Detail publikace

Abstrakt

This paper deals with the task of developing a laboratory framework for testing Simultaneous Localization And Mapping algorithms (SLAM). The laboratory framework is composed of three parts. The first one are sensors attached to some mobile device like an unmanned ground or aerial vehicle. The second part is an embedded computer which is employed for collecting data from attached sensors and then it sends it to a remote computing node which is the last part of the proposed laboratory framework. The main purpose of the computing node is to solve the SLAM task. For computation and communication between the embedded computer and the computing node the Robot Operating System (ROS) is used. It provides communication layer based on standard ROS message mechanism that simplifies data exchange over a network. The laboratory framework is designed to work with common combinations of sensors used in various SLAM algorithms. Moreover, the laboratory framework makes it possible to replace the real environment or the robot platform with a simulated alternative. The laboratory framework builds on open source projects and on a proprietary software that is freely available for academic use.