Room categorization using local receptive fields-based extreme learning machine

Abstract

For indoor mobile robots, the ability to identify different scenes correctly is an important condition for them to complete a variety of tasks. In this paper, we propose a method which is based on range measurements to solve the problem of room categorization for mobile robots using Local Receptive Fields Based Extreme Learning Machine. We download the DR Dataset which was gathered by a Pioneer P3-DX robot equipped with a Hokuyo URG laser range-finder and extract the range data characteristics in three different ways. Finally, six different types of experiments are carried out in two different scenarios, and the results show the effectiveness of the method in different scenarios.