Off-Road Navigation Maps for Robotic Platforms using Convolutional Neural Networks

Abstract

Abstract. As part of AMADEE-20, an integrated Mars analog field mission in the Negev Desert in Israel conducted by the Austrian Space Forum, an exploration cascade for the remote sensing of extraterrestrial terrain was implemented. For this purpose, aerial robots were conceptualized, which were used in an iterative process to generate a navigational map for an autonomous ground vehicle. This work presents the process for generating navigation maps using multiple aerial image sources from satellites as well as from low orbiting aerial vehicles. First, Deep Learning methods are used to analyze a high altitude aerial images of a large area, creating a basis map for mission planning and navigation. Second, high resolution unmanned aerial vehicle (UAV) images were recorded on low altitude for a pre-defined area of interest, processed with Deep-Learning and Structure from Motion and used to update the basis map. This approach results in a high accuracy navigation map for autonomous, off-road robot navigation. Experiments during the AMADEE-20 mission in the Israeli Negev Desert validated the proposed methods by sending an autonomous ground vehicle through the environment using the generated map.

Map representations for mobile robot localization

“…Currently, there are many kinds of map representations for mobile robot localization. According to different environmental changes, map representations can be divided into static maps and dynamic maps [8] [9]; according to different environmental dimensions, map representations can be divided into 2D maps and 3D maps [10] [11]; according to the different resolutions, map representations can be divided into low resolution maps and high resolution maps [12] [13]. The above classification methods provide limited guidance on how to choose map representations to adapt to different working conditions.…”