DS-PTAM: Distributed Stereo Parallel Tracking and Mapping SLAM System

Abstract

This paper presents DS-PTAM, a distributed architecture for the S-PTAM stereo SLAM system. This architecture is developed on the ROS framework, separating the localization and mapping tasks into two independent ROS nodes. The DS-PTAM system is ideal for mobile robots with low computing power because it allows to run the localization module on-board and the mapping module —which has a higher computational cost— on a remote base station, relieving the load on the on-board processor. The proposed architecture was implemented based on the original S-PTAM monolithic code and then validated through different experiments on public datasets. The results obtained show the feasibility of the proposed distributed architecture, its correct implementation and the benefits of distributing the computational load on several computers.