Solving the Indoor SLAM Problem for a Low-Cost Robot using Sensor Data Fusion and Autonomous Feature-based Exploration

Abstract

This article is concerned with the solution of the SLAM (Simultaneous Localization And Mapping) problem in an indoor environment using a low-cost mobile robot that autonomously explores the environment. The robot was constructed with a distance measurement subsystem composed of three types of sensors: a wireless webcam with a laser pointer (a visual sensor), two infrared sensors and an ultrasonic TOF (time-offlight) sensor. Firstly, an algorithm that requires a small computational load is used to fuse the noisy raw data acquired by these sensors and generate the environment features. These features are then used by a particle filter to solve the SLAM problem. An autonomous feature-based exploration algorithm was implemented and is also presented. The results obtained in the experiments carried out in two small indoor environments show that the estimated environment map generated when the robot uses the autonomous exploration algorithm is very similar to the one generated when the robot poses were manually chosen.