# Multi-Domain Robot Swarm for Industrial Mapping and Asset Monitoring: Technical Challenges and Solutions

## TL;DR

This paper presents a multi-domain robot swarm system combining ground and aerial robots to monitor industrial assets like gauge meters with high accuracy.

## Contribution

The novel integration of heterogeneous robotic systems for industrial mapping and asset monitoring with real-time collaboration capabilities.

## Key findings

- The system achieved 84% accuracy in detecting meter gauges.
- It reached 87.5% accuracy in reading gauge indicators using the paddle OCR algorithm.
- The system demonstrated effective navigation and collaboration in complex environments.

## Abstract

Industrial environments are complex, making the monitoring of gauge meters challenging. This is especially true in confined spaces, underground, or at high altitudes. These difficulties underscore the need for intelligent solutions in the inspection and monitoring of plant assets, such as gauge meters. In this study, we plan to integrate unmanned ground vehicles and unmanned aerial vehicles to address the challenge, but the integration of these heterogeneous systems introduces additional complexities in terms of coordination, interoperability, and communication. Our goal is to develop a multi-domain robotic swarm system for industrial mapping and asset monitoring. We created an experimental setup to simulate industrial inspection tasks, involving the integration of a TurtleBot 2 and a QDrone 2. The TurtleBot 2 utilizes simultaneous localization and mapping (SLAM) technology, along with a LiDAR sensor, for mapping and navigation purposes. The QDrone 2 captures high-resolution images of meter gauges. We evaluated the system’s performance in both simulation and real-world environments. The system achieved accurate mapping, high localization, and landing precision, with 84% accuracy in detecting meter gauges. It also reached 87.5% accuracy in reading gauge indicators using the paddle OCR algorithm. The system navigated complex environments effectively, showcasing the potential for real-time collaboration between ground and aerial robotic platforms.