Advancing Underwater Vision for 3D Phase 2 (AUV3D-P2)

"Safe and efficient construction, operation and decommissioning of subsea assets is critically important to UK and worldwide energy production. This is particularly true for offshore renewable energy where cost efficiencies are necessary to deliver clean power that is cost competitive with other low carbon systems and at an affordable scale. From construction to decommissioning, underwater survey provides the data to monitor condition, predict asset life and ensure the environment is protected. We aim to deliver a step change in efficiency and safety by delivering live, dense, 3D point cloud data from small, Remotely Operated Underwater Vehicles. This will enable smaller vessels to be used with fewer crew, no divers, and removing the need to put people at risk. Compared to traditional visual survey, 3D data allows accurate measurement and repeatable, reliable metrics for asset condition monitoring and automatic monitoring from autonomous underwater vehicles (AUVs). Ultimately, live 3D enables accurate navigation for fully autonomous inspection AUVs reducing manpower and increasing efficiency yet further. Currently, AUVs do not possess the detailed mapping and localisation required for visual inspection work. Quality 3D visual data is also a prerequisite to applying artificial intelligence and deep learning solutions to 3D images thereby enabling greater autonomy and reliably repeatable measurements.

AUV3D Phase 2 continues from the successful phase-1 project, which saw Rovco develop and demonstrate technical feasibility of live underwater 3D reconstruction from vision. This took place in the Offshore Renewable Energy Catapult's Blyth test facilities, where a dry dock with test targets was used to test and evaluate the system. For phase-2, the goal is to extend and improve on this both in terms of the underpinning technology and with more representative testing both in test tank and at sea.

The prototype developed in Phase-1 enables innovative real-time underwater 3D survey from video, and for phase-2 we extend this into a more complete solution, considering integration with additional sensors and the delivery of live survey data to shore.

By demonstrating the software and hardware necessary to produce live 3D data from cameras in the challenging and extreme subsea environment we enable the development of a complete vision based underwater Robotic Artificial Intelligence (RAI) survey solution. This is vital to create small, capable, intelligent autonomous vehicles and allow more efficient survey with fewer people in harm's way."