Path searching for a mobile robot by local planning

Abstract

This paper describes a local path planning method for a mobile robot to search for a path in an unknown environment by using visual information. The mobile robot system has a hierarchical path planning system which searches for a path efficiently in an uncertain environment. The planning system consists of a global planner and a local planner. The global planner gives a global path in terms of a sequence of visual sub-goals. Then the local planner generates a local path between the sub-goals with the help of a visual sensor. The main focus of this paper is on local path planning, which provides real-time guidance to the system. A visual sensor can provide useful information about the environment. So, an algorithm is proposed to generate avoiding points by using visual information to bypass unknown obstacles in the local path planning. Local path planning in a simple environment is simulated by using three-dimensional graphics. A simple experiment is also done for the case where there are two obstacles. The validity of the proposed method is verified by these simulations and experimental results.