Back to search

IKTPLUSS-IKT og digital innovasjon

Safe and Autonomous Subsea Intervention (SAFESUB)

Alternative title: Sikker og autonom subsea intervensjon (SAFESUB)

Awarded: NOK 12.0 mill.

There is an increasing industry push for smart robotic solutions able to operate in complex and unstructured scenarios. To meet this need, we will in the SAFESUB project move beyond the research front and build vital interdisciplinary competence in the intersection of Artificial Intelligence (AI) and robotics to safely increase the autonomy of robotic interventions and reduce operational risk. More specifically, we will develop novel AI-based uncertainty-aware methods for 3D vision, object localization and manipulation. The main SAFESUB research challenge is how to make the methods robust to uncertainty by efficiently estimating - and utilizing - the aggregated uncertainty of AI predictions throughout a sensing, perception, and control pipeline. By solving this challenge, we will reliably determine the risk associated with robotic interventions and thus safely increase the autonomy of interventions in complex and high-risk operations. We will verify and demonstrate the project results on industry-relevant use cases with intervention with Remotely Operated Vehicles (ROVs). We will carry out both field trials in the North Sea and underwater laboratory experiments. SAFESUB results will be developed and show-cased as close collaboration between the research partners SINTEF and NTNU, and the industry partners Imenco and IKM. Together, the partners constitute a long-track record on research and field-trials with autonomous underwater robots (SINTEF, NTNU and IKM Subsea), a marked leader in underwater camera solutions (Imenco) and a developer of autonomous vehicles with the first-ever commercially deployed resident ROV (IKM). SAFESUB focuses on subsea intervention for ocean industries such as oil and gas, offshore wind and aquaculture. However, the project results will be applicable to other fields requiring safe robotic intervention, such as aerial drones, healthcare, above-water inspection and maintenance, manufacturing, and space.

SAFESUB will move beyond the research front and build vital interdisciplinary competence in the intersection of Artificial Intelligence (AI) and robotics to safely increase the autonomy of robotic interventions and reduce operational risk. This is motivated by the increasing industry push for smart, robotic solutions able to operate in complex and unstructured scenarios. To meet this need, we will develop novel AI-based uncertainty-aware methods for 3D vision, object localization and manipulation. The main SAFESUB research challenge is how to make the methods robust to uncertainty by efficiently estimating - and utilizing - the aggregated uncertainty of AI predictions throughout a sensing, perception, and control pipeline. By solving this challenge, we will move beyond the state-of-the-art and enable us to reliably determine the risk associated with robotic interventions and thus safely increase the autonomy of interventions in complex and high-risk operations. We will verify and demonstrate the project results on industry-relevant use cases with intervention with Remotely Operated Vehicles (ROVs). We will carry out both field trials in the North Sea and underwater laboratory experiments. SAFESUB results will be developed and show-cased as close collaboration between the research partners SINTEF and NTNU, and the industry partners Imenco and IKM. Together, the partners constitute a long-track record on research and field-trials with autonomous underwater robots (SINTEF, NTNU and IKM Subsea), a marked leader in underwater camera solutions (Imenco) and a developer of autonomous vehicles with the first-ever commercially deployed resident ROV (IKM). SAFESUB focuses on subsea intervention for ocean industries such as oil and gas, offshore wind and aquaculture. However, the project results will be applicable to other fields requiring safe robotic intervention, such as aerial drones, healthcare, above-water inspection and maintenance, manufacturing, and space.

Funding scheme:

IKTPLUSS-IKT og digital innovasjon