Submap-Based Indoor Navigation System for the Fetch Robot

In this paper, we present a novel navigation framework for the Fetch robot in a large-scale environment based on submapping techniques. This indoor navigation system is divided into a submap mapping part and an on-line localization part. For the mapping part, in order to deal with large environments or multi-story buildings, a submap mapping framework fusing two-dimensional (2D) laser scan and 3D point cloud from RGBD sensor is proposed using Google Cartographer. Meanwhile, several image datasets with corresponding poses are created from the RGBD sensor. Thanks to the submap framework, the error is limited corresponding to the size of the map, thus localization accuracy will be improved. For the on-line localization, so as to switch the submaps, the on-line images from the RGBD sensor are used to match the database images using DeepLCD, a deep learning based library for loop closure. Based on the information from DeepLCD and odometry, adaptive Monte Carlo localization (AMCL) is reinitialized to finish the localization task. In order to validate the result accuracy, reflectors and a motion capture system are used to compute the absolute trajectory error (ATE) and the relative pose error (RPE) based on the Gaussian-Newton (GN) algorithm. Finally, the proposed framework is tested on the Fetch simulator and the real Fetch robot, including both submap mapping and on-line localization.