Research Of Intelligent Mobile Robot's Location

If a mobile robot wants to move in a certain environment, it must know its location in the environment. Only by this, it can make the right choice and get the good decision in structured or unstructured environment. All these say that location is very important to robot' s practical use. It is the basis of locomotion and other tasks. It is a very interesting research topic.This paper mainly discusses the theory and application of robot location. At first, the theory of location using dead-reckoning and ultrasonic sensor is presented. The location simulation of GAIA-2 robot is shown. The result of simulation shows that the method using data fusion is better than dead reckoning. The former gains not only less error but also faster process speed.The computer vision and its application in robotics are also presented. The pin-hole model of camera is introduced. The parameter of camera using in this research is measured by camera calibration. It provides data for the design of omni-directional camera.There are some shortcomings for common camera, such as limited visual field. So the omni-directional camera is introduced. Its model, design and restriction are presented in details. An omni-directional camera is produced. The unwrapping algorithm of distorted view is shown. The natural characters such as door, window and vertical wall corners are gained by feature extraction in omni-directional picture. Robot location using trigonometry is experimentalized. The result of experiment shows that this location method is viable.In the final of the paper, the research and results are summarized. The future of this research field is described.