Trajectory Tracking Based Visual Navigation Method of the Mobile Robot

摘要

A trajectory tracking method is presented for the application of the visual navigation of the mobile robot. The robot moves along the line trajectory drawn beforehand, recognize and stop on the stop-sign to finish special task. The robot use a forward looking colorful camera to capture information of the road, and by the use of HSI model partition the trajectory and the stop-sign out. Then use “sampling estimate” method to calculate the navigation parameters. The stop-sign is easily recognized and can identify 256 different signs. Tests indicate that the method can fit large-scale intensity of brightness and has more robustness and better real-time character.