Autonomous UAV for Building Monitoring, Detection and Localisation of Faults

TL;DR

This paper presents an automated UAV system that monitors buildings for faults using neural networks, localizes detected faults, and navigates around the structure, demonstrated through simulation in ROS and AirSim.

Contribution

It introduces a novel UAV-based method for building fault detection and localization using neural networks and path planning in a simulated environment.

Findings

Effective fault detection via neural networks in simulation

UAV successfully navigates to fault locations

Integrated ROS-AirSim environment for testing

Abstract

Collapsing of structural buildings has been sighted commonly and the presence of potential faults has proved to be damaging to the buildings, resulting in accidents. It is essential to continuously monitor any building for faults where human access is restricted. With UAVs (Unmanned Aerial Vehicles) emerging in the field of computer vision, monitoring any building and detecting such faults is seen as a possibility. This paper puts forth a novel approach where an automated UAV traverses around the target building, detects any potential faults in the building, and localizes the faults. With the dimensions of the building provided, a path around the building is generated. The images captured by the onboard camera of the UAV are passed through a neural network system to confirm the presence of faults. Once a fault is detected, the UAV maneuvers itself to the corresponding position where the crack is detected. The simulation is done with ROS(Robot Operating System) using the AirSim environment which initializes ROS Wrappers and provides an integrated interface of ROS and AirSim to work with, The UAV is simulated in the same.