Environmental Map Learning Method based on Growing Neural Gas for a Mobile Robot

An autonomous mobile robot needs many tasks such as self-localization, collision detection, and path planning to a target position in an unknown environment. Therefore, the robot needs to build environmental maps with different resolutions in each workspace. In addition, the robot requires the path planning capability in the unknown environment for applying the robot to various domains such as a disaster site and commercial construction. This research proposes a Growing Neural Gas based topological environmental map building method from a metric map with a high-resolution map for using self-localization. Our proposed method enables us to build the topological map with occupancy information of the metric map and simultaneously preserve the geometric feature of the map. Next, the path planning method in unknown environments is proposed by utilizing the topological map, and the sub-goal selection of the topological map is proposed by utilizing the contour node information for realizing the path planning in an unknown environment. Finally, we conducted several experiments to evaluate our proposed method and discuss its effectiveness.