In the SEAVENTION (Autonomous subSEA interVENTION) project (2018-2021) we target to meet this goal by researching underwater robot autonomy for such subsea operations. We will develop methods and demonstrate results where Unmanned Underwater Vehicles (UUVs) understand their environment and are able to operate at a right level of autonomy while keeping the operator in the loop.
The main objective of SEAVENTION is to deliver research and competence building on robust subsea perception with active 3D sensors, automated planning for UUV intervention operations and augmented reality for UUV operator decision support.
Autonomy in underwater operations
To enable UUVs to use a right level of autonomy, SEAVENTION will:
- Develop methods for UUVs to utilize 3D sensor data to understand their environment. This includes detection and localization of 3D objects underwater based on 3D sensor data. This will include methods for Deep Learning.
- Develop techniques for automated planning such that UUVs can plan operations with human oversight, but with minimal human intervention. This will include methods for machine learning.
- Investigate the usage of augmented reality for UUV operator decision support.
SEAVENTION is a collaboration between The Research Council of Norway (project number 280934), Equinor, TechnipFMC, IKM, OCEANEERING, NTNU, and SINTEF.
The project is funded by the Research Council and the industrial partners and led by SINTEF. The industrial partners represent a value chain of equipment manufacturer, service provider, operator, and user/owner.