Automatic Interpretation of Unordered Point Cloud Data for UAV Navigation in Construction

TL;DR

This paper presents an automated data processing system that uses laser scanner and IMU data to generate navigation waypoints for UAVs inspecting structures, enhancing autonomous inspection capabilities.

Contribution

It introduces a novel integrated algorithmic framework for 3D modeling, surface detection, and waypoint generation from unordered point cloud data for UAV navigation.

Findings

Successful 3D reconstruction of structures from laser data

Effective surface and obstacle detection for UAV monitoring

Automated waypoint generation for inspection tasks

Abstract

The objective of this work is to develop a data processing system that can automatically generate waypoints for navigation of an unmanned aerial vehicle (UAV) to inspect surfaces of structures like buildings and bridges. The input includes data recorded by two 2D laser scanners, orthogonally mounted on the UAV, and an inertial measurement unit (IMU). To achieve the goal, algorithms are developed to process the data collected. They are separated into three major groups: (i) the data registration and filtering to generate a 3D model of the structure and control the density of point clouds for data completeness enhancement; (ii) the surface and obstacle detection to assist the UAV in monitoring tasks; and (iii) the waypoint generation to set the flight path. Experiments on different data sets show that the developed system is able to reconstruct a 3D point cloud of the structure, extract its surfaces and objects, and generate waypoints for the UAV to accomplish inspection tasks.