UK-led project aims for AUVs that can learn from mistakes

A UK-led European project is aiming to build truly intelligent autonomous underwater vehicles (AUVs) that can learn from their mistakes and adapt mid-mission to changing circumstances.

Ultimately the aim is have an AUV deployed almost continuously underwater around oil rigs that will identify and fix problems before they occur, preventing costly downtime.

The three-year FP-7 PANDORA project gathers researchers from Heriot-Watt University and King’s College London alongside academic colleagues from Italy and Greece with an industrial steering group that includes BP, SubSea7 and SeeByte.

Any PANDORA prototype would have three core operational capabilities: structure inspection using sonar and video; cleaning marine growth using water jets; and finding, grasping and turning valves.

Remotely operated vehicles (ROVs) are the workhorses of offshore inspection, repair and maintenance. However, they require up to 6km of cable and the constant presence of a support boat, which must be commissioned and mobilized specifically for ROV deployment.

AUVs have long been seen as a desired piece of technology in offshore environments. They could be launched opportunistically from a ship or permanent FPSO(Floating Production Storage and Offloading)unit while the ship continues its journey.

However, there are some inherent challenges in removing the umbilical cable from underwater robots. Electromagnetic waves including radio waves, do not propagate far underwater at the sort of frequencies required to send useful information.

So rather than trying to communicate with the robot as ROVs do, one solution is to delegate decision making to the AUV robot itself.

‘It’s quite a tough thing to do because you have to sense where you are relative to the valve, you have to control the forces that the manipulator exerts on the valve and position everything quite accurately — you don’t have a guy there doing that,’ said Prof David Lane of Heriot-Watt.

Such AUVs have been investigated for around 10 years now, with some models appearing commercially, although the technology is far from mature.

‘They do okay provided they know the task and the environment very well, but what tends to happen is something isn’t quite right, you’re not in the position you thought, the valve isn’t the way it was supposed to be, then the robot tries to do its mission and fails,’ said Lane. ‘At the moment the systems can’t really deal with that, they cry for help or abort.’

The aim of PANDORA is to build systems that can recognise when they’ve failed.

‘So they’re trying to carry out a task but something has gone wrong — then they can learn from that and figure out how to change what they’re doing in order to succeed,’ Lane said.

A complete version would hopefully be able to maintain a continuous presence submerged around rigs and other offshore structures. It would resurface only to re-charge its batteries and download data.

‘The business case is more about doing regular inspections, being more aware of what’s going on and therefore having a lower likelihood of downtime, which could cause a ceasing in production,’ Lane said.

Nevertheless, Lane conceded that ROVs will still always be needed – certainly in the foreseeable future – since they provide live, real-time images and video back to the surface.

SeeByte, a spinout from the Ocean Systems Lab at Heriot-Watt, has around 10 years’ experience developing offshore robotics technologies. It has a strategic partnership with service provider SubSea7, and Lane added the platform is in place for commercialisation of technology from PANDORA.