Abstract: It is very difficult for the robot to obtain the surrounding environment information and establish a real-time environment map to achieve autonomous operation quickly in the unknown environment.To solve the problem,this paper presents a method based on visual navigation,which use the panoramic camera as a robot vision sensor system to collect environmental information and use the fuzzy clustering image segmentation to division the color map in HSI space that get the binary image.Then build the environment map,and use the Dijkstra method to calculate the global path planning and obtain the optimal path.Finally achieve the fast and autonomous movement of the mobile robot.The simulation experiments show that the method iS effective and feasible.