Abstract
In recent years, there is more and more attention on robotics research. Many related application and technology are also widely developed. In particular, for some labor-intensive or extremely dangerous works, we long for using robots to substitute for human being and accomplish these works. Therefore, robot navigation is necessary and widely discussed. Simultaneous self-positioning, environment map building, path planning and obstacle avoidance are essential abilities for autonomous mobile robots.However, it is not easy to achieve these functions. These four problems are not independent but mutually correlated. For example, once self-localization consists in error, it may cause the wrong map building. And the wrong map will cause self-localization in larger error. Furthermore, path planning and obstacle avoidance also need to rely on good self-localization to determine the relative position of robot, obstacles and map.In this thesis, we propose a system for wheeled robot SLAM and navigation in indoor environments. An omni-directional camera and a laser range finder are the sensors to extract the point features and the line features as the landmarks. In SLAM and self-localization while navigation, we use extended Kalman filter (EKF) to deal with the uncertainty of robot pose and landmark feature estimation. After the map is built, robot can navigate in the environment based on it. We apply two scale path-planning for navigation. The large-scale planning finds an appropriate path from starting point to destination. The local-scale path-planning fills up the drawbacks of the prior step, such as dealing with the static and dynamic obstacles and smoothing the path for easier robot following. Through the experiment results, we show that the proposed system can smoothly and correctly locate itself, build the environment map and navigate in indoor environments.