Panagiotis T. Karfakis

Panagiotis T. Karfakis

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Blog Posts vs Time

less than 1 minute read

Published:

Blog posts are cool! But for the time being lets skip! Already involved in many things!

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

publications

A Novel Holonomic Mobile Manipulator Robot for Construction Sites

Published in International Conference Series on Climbing and Walking Robots (CLAWAR), 2018

This article describes a novel mobile manipulator robot designed to work at height on construction sites. The robot comprises a mobile platform and a scissor lifter on which an ABB 6 dof manipulator is mounted. The mobile base is characterised by holonomic kinematics, provided by a novel designed omnidirectional wheel system that can travel directly and autonomously to desired poses. The robot was successfully tested in a construction site scenario to perform drilling tasks.

Recommended citation: Gmerek, Artur & Plastropoulos, A & Collins, Peter & Kimball, Matthew & Wheatley, A & Liu, Jianwei & Karfakis, Panagiotis & Shah, Kiran & Carroll, J & Virk, Gurvinder & Sain, Amit. (2018). A Novel Holonomic Robot Manipulator for Construction Sites. In 21st International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines Robotics Transforming the Future, Panama City, Panama, 2018,9. https://core.ac.uk/download/pdf/234021207.pdf

Mooring Chain Climbing Robot for NDT Inspection Applications

Published in International Conference Series on Climbing and Walking Robots (CLAWAR), 2018

Inspection of mooring chains is an important but dangerous and costly procedure covering inspection above and below the waterline. The paper presents initial results from the RIMCAW project which aimed at designing and building an inspection robot able to climb mooring chains and deploy NDT technologies for scanning individual links thereby detecting critical defects. The paper focuses on the design and realisation of the inchworm type novel crawler developed and tested in the TWI Middlesbrough, UK water tank

Recommended citation: Kimball, Matthew & Gmerek, Artur & Collins, Peter & Wheatley, Andrew & Shah, Kiran & Liu, Jianwei & Dissanayake, Mahesh & Caroll, Jessica & Plastropoulos, Angelos & Karfakis, Panagiotis & Sattar, Tariq & Sain, Amit & Virk, Gurvinder. (2018). MOORING CHAIN CLIMBING ROBOT FOR NDT INSPECTION APPLICATIONS. https://core.ac.uk/download/pdf/234021207.pdf

A Comparative Study of Mobile Robot Positioning Using 5G NR

Published in IEEE ICRA IFRRIA Workshop, 2022

In this work we study the use of the 5G New Radio (NR) communication model for position tracking of a mobile robotic system. We have deployed the 5G NR in three different configurations in a simulated agricultural environment. We evaluate the impact of using different number of gNodeB (gNB) base stations and the increased topological complexity on the position estimation, using three different heuristic approaches. The setups consist of 5, 10 and 15 gNBs that communicate with the user equipment (UE) carried by the robot. The ground truth trajectory of the system is recorded and estimated by three meta-heuristics, namely Hyperbola Crossing points (HCP), Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). We measure the performance according to statistical metrics such as the average prediction time, the average Euclidean Distance (ED) and their standard deviations. We provide and discuss the qualitative results derived experimentally to assess the positioning capability of 5G NR for a simulated field robotics application.

Recommended citation: Panagiotis T. Karfakis, Micael S. Couceiro, David S. Portugal, & Carlos H. Antunes. (2022). A Comparative Study of Mobile Robot Positioning Using 5G NR. ICRA 2022 Workshop in Innovation in Forestry Robotics: Research and Industry Adoption (IFRRIA), Philadelphia, Pennsylvania, United States. Zenodo. https://doi.org/10.5281/zenodo.7937189 https://doi.org/10.5281/zenodo.7937189

UWB Aided Mobile Robot Localization with Neural Networks and the EKF

Published in IEEE Systems, Man and Cybernetics (SMC), 2022

This paper exploits the use of Ultra Wide Band (UWB) technology to improve the localization of robots in both indoor and outdoor environments. In order to efficiently integrate the UWB technology in existing multi-sensor architectures, such as Kalman-based, we propose two approaches to estimate the UWB position covariance values. The first approach uses statistical methods to estimate static covariance values based on data acquired a priori. The second approach adopts a neural network (NN) to capture the relationship between the positional error of the UWB data and the signal quality information, such as the Estimate Of Precision (EOP) and Received Signal Strength Indicator (RSSI). The GPS-RTK is used as ground truth and RGB-D odometry is adopted for both bench-marking and integration purposes. Position sources are fused by means of an Extended Kalman Filter (EKF). Real world experiments are conducted with a tracked mobile robot driving outdoors in a closed-loop trajectory. Results show that the NN is able to efficiently model the sensor covariances and adapt the trustworthiness of the EKF estimation, overcoming data loss by relying on the other available estimation source.

Recommended citation: P. T. Karfakis, M. S. Couceiro, D. Portugal and R. Cortesão, "UWB Aided Mobile Robot Localization with Neural Networks and the EKF," 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Prague, Czech Republic, 2022, pp. 93-99, doi: 10.1109/SMC53654.2022.9945357. https://ieeexplore.ieee.org/document/99453

Tailoring 3D Mapping Frameworks for Field Robotics

Published in IEEE ICRA IFRRIA Workshop, 2022

Mapping is an essential part for the adoption of robots in agricultural and forestry environments. Providing the robot with the ability to map its surroundings, facilitates its navigation and is necessary for implementing obstacle avoidance, without human interference. Herein we present the challenges of outdoor environments, present an overview of existing mapping frameworks and then evaluate their suitability for field applications. Two widely used mapping frameworks, OctoMap and RTAB-Map are analyzed within the Robot Operating System (ROS) ecosystem and a parametric study is carried out in order to assess their performance, under both simulated and real-world constraints. Finally this work aims to be utilized as a deployment reference guide for mobile robotic applications in outdoor environments.Mapping is an essential part for the adoption of robots in agricultural and forestry environments. Providing the robot with the ability to map its surroundings, facilitates its navigation and is necessary for implementing obstacle avoidance, without human interference. Herein we present the challenges of outdoor environments, present an overview of existing mapping frameworks and then evaluate their suitability for field applications. Two widely used mapping frameworks, OctoMap and RTAB-Map are analyzed within the Robot Operating System (ROS) ecosystem and a parametric study is carried out in order to assess their performance, under both simulated and real-world constraints. Finally this work aims to be utilized as a deployment reference guide for mobile robotic applications in outdoor environments.

Recommended citation: Karfakis, P.T.; Couceiro, M.S.; Portugal, D.; Antunes, C.H. A Comparative Study of Mobile Robot Positioning Using 5G-NR. IEEE International Conference on Robotics and Automation (ICRA) Workshop in Innovation in Forestry Robotics: Research and Industry Adoption, Philadelphia, PA, USA, 2022. https://labs.ri.cmu.edu/ifrria-icra-2022/call-for-papers/

NR5G-SAM: A SLAM framework for Field Robotics Based on 5G New Radio

Published in MDPI Sensors Journal, 2023

Robot localization is a crucial task in robotic systems and is a pre-requisite for navigation. In outdoor environments, Global Navigation Satellite Systems (GNSS) have aided towards this direction, alongside laser and visual sensing. Despite their application in the field, GNSS suffers from limited availability in dense urban and rural environments. Light Detection and Ranging (LiDAR), inertial and visual methods are also prone to drift and can be susceptible to outliers due to environmental changes and illumination conditions. In this work, we propose a cellular Simultaneous Localization and Mapping (SLAM) framework based on 5G New Radio (NR) signals and inertial measurements for mobile robot localization with several gNodeB stations. The method outputs the pose of the robot along with a radio signal map based on the Received Signal Strength Indicator (RSSI) measurements for correction purposes. We then perform benchmarking against LiDAR-Inertial Odometry Smoothing and Mapping (LIO-SAM), a state-of-the-art LiDAR SLAM method, comparing performance via a simulator ground truth reference. Two experimental setups are presented and discussed using the sub-6 GHz and mmWave frequency bands for communication, while the transmission is based on down-link (DL) signals. Our results show that 5G positioning can be utilized for radio SLAM, providing increased robustness in outdoor environments and demonstrating its potential to assist in robot localization, as an additional absolute source of information when LiDAR methods fail and GNSS data is unreliable.

Recommended citation: Karfakis, Panagiotis T., Micael S. Couceiro, and David Portugal. 2023. "NR5G-SAM: A SLAM Framework for Field Robot Applications Based on 5G New Radio" Sensors 23, no. 11: 5354. https://www.mdpi.com/1424-8220/23/11/5354

teaching

Robotcraft 2022 Mentor

Undergraduate/Postgraduate course, Ingeniarius Ltd, 2022

This is a description of a teaching experience. You can use markdown like any other post.