ANALYSIS OF STATE-OF-THE-ART SOFTWARE SOLUTIONS FOR UNSTRUCTURED OUTDOOR ENVIRONMENT PERCEPTION IN GOAL-ORIENTED NAVIGATION OF OFF-ROAD UNMANNED GROUND VEHICLES

This paper presents a comprehensive analysis of state-of-the-art software solutions designed for the perception of unstructured outdoor environments, with a focus on their applicability in goal-oriented navigation for off-road unmanned ground vehicles (UGVs). The analysis encompasses the evaluation...

Full description

Saved in:
Bibliographic Details
Published inScience & Military Journal Vol. 18; no. 2; pp. 5 - 15
Main Authors Vargovčík, Matej, Pásztó, Peter, Kľúčik, Marian, Smoľák, Martin, Štefka, Patrik, Lenner, Jakub
Format Journal Article
LanguageEnglish
Published Liptovský Mikulás Armed Forces Academy 01.07.2023
Subjects
Algorithms
Autonomous navigation
Cameras
Datasets
Localization
Mapping
Neural networks
Perception
Registration
Roads
Roads & highways
Sensors
Simultaneous localization and mapping
Software
Unmanned ground vehicles
Vegetation
Online AccessGet full text

Cover

More Information
Summary:This paper presents a comprehensive analysis of state-of-the-art software solutions designed for the perception of unstructured outdoor environments, with a focus on their applicability in goal-oriented navigation for off-road unmanned ground vehicles (UGVs). The analysis encompasses the evaluation of various sensors for UGV navigation, comparison of methods for extracting perceptual information from sensor data, and the development of a perception system based on the findings. The proposed system leverages advancements in simultaneous localization and mapping (SLAM), visual odometry, and traversability segmentation using 3D LiDAR and visual systems. The analysis suggests a phased approach for the development of autonomous navigation, where the initial phase relies on complex SLAM and teleoperation assistance, and the subsequent phase introduces an autonomous mode utilizing semantical terrain representation.
DOI:10.52651/sam.a.2023.2.5-15