![]() | Only 14 pages are availabe for public view |
Abstract Case-Based Reasoning (CBR) suggests a model of reasoning that depends on experiences and learning. CBR solves new cases by adapting solutions of retrieved cases. Recently, CBR is considered as one of the most important Artificial Intelligent (AI) techniques used in many robotics tasks as: motion control and behavior control, especially for humanoid robots in RoboCup domain. This is due to the complexities of the dynamics of the environment and the complexities of behaviors coordination and selection in real-time. In this thesis: A study on case retrieval and adaptation algorithms for robots has been done. This study points out the appropriateness and the limitations of conventional and recent CBR algorithms. from this study, we concluded that the use of conventional retrieval or adaptation algorithms is the main bottleneck for CBR particularly in robotics tasks. However, the use of recent directions are more suitable for overcoming the retrieval and adaptation burden,. But these approaches are successful only in specific CBR tasks as diagnosis and planning. However, more research for CBR for robots tasks is still essential, especially for motion planning and behavior control tasks. |