Unreal Engine 5 Simulations of Solar Plant Inspections by Unmanned Aerial Systems with Robot Operating System 2
This paper presents a high-fidelity simulation system for solar plant inspections using Unmanned Aerial Systems. It integrates Unreal Engine 5 for realistic visuals, AirSim for drone physics and sensors and Robot Operating System 2 for algorithm development. The system allows testing of inspection algorithms in a realistic virtual environment, improving the development of computer vision and object detection solutions. A case study using ArduPilot Flight Control Unit, Canny Edge Detection and PID control demonstrates its effectiveness.
Authors
- Fabio Andrade (ORCID: https://orcid.org/0000-0001-5599-8080)
- Mariane R. Petraglia (ORCID: https://orcid.org/0000-0002-9451-3522)
- Agnar Holten Sivertsen (ORCID: https://orcid.org/0000-0003-3905-130X)
- G. L. G. Gonzáles (ORCID: https://orcid.org/0000-0002-0071-1246)
- Carlos Alberto Correia
- Alessandro R. L. Zachi (ORCID: https://orcid.org/0000-0002-5671-5588)
- Marcos G. L. Moura (ORCID: https://orcid.org/0009-0006-0197-8651)
- Luis Albuquerque (ORCID: https://orcid.org/0009-0009-1867-8446)
- Lucas Clarino
Institutions
- Universidade Federal do Rio de Janeiro (BR)
- University of South-Eastern Norway (NO)
- NORCE Research AS (NO)
- Federal Center for Technological Education of Minas Gerais (BR)
Publication Details
- Journal
- IFAC-PapersOnLine
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1016/j.ifacol.2025.09.198
- Primary Topic
- Robotics and Sensor-Based Localization
- Type
- article
- Field-Weighted Citation Impact
- 0.00