High speed navigation of a mobile robot based on robot’s experiences

In this paper, it is shown how a mobile robot can navigate with high speed in dynamic real environment. Our control scheme is developed based on the dynamic window approach [2]. Although the mobile robot is able to navigate using the DWA, there is a fundamental limitation that the robot can avoid only “visible” obstacles. There are many dangerous regions where dynamic obstacles appear abruptly, in human co-existing real environments. The robot should move “slowly” to prevent unexpected collision in practical application. In order to achieve high speed and safe navigation, a robot should collect environmental information. After collecting sufficient data, a robot navigates in high speed in safe regions. This paper proposes a computational scheme how a robot can distinguish regions of high risk. The proposed scheme is experimentally tested in a real office building. The experimental results clearly show that the proposed scheme is useful for improving a performance of autonomous navigation.