Autonomous mapping for robot based on monocular vision and DGSOM algorithm

Abstract

Aiming at the problems in unknown environment for mobile robots map building, a method combined monocular vision and DGSOM(Dynamic Growing-SOM) Algorithm is proposed. The method first uses a monocular camera to collect environment images, after treatment with monocular vision processing technology, environmental information samples for DGSOM algorithm are obtained from image information, and then they can be used as neural network training samples, thus the topologic map that describes the environment information is generated with a few SOFM neurons. The experimental result shows that autonomous mapping for robot using a combination of monocular vision and DGSOM algorithm is feasible, and the robot can realize environment mapping automatically.