Environment Recognition Of Mobile Robot Based On Multisensors Fusion

In recent years , the application of mobile robot is becoming very abroad. One important research aspect of mobile robot is that it can navigate autonomously and avoid effectively all kinds of obstacles. Before mobile robot can void obstacles in the course of running., it should detect categories of obstacle .In this paper, Recognizing obstacle based on multisensor fusion technology is given .In the support of Tianjin's Natural Science Foundation" the Study of Mobile Robot System Technology Faced to Complicated Task"(No.003601211) and Hebei Province's Tackling Key Problem Plan "the Study of AGV Accurate Navigation Used in Material Automation Transportation"(No.00547001D-18),this thesis developed application study of information fusion based of multisensor in mobile robot's navigate autonomously .In this thesis ,the main work and innovation include:The structure of HEBUT-1 mobile robot is designed. Furthermore, the driving system's characteristics and the kinematics features of the mobile robot are analyzed.The vision system and sonar system of HEBUT-1 mobile robot is designed .The model of camera and the conversion from obstacle image coordinate into the world coordinate is completed, which the information of obstacle is converted into camera coordinate.therefore the different coordinate are unified.Experiment on segmentation are done and a method of image segmentation based of HIS color threshold is used for mobile robot's obstacle image segmentation. The image segmentation method based on HIS color threshold has many advantage: strong antinoise ability, using more information during image processing ,perfect segmentation result without being affected by illuminative condition, and simple calculating process. All these advantages improve the segmentation speed and veracity of complicated obstacle image. Then , the principle of sonar sensors and it's disposition in mobile robot is introduced.Distilling valid character of obstacle's image and distance between obstacle and mobile robot. Due to disadvantage of fusion method generally, In this paper, the advantage of neural network based is used, these advantage include the ability of real-time processing data, the ability of knowledge overflowing and tolerance mistake of structure. Taking the image of obstacle from CCD vidicon, these image must pretreat. and distill valid feature ,at the same time ,provide third dimension distance information from ultrasonic sensor group. By these information, the type of obstacle is recognized by information fusion of neural network, also is independent of obstacleposition .The experiment shows, the above method is succeed, the ratio of recognition is good . The foundation is layed for avoiding obstacle and improving intelligence of mobile robot.