This thesis is focused on using softcomputing method for learning bipedal robot to walk. Robot is represented by virtual model. At the beginning are the motivation and reasons for processing this theme. Next is devised shape of the robot which will be used. Then are selected libraries used by simulation. Further is devised system of robot learning algorithms. The most important of them is SOMA which is therefore described more. Due to assumed computational complexity is part of thesis focused on optimalization and simplification. One chapter focuses on measurement of quality of solution approximation. At the end there is an evaluation of thesis results.
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:237227 |
| Date | January 2010 |
| Creators | Pokorný, Jan |
| Contributors | Janoušek, Vladimír, Martinek, David |
| Publisher | Vysoké učení technické v Brně. Fakulta informačních technologií |
| Source Sets | Czech ETDs |
| Language | Czech |
| Detected Language | English |
| Type | info:eu-repo/semantics/masterThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.002 seconds