds, but none combines complexity, dynamicity and extensibility. It was de- cided to fill the gap by creating the EmohawkVille virtual world. EmohawkVille is a first-person virtual world in a day-to-day life setting. The purpose of this thesis is to explain why is EmohawkVille needed and to document features, de- sign and development of EmohawkVille and its Pogamut module. The thesis also presents results of a case study that confirms the EmohawkVille's suitability for experiments concerning intelligent virtual agent behaviors.