An experimental distributed framework for distributed Simultaneous Localization and Mapping

Abstract

Simultaneous Localization and Mapping (SLAM) is widely used in applications such as rescue, navigation, semantic mapping, augmented reality and home entertainment applications. Most of these applications would do better if multiple devices are used in a distributed setting. The distributed SLAM research would benefit if there is a framework where the complexities of network communication is already handled. In this paper we introduce such framework utilizing open source Robot Operating System (ROS) and VirtualBox virtualization software. Furthermore, we describe a way to measure communication statistics of the distributed SLAM system.