AERIAL-CORE: AI-Powered Aerial Robots for Inspection and Maintenance of Electrical Power Infrastructures

TL;DR

AERIAL-CORE addresses the safety, cost, and regulatory challenges of inspecting and maintaining electrical power infrastructures by presenting an integrated, autonomous system that combines morphing aerial platforms, long-range perception, aerial manipulation, and aerial co-working with human operators. The approach unifies BVLOS inspection, line-perching-based maintenance, tool delivery, and safety-focused multi-UAV coordination under a single workflow, validated through extensive BVLOS demonstrations and real maintenance tasks. Key innovations include morphing platforms (e.g., Marvin-5-M and Morpho) for data-quality and energy efficiency, online LIDAR-based semantic mapping (FAST-LIO2 with GNSS), perching-enabled maintenance with MLMP and a dual-arm system, and gesture-driven co-working with ACWs. The results indicate significant reductions in inspection time and human exposure, suggesting strong potential for scalable, low-risk I&M of power grids and a path toward future drone-enabled infrastructure networks.

Abstract

Large-scale infrastructures are prone to deterioration due to age, environmental influences, and heavy usage. Ensuring their safety through regular inspections and maintenance is crucial to prevent incidents that can significantly affect public safety and the environment. This is especially pertinent in the context of electrical power networks, which, while essential for energy provision, can also be sources of forest fires. Intelligent drones have the potential to revolutionize inspection and maintenance, eliminating the risks for human operators, increasing productivity, reducing inspection time, and improving data collection quality. However, most of the current methods and technologies in aerial robotics have been trialed primarily in indoor testbeds or outdoor settings under strictly controlled conditions, always within the line of sight of human operators. Additionally, these methods and technologies have typically been evaluated in isolation, lacking comprehensive integration. This paper introduces the first autonomous system that combines various innovative aerial robots. This system is designed for extended-range inspections beyond the visual line of sight, features aerial manipulators for maintenance tasks, and includes support mechanisms for human operators working at elevated heights. The paper further discusses the successful validation of this system on numerous electrical power lines, with aerial robots executing flights over 10 kilometers away from their ground control stations.

Figures (10)

• Figure 1: AERIAL-CORE intelligent aerial robotic system for inspection and maintenance of large infrastructures.
• Figure 2: (Top) MARVIN-5-M. (Bottom) (A) Morpho in hovering flight with different wing configurations. (B) Morpho in hovering experiments. Demonstration of the pitch angle related to wind speed and energy consumption.
• Figure 3: (Left) Output of the event-based tracker dietsche2021powerline. Our algorithm assigns to each tracked line a unique ID. (Right) Output of the RGB-based tracker xing2023autonomous. Our algorithm assigns to each tracked line its inclination (positive or negative), a confidence score, and a unique ID (not visualized).
• Figure 4: (Top) Autonomous inspection of ATLAS power grid by multi-UAV team: planned trajectories (top-left), a snapshot of the video streamed by one multi-rotor when a plastic foreign object hung from the line is detected (top-center) and autonomous landing on charging station (top-right). (Bottom) The resulting 3D map was obtained in the final AERIAL-CORE experiments.
• Figure 5: (Top) Aerial deployment. (Middle) devices installation. (Bottom) aerial retrieval of the dual arm rolling robot operating on the power line.