|
|
Evolutionary development of robotic organisms
Krčah, Peter
Thirteen years have passed since Karl Sims published his work on evolving virtual creatures. Since then, several approaches to neural network evolution and genetic algorithms have been introduced. This thesis proposes a novel algorithm for the evolution of virtual creatures. The algorithm - Hierarchical NEAT - is inspired by NeuroEvolution of Augmenting Topologies (NEAT) algorithm which efficiently evolves artificial neural networks. Hierarchical NEAT applies all three main components of NEAT algorithm (protecting evolutionary innovation through speciation, sensible mating of the creatures and incremental growth from minimal structure) to the evolution of morphology and control system of the virtual creatures. Furthermore, the algorithm also allows sensible mating of control systems of the creatures, as opposed to original mating methods. Experiments have shown that the proposed algorithm significantly increases the performance of the evolution on all tested tasks. Several supplementary experiments have also been conducted to confirm that each component of the algorithm is beneficent for the evolution, that central coordination in not necessary for successful evolution of light-following strategies and that the choice of neuron transfer functions does not have significant impact on the evolution of the...
|
|
|
Introduction of Castes in Evolution of Artificial Beings
Trunda, Otakar ; Hric, Jan (advisor) ; Holan, Tomáš (referee)
In present work we study questions about introduction of castes in evolution of artificial beings. We present the concept that allows defining various castes and its mutual relations and simulating life of members of these castes in virtual environment. We describe features of our concept and illustrate its usability on several typical scenarios using castes. In this environment we study model situations where the beings in virtual world play different roles. We observe the simulations and its results trying to learn what impact the initial conditions, agents parameters (such as Life expectancy) and environment parameters (e.g. mutation probability) have on the outcome of the simulation.
|
|
|
Artificial Life Models
Ďuričeková, Daniela ; Martinek, David (referee) ; Peringer, Petr (advisor)
This bachelor thesis describes design and implementation of an artificial life simulator. The work is divided into four parts. The aim of the first part is to provide a brief overview of artificial life and related terminology. The second part deals with selected design patterns and the process of designing a simulation system, whose purpose is to simulate an ecosystem of artificial life entities. The subsequent part focuses on implementation of individual system components. Finally, the system is tested and evaluated on two sample models.
|
|
|
Distributed Artificial Life Simulator
Weiss, Martin ; Kočí, Radek (referee) ; Martinek, David (advisor)
Along with the artificial intelligence modelling and related studies, distributed computing ranks amongs the most discussed scientific topics nowadays and one can be certain that it will not fade away anytime soon. This work is also concerned about the above mentioned topics, more precisely its its main goal is to design and implement a distributed artificial intelligence simulator. The mentioned application was realized during as an firm part of this work and some benchmarks were run to determine and observe some properties inherent to distributed systems. The actual realization takes into account different approaches to distributing simulation resources. The final product did not prove as that convenient for simulation of rather simple AI models, which it if fact, even slowed down at times. In the future the project should be aimed towards more computationally challenging problems, that can truly use the capacity and advantages of such a computational system.
|
|
|
Artificial Life Simulator
Popek, Miloš ; Grulich, Lukáš (referee) ; Martinek, David (advisor)
Area of artificial life is very extensive. Simulations with reactive agents are the target of this work. Simulator of artificial life and language for definition agent's behavior are described in this work. Porposals a results of simulation made are described in this work.
|
|
|
Artificial Life Modelling
Žák, Jakub ; Kunovský, Jiří (referee) ; Zbořil, František (advisor)
This paper deals with artificial life simulation by means of artificial BDI agents.This work aims to create a virtual world, to which agents are put. In system, there is 5 kinds of agents. Agent father, who rules and synchronizes the system. Next are agent worker, salesman, cop and thief. Model of the system is created by use of Prometheus methodology. The system is programed in the Jason language, which is implementation of AgentSpeak language.
|
|
|
Selected methods of artificial intelligence - artificial life and computer viruses
Hapala, Michael ; Jirků, Petr (advisor) ; Berka, Petr (referee)
The aim of this bachelor's thesis is to introduce a reader into the area of artificial intelligence, artificial life and computer viruses. The thesis is divided into chapters. First chapter deals with artificial intelligence, it tries to define natural intelligence and then also artificial intelligence. Next part of the thesis describes history of artificial intelligence from its beginings till current times, particular points are separated by years, in which they happenned. Second chapter deals with artificial life, it defines life and characterizes artificial life. Then it deals with cellular automata. It describes, what a cellular automaton is. It deals with von Neumann's kinematic model and celullar automaton and then characterizes particular cellular automata -- the Game of Life, Langton Qloops and Wolfram's one-dimensional cellular automaton. It describes the meaning of cellular automata, then Lindenmayer systems and other methods of artificial life -- artificial life and chaos and life simulators. Third chapter deals with computer viruses, their definition and beginnings. Then it describes classification of malware and techniques of computer viruses. Remaining part sorts viruses by target they infect, by their concealment strategy, by their location in memory and it mentions other types of viruses.
|
|
|
Meaning of cognitive processes for creating artificial intelligence
Smutný, Zdeněk ; Pstružina, Karel (advisor) ; Kelemen, Jozef (referee)
This diploma thesis brings an integral view at cognitive processes connected with artificial intelligence systems, and makes a comparison with the processes observed in nature, including human being. A historical background helps us to look at the whole issue from a certain point of view. The main axis of interest comes after the historical overview and includes the following: environment -- stimulations -- processing -- reflection in the cognitive system -- reaction to stimulation; I balance the approach and the limited potential of the human being against the machine (or artificial intelligence). In the last part, there are introduced two projects that have been already implemented in the inteligent transport systems, and their potential for the further expansion and development is shown here. The main emphasis is placed on the coherence between each part of this thesis and cognitive processes, and on the relation and the mutual dependence of these processes.
|
|
|
Natural and Artificial Life
Noska, Martin ; Pavlík, Ján (advisor) ; Petrášek, František (referee)
This thesis is about similarities and differences between natural and artificial life. It examines how a combination of insight from the disciplines of computer science and philosophy can be used to address this issue. By applying the principles of evolution to artificial life, the paper shows the perspectives of this life form and its implications for mankind. Human history contains many attempts at constructing artificial creatures; however, this dream only became reality with the advent of digital computers. Although artificial life is built on different principles than natural life, is better to view both as complementary rather than as opposites. It is possible to speculate on symbiosis between artificial and natural elements and on the formation of hybrid life forms that combine features from both worlds. Artificial life is not dependent on biological cycles and its evolution can proceed much faster. It has the potential to overcome the necessity of death, which is characteristic of all biological entities. If we compare the intelligence of machines to that of natural organisms, it is possible to identify the differences between them. Machine intelligence has the potential to create artificial collective intelligence through computer networks that exceed the level of separate entities. Simple forms of artificial life, identifiable at present, will evolve in coming decades and raise a number of unsolved questions (i.e. ethical concerns). These issues are and will remain current.
|
guest ::
