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.

There are dozens of formalisms specialized programming intelligent virtual agents (IVA). However, there is lack of an evaluation, which would provide the designer of a new agent with an overview of their usability in real-world applications. The goal of this study was evaluation of selected formalisms in order to identify their shortcomings and suggesting improvements. These improvements would allow the designer more accurate control of the IVA's behavior. Evaluation of formalisms was designed based on real-world scenarios and their implementation in different formalisms using the platform Pogamut 3. One of the formalisms is Jason (AgentSpeak language interpreter) and it was connected to that platform as a part of this thesis. During the implementation of the scenarios were identified some problems which make creating the behavior of intelligent virtual agents harder. For these problems was proposed solution in the form of action selection mechanism (ASM) prototype and the basic methodology for designing agents with this ASM. The results of this study could be a starting point for more advanced action selection mechanism, which would allows more precise control of the behavior of intelligent virtual agents. Powered by TCPDF (www.tcpdf.org)

Many contemporary computer games can be described as dynamic real-time simulations inhabited by autonomous intelligent virtual agents (IVAs) where most of the environment structure is immutable and navigating through the environment is one of the most common activities. Though controlling the behaviour of such agents seems perfectly suited for action planning techniques, planning is not widely adopted in existing games. This paper attempts to answer the question whether the current academic planning technology is ready for integration to existing games and under which conditions. The paper compares reactive techniques to classical planning in handling the action selection problem for IVAs in game-like environments. Several existing classical planners that occupied top positions in the International Planning Competition were connected to the virtual environment of Unreal Development Kit via the Pogamut platform. Performance of IVAs employing those planners and IVAs with reactive architecture was measured on a class of game like test environments under different levels of external interference. It was shown that agents employing classical planning outperform reactive agents only if the size of the planning problem is small or if the environment changes are either hostile to the agent or not very frequent.

Indiana University-Purdue University Indianapolis (IUPUI) / Just as physical appearance affects persuasion and compliance in human communication, it may also bias the processing of information from avatars, computer-animated characters, and other computer interfaces with faces. Although the most persuasive of these interfaces are often the most humanlike, they incur the greatest risk of falling into the uncanny valley, the loss of empathy associated with eerily human characters. The uncanny valley could delay the acceptance of humanlike interfaces in everyday roles. To determine the extent to which the uncanny valley affects persuasion, two experiments were conducted online with undergraduates from Indiana University. The first experiment (N = 426) presented an ethical dilemma followed by the advice of an authority figure. The authority was manipulated in three ways: depiction (recorded or animated), motion quality (smooth or jerky), and recommendation (disclose or refrain from disclosing sensitive information). Of these, only the recommendation changed opinion about the dilemma, even though the animated depiction was eerier than the human depiction. These results indicate that compliance with an authority persists even when using a realistic computer-animated double. The second experiment (N = 311) assigned one of two different dilemmas in professional ethics involving the fate of a humanlike character. In addition to the dilemma, there were three manipulations of the character’s human realism: depiction (animated human or humanoid robot), voice (recorded or synthesized), and motion quality (smooth or jerky). In one dilemma, decreasing depiction realism or increasing voice realism increased eeriness. In the other dilemma, increasing depiction realism decreased perceived competence. However, in both dilemmas realism had no significant effect on whether to punish the character. Instead, the willingness to punish was predicted in both dilemmas by narratively characterized trustworthiness. Together, the experiments demonstrate both direct and indirect effects of narratives on responses to humanlike interfaces. The effects of human realism are inconsistent across different interactions, and the effects of the uncanny valley may be suppressed through narrative characterization.

Title: Controlling Virtual People Author: Mgr. Jakub Gemrot Department: Department of Software and Computer Science Education Supervisor: Mgr. Cyril Brom, PhD. Abstract: In this thesis, we provide a computational formalization of reactive planning as a paradigm for decision making of intelligent virtual agents and videogame non-player characters. We formalize agent decision-making (ADM) as a process of deciding on which body actions to execute next and differentiate it from agent reasoning as a process of computing facts needed for decision making. We show that imperative programming languages are not suitable for ADM specification and explain why they are not suitable. Thereafter, we create a new computational model that we use as the basis for the definition of Behavior Design Language (BDL). We show that BDL can model decision-making specified by scripting, hierarchical finite-state machines, AgentSpeak(L), GOAL, SPOSH and Behavior trees. Importantly, BDL can model these approaches economically in terms of the number of behavior primitives. The key strengths of the BDL language are: versatility (it can mix decision making patterns of multiple languages together), extensibility (it allows developers to devise new language primitives as they see fit), and generality (it can abstract any computable...

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness. Evidence-based patient-centered Brief Motivational Interviewing (BMI) interven- tions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary. Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems. To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].