Page 30: of Offshore Engineer Magazine (Jul/Aug 2020)

29 31

ROBOTICS of data transfer. During the ARGOS

Challenge we experienced black spots

Kris Kydd, with the Wi-Fi network even on small sites because of interference caused by

Head of Robotics, metallic equipment. Our latest robot

Total E&P UK design has a dual router offering both

K 4G and WiFi capability.

You mention machine learn- ing quite a lot. Could you ex- plain what you mean by ma- chine learning?

Machine learning, in this respect, al- lows for automated inspection capabili- ties. The robot captures images of vari- ous types of equipment, which allows us to generate a large data set upon which machine learning algorithms can be de- veloped and tested. As the robot captures more images, the dataset grows, which can be re-fed into the machine learning model allowing the algorithms to be re- tested, which in turn allows its predic- tions to become increasingly accurate.

Are there any remaining technology gaps or areas where you see “Our major objective is for the more advances can be made? robots to successfully operate

During the early stages, we focused more on the safety as- autonomously in an ATEX pects of the hardware (e.g specifying that the design had to be capable of working in a potentially explosive atmosphere environment. We will test – ATEX) rather than the safety aspects of the software. We robotic fundamentals such worked with Saft, Total’s battery specialist af?liate, to meet as mobility, navigation over this challenge. However, there is no point in specifying safety a range of surfaces such as aspects for the hardware if you do not have the software equiv- alent. Assuring the safe behavior of an autonomous robot in gratings, gravel, and stairs.” a complex environment is of paramount importance for ac- ceptability. The wider workforce needs to know they can trust these robots to make the correct decisions. In order to gain either during or after its mission, the robot uploads its in- spection data to the cloud data store in the machine learning that trust, those autonomous decisions need to be transparent and explainable. We are currently working on this and recog- module. This data is then processed through machine learn- nize how important it is before we can deploy at scale. ing algorithms. It also means making the interface for the hu- man operator as simple as possible, ?rst through a mission

When do you expect Stevie to head up to Shet- planning app and second through a Dashboard for presenting land, and what are the trials going to involve? the results of the mission.

Robotics for oil and gas is still in its infancy, so it’s very 4G/LTE is also much more standard these days. It’s a more recent mobile broadband internet access offering exciting for Total to be starting site acceptance testing at the higher capabilities in connectivity as it offers a higher rate Shetland Gas Plant this September. Our major objective is 30 OFFSHORE ENGINEER OEDIGITAL.COM