This paper describes a control method of chasing person by a vision guided mobile robot in an unknown indoor environment. The robot obtains the environment information by stereo vision and makes a map. From both the map and the observed person position, the robot decides the optimal path to chase the person while avoiding obstacles. Since the observation by stereo vision may include uncertainty, we model the uncertainty to calculate the reliability of the map to be obtained by integrating multiple observation results.
展开▼