|
|
Adaptive agents and emotions
Kadlec, Rudolf ; Kryl, Rudolf (referee) ; Brom, Cyril (advisor)
This thesis investigates possible assets of emotions for autonomous adaptive agents working in environments similar to the real world. In living organisms, emotions have developed as a mechanism of adaptation to the surrounding environment. Therefore it is worth asking whether mechanisms similar to emotions can be implemented in models of autonomous agents. In this thesis a model of ethology inspired agent using reinforcement learning was implemented. This model suggests that emotions influence the balance between exploring new strategies and exploiting the strategies already known (the so-called explore/exploit problem). Negative emotional evaluation leads to changes in action selection strategy. The emotional version proved to be better than the non-emotional one in some environments. In other types of environments, the expectations have not been fulfilled. The instability of the received results is probably caused by non-optimal parameterization of the whole model.
|
|
|
Unreal Tournament Twins
Burkert, Ondřej ; Yaghob, Jakub (referee) ; Brom, Cyril (advisor)
This bachelor thesis is focused on team cooperation of a couple of agents in the enviroment of Unreal Tournament (UT) in the fundamental team-play mode. I worked on realization of autonomous behavior, communication, synchronization of important informations and implementation of tactical operations. Better informed agent could deliver more sofisticated performance and credibility. I implemented the project on the framework made from the game UT, the middleware Gamebots, POSH (the architecture for making agent's logic) and the middleware Pogamut. When I succesfully finished implementation, I have made set of tests to find out the impact of some approaches on agents performance in the game. I found out that the level of cooperation affects the performance. Couple of agents who were cooperating only by sharing informations proved to be the most effective and suitable for the choosen mode of the game.
|
|
| |
|
|
Mapping, processing, and representation of a map for Unreal Tournament bots
Gemrot, Jakub ; Brom, Cyril (advisor) ; Yaghob, Jakub (referee)
In many computer games the navigation points are used for the movement of computer-controled players. With the growing power of desktop computers more sophisticated methods are used for the movement of players, namely the method of NavMesh. NavMesh is a set of convex polygons continuously covering the reachable places inside the game by characters. This approach was used in the recently produced games Half-Life 2 and F.E.A.R. Those commercial products can't be used by the academy, therefore the chance to experiment with NavMesh doesn't exist. But there is a simple way to control the characters in environment of older game Unreal Tournament. This work is about the advantages of using NavMesh against older approach of navigation points. This work then presents the way how to automatically generate the NavMesh for the maps of Unreal Tournaments. NavMesh is created using the algorithm from computer graphics for the conversion from CSG representation of the map into boundary representation out of which the NavMesh can be generated. The work also contains a demonstration of usage of NavMesh for the movement of players in Unreal Tournament's maps.
|
|
|
Unreal bots with emotions
Bída, Michal ; Brom, Cyril (advisor) ; Holan, Tomáš (referee)
This work is concerned with usage of emotions in artificial inteligence in computer games. It inspects possible benefits of emotions for artificial inteligence in the means of better imitation of human behavior. Main goal of this work is the implementation of an emotion model in the enviroment of the game Unreal Tournament (project UT Emotion Bots) and appraisal of its properties and suitability for the simulation of emotions in FPS games. This work introduces platforms used in the development of the project UT Emotion Bots and it evaluates their suitability for development of artificial inteligence.
|
|
|
Hierarchical reactive planning with transions
Mikula, Tomáš ; Bojar, Ondřej (referee) ; Brom, Cyril (advisor)
Hierarchical reactive planning (HRP) is a popular method for controlling virtual beings' behaviour. The advantage of HRP is that complex behaviours can be described relatively easily. However, in particular situations problems with biological plausibility arise. This is partially caused by the fact that so called transition behaviours and postponement of behaviour are hard to express in HRP. Transition behaviours are short actions that the simulated beings should engage in between two main behaviours in order to ensure a smooth transition between them. Postponement of behaviour is desirable in case the running behaviour is approaching the end and therefore should not be interrupted. In the present work we incorporate transition behaviours and postponement of behaviour into the model of HRP and describe the implemented prototype.
|
|
|
Animated works and education
Javora, Ondřej ; Brom, Cyril (advisor) ; KOUTSKÝ, Pavel (referee)
This postgraduate thesis deals with the relationship between animated works and education. Main importance is given to the prior historical trends of educational animated works and to the question if are the animated works suitable for educational purposes. The thesis is divided to four chapters. First chapter depicts the historical development of educational animated works and briefly maps this area of animation. Second chapter analyzes specific characteristics of animation and abilities of its means of expression for educational use. Third chapter is a brief introduction to the cognitive psychology which offers valuable knowledge about functions of human mind. The center of attention is focused on attributes of human memory and process of learning, which are somehow related to the usage of animation. Fourth chapter sort of expands the third chapter and bases its conclusions on the work of American psychologist Richard E. Mayer. The subject matter are more practical ways how to use animation to enhance effective learning.
|
|
|
Episodic memory for virtual beings
Pešková, K. ; Brom, C. ; Lukavský, Jiří
Episodic memory is from the psychological point of view the memory for personal events. The problems of episodic memory in virtual humans haven't been studied deeply yet, despite it is a key aspect of virtual beings' believability in simulations, virtual drama or some computer games. The character without episodic memory can't answer simple questions, e.g. what he did the day before, and it will suffer problems, when it is interrupted because the information on interrupted task will disappear from memory. In this report the model of symbolic episodic memory for virtual beings based on Gibson's affordance theory is introduced and the prototype implementation is presented. The believability aspects are discussed e.g. whether the character can reproduce his day story and also the technical parameters (memory, access speed) are reported. The report mentions the phenomenological dimension of the model, and the differences between event forgetting in psychology and in the model are compared.
|
|
|
The Virtual Being's Mind
Brom, C. ; Lukavský, Jiří
Virtual beings are being used in computer games, film industry, education and even in therapy. They need a functional model of mind – to process the signals from environment, to set their goals and to act. In this work we try to define the term of virtual being and to illustrate this concept in one particular project. Virtual beings in IVE Project have three remarkable features: 1) their perception is based on Gibson's theory of affordances, 2) their actions are planned using Belief-Desire-Intention theory, 3) their behavior can be dynamically simplified using Level-of-Detail technique.
|
|
|
Why is the border between a virtual being and its world fuzzy
Brom, C. ; Lukavský, Jiří
In this article we first introduce the IVE project (Intelligent Virtual Environment - developed in 2005 at MFF UK, Prague) and ISMA model (Intention - Suitability - Materialisation - Advice) and describe related theoretical issues of the project. IVE is a simulator of large virtual worlds populated with virtual beings, which uses a new model called ISMA for virtual world representation. This model is inspired by Gibson's affordace theory and Bratman's theory of practical reasoning. Gradually we realized that some project results also have psychological and philosophical interpretation, which is being discussed in this article.
|
guest ::
RSS feed.