Automated Inspection Robots for Surface, Aerial and Underwater Substructures

ongoing

AEROSUB will develop world-class robotic solutions for different wind energy operating scenarios – fixed and floating offshore wind farms, promoting innovations for operation and maintenance (O&M) procedures to foster the competitiveness and sustainability of renewable energy production in challenging environments. AEROSUB will demonstrate the added value of robotics deeply integrated with advanced AI and data analytics technologies and their potential of reducing the eCO2 emissions of O&M operations by up to 15M tonnes, enabling cost savings by 2,400€/MW/year and lowering the levelized cost of electricity (LCOE) of offshore wind energy by 2.5%. By deploying an orchestration of multiple robotic platforms, including Uncrewed Fleet Carrier (UFC), Unmanned Surface Vehicle (USV), Remotely Operated Vehicles (ROVs), long endurance aerial drones (UAS), and Unmanned Aerial Vehicles (UAVs), and optimizing human-robot and robot-robot collaboration, AEROSUB aims to reduce the on-site humans’ exposure to dangerous and strenuous environments. Large scale pilots related to monitoring, inspection, cleaning, and maintenance of structures below and above water line will be performed autonomously by AEROSUB solutions, which requires introducing AI-based features for enhancing perception and on-platform decision-making capabilities, improving collaborative navigation, manipulation, and mission planning. AEROSUB is proposing the first fully unmanned robotic solution for both aerial and underwater inspection and intervention, demonstrated in real offshore wind farm, to show an increased O&M operational efficiency of 40%, reducing of the associated downtime by 60% as well as the risk exposure of workers by 90%. Digital twin (DT) and AI solutions for automated information analysis of operational data, collected by remote robotic platforms in >30 operations, will increase the reactivity, responsiveness and intelligibility of the O&M operations: reducing the human burden by 80% to monitor