Combining metric and topological navigation of simulated robots
AbstractMobile robotics and robot navigation is a growing area of scientific research. Robot simulators are useful designing and analizing tools of this domain. Webots  is a well-known representant of these programs, a three-dimensional mobile robot simulator. Various guidance principles can be developed in C/C++ or Java programming language with the use of Webots controller programs. In this paper a short overview is given about the problems arising in the process of the navigation, and a short taxonomy is presented about the possible problem solving methods . A brief introduction to the probabilistic navigation techniques concerning Kalman filter and expectation maximization is included with a special focus on occupancy grid. Formerly I presented a metric navigation method based on occupancy grid working in the Webots simulation environment . As a continuation of that research I created an enhancement of the former processes, a hybrid metric-topological navigation mechanism. A topologic layer is introduced in the environment exploration phase replacing the older value iteration . The implementation of a topologic graph of the explorable places using the metric map enables the robot to navigate in a more efficient manner. A comparison of the pure metric and the new hybrid methods is also given.
Download data is not yet available.
How to Cite
Szabó, R. (2005). Combining metric and topological navigation of simulated robots. Acta Cybernetica, 17(2), 401-417. Retrieved from https://cyber.bibl.u-szeged.hu/index.php/actcybern/article/view/3674