الفهرس 
Genetic AlgorithmOnly 14 pages are availabe for public view
 |  | from | 164 |  |  |
| | | from | 164 | | |
Abstract
The aim of this thesis is to develop a robust controller of a mobile robot br regardless of its morphology or malfunction. br Many researches implemented a controller for a mobile robot with br different techniques, some of them use a fuzzy system for the implemen- br tation but they use a fixed rule base dependent on the mobile robot’s br morphology causing a failure in the controller when a malfunction oc- br curs. In this thesis, we overcome this problem by implementing this br controller using (Evolvable Hardware) EHW. br The EHW is designed to adapt, like the chameleon changing its br color to blend with the environment to changes in task requirements or br changes in the environment, through its ability to reconfigure its own br hardware structure dynamically and autonomously. This capacity for br adaptation is achieved by employing efficient search algorithms known br as genetic algorithm. This adaptation has great potential for the de- br velopment of innovative industrial applications. br The Mobile robot controller used in this thesis is a fuzzy-genetic br controller. The controller is implemented by hardware that can change br the rule base according to the result generated from the genetic algo- br rithm to be suitable with the robot’s morphology. By this method, the br controller adjusts itself autonomously. br Finally, we implement a new obstacle avoidance technique to over- br come obstacle collision. The controller was implemented using Xilinx br FPGA. SIM-MECH and Virtual Reality MATLAB’s toolboxes are used br for simulating the mobile robots to evaluate its performance. br Different mobile robot’s morphology (two wheel mobile robot, like br car mobile robot and omniwheel mobile robot) were studied to check br the proposed method. Simulations have been performed with or with- br out obstacles and with or without malfunction in the robot.