Growing Neural Gas based Traversability Analysis for Autonomous Driving

Abstract

An autonomous mobile robot needs to many tasks such as a self-localization, collision detection, and path planning to a target position in an unknown environment. Therefore, it is important for the robot to build environmental maps with different resolutions in each work space. This research proposes a Growing Neural Gas based topological environmental map building method from 3D point cloud data. Our proposed method enables to build the topological map of traversability created by mobility information. Finally, we conduct on experiment for evaluating our proposed method, and discuss the effectiveness of our proposed method.