The paper deals with a problem of intelligent system’s design for complex environments. There isdiscussed a possibility to integrate several technologies into one basic structure that could form a kernel of anautonomous intelligent robotic system. One alternative structure is proposed in order to form a basis of anintelligent system that would be able to operate in complex environments.The proposed structure is very flexible because of features that allow adapting via learning and adjustment of theused knowledge. Therefore, the proposed structure may be used in environments with stochastic features suchas hardly predictable events or elements. The basic elements of the proposed structure have found theirimplementation in software system and experimental robotic system. The software system as well as the roboticsystem has been used for experimentation in order to validate the proposed structure - its functionality, flexibilityand reliability. Both of them are presented in the paper. The basic features of each system are presented as well.The most important results of experiments are outlined and discussed at the end of the paper. Some possibledirections of further research are also sketched at the end of the paper.
展开▼