PCA-Based Line Detection from Range Data for Mapping and Localization-Aiding of UAVs

Roberto Opromolla,Al Savvaris,Giancarmine Fasano,Antonio Moccia,Michele Grassi

doi:10.1155/2017/4241651

Abstract

This paper presents an original technique for robust detection of line features from range data, which is also the core element of an algorithm conceived for mapping 2D environments. A new approach is also discussed to improve the accuracy of position and attitude estimates of the localization by feeding back angular information extracted from the detected edges in the updating map. The innovative aspects of the line detection algorithm regard the proposed hierarchical clusterization method for segmentation. Instead, line fitting is carried out by exploiting the Principal Component Analysis, unlike traditional techniques relying on least squares linear regression. Numerical simulations are purposely conceived to compare these approaches for line fitting. Results demonstrate the applicability of the proposed technique as it provides comparable performance in terms of computational load and accuracy compared to the least squares method. Also, performance of the overall line detection architecture, as well as of the solutions proposed for line-based mapping and localization-aiding, is evaluated exploiting real range data acquired in indoor environments using an UTM-30LX-EW 2D LIDAR. This paper lies in the framework of autonomous navigation of unmanned vehicles moving in complex 2D areas, for example, being unexplored, full of obstacles, GPS-challenging, or denied.

Highlights

Among the technical challenges which drive the research activities carried out in the field of Unmanned Aerial Vehicles (UAVs), a major issue is to improve their level of autonomy
This sensor is installed on a portable platform together with one autopilot, that is, the Pixhawk produced by 3D robotics, which is used to obtain reference information regarding the attitude of the platform, and one embedded board, that is, the Nitrogen6X produced by Boundary-Devices
This paper presented a new technique for line detection from range data (2D point clouds) provided by a 2D LIDAR, which is of interest to Unmanned Aerial Vehicles which need to carry out autonomous navigation applications, such as localization and mapping, in 2D cluttered environments

Summary

Introduction

Among the technical challenges which drive the research activities carried out in the field of Unmanned Aerial Vehicles (UAVs), a major issue is to improve their level of autonomy. In the case of large-scale outdoor scenario, autonomous and safe navigation is ensured by the classical sensor fusion architectures integrating an Inertial Navigation System (INS) with GPS, typically indicated as GPS-INS [2, 3], which has been extensively exploited by researchers considering fixed-wing [4, 5], helicopter [6, 7], and multirotor [8] UAVs. a wide range of both military and civil applications, for example, urban and indoor surveillance, infrastructure monitoring, and exploration, require a microUAV (MAV) to be able to navigate in more complex environments, such as unknown areas, full of static, and/or mobile obstacles in which the GPS signal may be completely absent (GPS-denied, e.g., indoor) or unreliable due to multipath, absorption, and jamming phenomena (GPS-challenging, e.g., urban or natural canyons). Alternative solutions have to be found, which involve the use of exteroceptive sensors that can be active, such as RADAR [9], LIDAR [10], ultrasonic rangefinders [11], and ultra-wideband (UWB) positioning system [12], passive, for example, monocular [13] and stereovision [14] cameras operating in the visible band of the electromagnetic spectrum, or hybrid, like RGB-depth cameras [15], as they simultaneously acquire passive RGB images and depth images of the same scene in an active way [16].

Objectives

Results

Conclusion