Behavior based mobile robot in automatic assembly

This work deals with the development of intelligent autonomous robot using behavior based control approach. The hypothesis is that intelligence, as something what assumes the understanding, creativity and self-improving, should rely on the learning ability. Planning of intelligent robot behavior addresses three main issues: finding task solutions in unknown situations, learning from experience and recognizing the similarity of problem paradigms. The presented behavior based model integrates perception, recognition, problem solving and learning capabilities. The reinforcement learning method is used here to evaluate robot behavior and to induce new, or improve the existing, knowledge. The acquired action (task) plan is stored as experience which can be used in solving similar future problems. To provide the recognition of problem similarities, the adaptive fuzzy shadowed (AFS) neural network is applied. This behavior based approach to the robot intelligence is simulated on the mobile robot model and verified on the Pioneer 2DX, the real mobile robot, using primarily the sonar perception of working environment to manage its performance in unknown surroundings for given task