New Hybrid Architecture in Artificial Life Simulation
This paper gives concise overview of our approach to the simulation of living forms and shows how it is possible, with help of the AI bottom-up methods, ethological and evolution principles, to simulate agents who have needs and desires, reflexes and instincts, but also have ability to perform deliberative tasks and to accomplish more complex goals. We have implemented a virtual environment - Artificial Life Simulator and our ideas and approaches were tested in practical situations.
Unable to display preview. Download preview PDF.
- 1.Ferber, J.: Multi Agent Systems. An Introduction to Distributed Artificial Intelligence. Addison-Wesley. (1999).Google Scholar
- 2.Maes, P.: A Bottom-Up Mechanism for Action Selection in Artificial Creatures. In: Proc. From Animals to Animats Conference’ 91, (1991), 238–248.Google Scholar
- 3.Svatoš, V., Nahodil, P., Kadleček, D., Kurzveil, J., Maixner V.: Community of Mobile Robots in Education. In: Proc. of IFAC EPAC 2000 Conference: The 21st Century Education in Automation and Control, Skopje, Macedonia, (2000), 53–57.Google Scholar
- 4.Nahodil, P., Svatoš, V.: Sense-Action Encoding in Hybrid Decision System. In Proc. MIC2001, IASTED Int. Conference, Innsbruck, Vol. 1, (2001), 414–419.Google Scholar
- 5.Tyrrell, T.: Computational Mechanisms for Action Selection. Ph.D. Thesis, Edinburgh University. (1999)Google Scholar