Panagiotis T. Karfakis

Panagiotis T. Karfakis

Portfolio

iFROG project

I have been the Project Engineer & Manager of the iFROG project during my employment at InnotecUK, Cambridge, UK. An amphibious robot capable of working in teams to clean and inspect monopiles above water level and up to 60 metres below (~6 bar), has successfully completed trials at the ORE Catapult’s National Renewable Energy Centre in Blyth Northumberland,UK for a duration of 3.5 years. The development started from scratch and we had to go through the conceptualization and iterative developments of a hybrid robotic platform suitable for the offshore wind industries. Fortunately, we managed to break through the hurdles of this massive engineering effort across all teams including Mechanical, Electrical and Software, generating two highly robust robots for non destruvtive testing (NDT) and water jet cleaning. A project funded by innovate uk from 2018 until 2021 and at the final stage, iFROG was deployed on monopile structures on land and in sea at ORE Catapult’s national renewable energy centre in Blyth, Northumberland, UK for real-world demonstrations of its capabilities. As part of the project, collaborated with Brunel’s Innovation Center (BIC), The Welding Institute (TWI) and Offshore Renewable Catapult (OREC) has generated valuable experience in engineering solutions for offshore wind assets and has ensured that iFROG meets the industry requirements specifications. This platform served as a stepping stone towards commercially ready robotic platforms for inspection and maintenance. The problem that we were tackling at the time concerned the race towards net zero targets, the acceleration of offshore wind growth and pushing of farm sites into ever deeper waters. Hence the operational landscape was envisaged to change too, as robotics and autonomous systems offer a ticket to reduced human deployment offshore, a chance to reduce costs and to improve asset integrity through predictive maintenance.The outputs of the project consist of: (i) a amphibious robotic team that can navigate turbine monopole walls using a magnetic adhesion above/below water (IP68), (ii) conduct non-destructive ultrasonic testing of monopole surfaces for corrosion loss of steel wall integrity, (iii) biofouling removal, (iv) Predictive analytics by combining inspection data with material properties and asset history and degradation pathways.
Link to project video

ROBFMS project

The ROBFMS project was the robotic product ready version of the iFROG project that I had the responsibility of managing as the Project Engineer from 2020 to 2021. Standing amidst powerful waves in briny waters, offshore wind turbines can suffer from rust, corrosion and eventually cracking of their foundations. Over time, they also accumulate weighty masses of algae and other microorganisms that can create drag, impede technicians trying to work on them and ultimately undermine and reduce turbines lifetimes at sea. Sending divers to the depths of the ocean for maintenance and cleaning of subsea structures is a risky business that entails long delays, as seas are in unsafe conditions for much of time, due to the harsh environment in which marine energy assets operate. An estimated 65% of the total lifetime operating costs are related to inspection and maintenance equipment, so operators have to combat corrosion, fouling and fatigue of the structures. The nature of the operating environment including the splash zone represent major challenges for traditional inspection techniques such as divers and ROV’s. ROBFMS represents the latest stage of this development, a robotic platform for external cleaning of steel structures used in the offshore wind and marine industries and can carry out not just a visual check, but a full NDT inspection carrying a varying payload of different equipment as attachments and cleaning of problematic bio fouling. It can do this quickly enough and with great precision while repeatability is the aim of any maintenance tasks. ROBFMS is the latest chapter in this success story the project funded by innovate uk linked long-standing partners such as Brunel Innovation Center (BIC) with the European Marine Energy Center (EMEC), the world’s first and leading facility for testing wave and tidal energy converters in Orkney Islands Scotland. It has inherited all the leading features from its predecessor (iFROG): (i) easy to control remote operation, (ii) reliable adhesion performing flawlessly on external steel surfaces of large structures and (iii) subsea design, (iv) ruggedized cage for even more compact transportion to offshore using small vessels and minimal crews. The improved robotic platform can still carry a significant payload and is fully compatible with NDT probes and pressure jetting-based cleaning systems. Used as a base it can create a team of inspection robots that perform various operational tasks on site and offer remote control by inspection teams and data collection capabilities. These smart robotic assistants could help offshore asset operators protect human workers from hazardous environments and effectively predict major faults using the collective data. they are capable of contributing to the maintenance schedule optimization and as a result to a reduction in inspection and maintenance costs leading to decrease to consumer energy prices.
Link to project video

5GSmartFact project

At part of this MSCA-ITN doctoral study, as a Robotics Researcher, I play a key role in contributing to the 5GSmartFact objectives, emphasizing on mobile robot 5G-enabled localization systems to support industrial Internet-of-Things (IIoT) applications. Absolute localization of mobile robots without knowledge of an environment map, typical in many I4.0 domains, rely on technologies such as global navigation satellite system (GNSS), whose accuracy and precision fall short for many robotic tasks, and has limited applicability indoors. Some recent works addressed the localization accuracy of 5G networks found to be at the cm-level. Adding this to other prospects in 5G networks, such as increased bandwidth, or device-to-device communication, paves the way towards the development and deployment of 5G-enabled field robots’ localization. Currently, there exists a plethora of different use case-specific technologies for positioning, e.g., based on ultra-sound, cameras, laser, LiDAR, ultra-wideband or Bluetooth, which are complex to manage and costly to deploy altogether. Also, legacy technologies, such as RFID, though quite cost-efficient, are too rigid and inflexible. What is missing to date is a highly flexible and powerful positioning solution that is suitable for a wide range of different use cases and requirements and that is ideally integrated into the already deployed connectivity infrastructure, thus avoiding the need to set up and operate parallel multiple networks, infrastructures, or technologies. To tackle the aforementioned challenges, the objectives for this doctoral study are as follows: 1) Analysis of user needs and requirements for the design of 5G-connected heterogeneous robotic platforms, based on 5G New Radio (NR) connectivity for pervasive localization, emphasizing on triangulation, multilateration, and fingerprinting optimization methods, as well as cooperative and multimodal-based localization. 2) Implementation of a Robot OS (ROS)-based solution for 5G Simultaneous Localization and Mapping (SLAM) approach in robotics. 3) Development of an advanced life-long localization architecture based on multimodal sensor fusion, encompassing 5G technology, possibly coupled with local ultrawide-band positioning, VLC, Global Navigation Sattelite Systems (GNSS), Inertial Measurement Units (IMU), wheel encoders, scan LiDAR and visual odometry. 4) Performance evaluation approach to assess the accuracy and precision of the 5G-based localization as a distributive multi-robot system under real-world constraints.
Link to project website