Contact Dr Dimitrios Panagiotakopoulos
Areas of expertise
- Aeronautical Systems
- Aerospace Structures
- Airworthiness
- Autonomous Systems
- Aviation Management & Operations
- Electric and Hybrid Vehicles
- Flight Physics
- Space Systems
- Vehicle Aerodynamics
- Vehicle Engineering & Mobility
Background
With over 15 years of contributions to the state-of-the-art in Air Traffic Management (ATM), currently enabling the path towards its digitalisation, Dimitri now heads the Unmanned Aircraft Systems Traffic Management (UTM) Research group at Cranfield University.
Before joining Cranfield, Dimitri worked as an ATM Systems Specialist at Air Navigation Solutions at Gatwick Airport, where he led the development of the Airport's 10-year Capacity Enhancement Roadmap to optimise and improve operations and infrastructure to enable Air Traffic Movement growth, which identified Operational Improvements from SESAR and NextGen Programmes and coordinated the different Airport stakeholders, including Airlines, Ground Handlers, Air Traffic Control to implement these solutions. During that time, Dimitri delivered a number of ATM systems to enable Airport operations and capacity growth, including an extension to its multi-lateration system, to allow a new Boeing Hangar (fitting 2 Code F aircraft) to be built without affecting operations.
Previous to this, Dimitri was a Senior Project Systems Engineer at NATS (formerly National Air Traffic Services), where he single-handedly delivered complex multi-million pounds Surveillance solutions to Airports, on time and on budget. This included the very first use of an X-band radar for windfarm mitigation in the UK.
Dimitri holds a PhD from Imperial College London on Satellite Navigation and Positioning Systems, with a thesis that developed innovative statistical algorithms to monitor and guarantee the integrity of GNSS-based position and navigation computations within safety-critical aircraft flight management systems. It was the first time Extreme Value Theory was introduced in an ATM-related field.
Research opportunities
Our Research Group is interested in leveraging emerging technological advances such as Machine Learning, data-driven solutions using smart contracts and distributed ledger technology, to enable more collaborative, efficient and optimised integrated ATM/UTM operations.
There are always opportunities for self-funded PhDs.
Contact us to find out more for funded PhD around our current and future activities.
Current activities
We are currently setting up the National Beyond Visual Line of Sight (BVLOS) Experimental Corridor (NBEC) within and around the Cranfield Airport Airspace to allow us to test and validate new Concepts, systems, procedures that enable BVLOS drone flights in non-segregated airspace. This together with our high-end simulator facilities and digital twins provides a unique live/virtual sandbox and UTM/UAM ecosystem to address the challenges that ATM/UTM integration and UAM applications present.
On-going areas of interest include:
applying deep learning and explainable AI methods in Air Traffic Management and safety-critical applications
intelligent operation-centric and risk-minimising UAS flight / contigency / emergency planning and management, de-confliction, collision avoidance solutions development
data-driven Comms, Navigation and Surveillance (CNS) signal and performance analysis to derive global quality of service in rural, semi-urban and urban contexts and ascertain optimum CNS combination for specific mission
alternative navigation mode mechanism that leverage information captured by the UAS on-board capabilities (e.g. camera, inertial navigation system (INS))
increased automation of ATM/UTM interface, including interaction with Air Traffic Control
data driven approach to Urban Air Mobility mission planning, traffic flow and capacity management.
Clients
Boeing, Airbus, SAAB, Thales,
Publications
Articles In Journals
- Alharbi A, Petrunin I & Panagiotakopoulos D. (2023). Deep learning architecture for UAV traffic-density prediction. Drones, 7(2)
- Alharbi A, Petrunin I & Panagiotakopoulos D. (2023). Assuring safe and efficient operation of UAV using explainable machine learning. Drones, 7(5)
- Souanef T, Al-Rubaye S, Tsourdos A, Ayo S & Panagiotakopoulos D. (2023). Digital twin development for the airspace of the future. Drones, 7(7)
- Alharbi A, Petrunin I & Panagiotakopoulos D. (2022). Modeling and characterization of traffic flow patterns and identification of airspace density for UTM application. IEEE Access, 10
Conference Papers
- Fraser B, Perrusquía A, Panagiotakopoulos D & Guo W. (2024). A deep mixture of experts network for drone trajectory intent classification and prediction using non-cooperative radar data
- Fraser B, Perrusquía A, Panagiotakopoulos D & Guo W. (2023). Hybrid deep neural networks for drone high level intent classification using non-cooperative radar data
- Warrier A, Al-Rubaye S, Panagiotakopoulos D, Inalhan G & Tsourdos A. (2022). Interference mitigation for 5G-connected UAV using deep Q-learning framework
- Alharbi A, Petrunin I & Panagiotakopoulos D. (2022). Traffic flow prediction for UTM application: a deep learning approach
- Doumard T, Gañán Riesco F, Petrunin I, Panagiotakopoulos D, Bennett C, .... (2022). Radar discrimination of small airborne targets through kinematic features and machine learning
- Nanos N, Kagan Isik O, Verdeguer Moreno R, Petrunin I, Panagiotakopoulos D, .... (2021). UAV path planning optimization based on GNSS quality and mission requirements
- Panagiotakopoulos D, Williamson A, Petrunin I, Harman S, Quilter T, .... (2021). Developing drone experimentation facility: progress, challenges and cUAS consideration
- Karyotakis MK, Panagiotakopoulos D, Braithwaite G & Tsourdos A. (2021). Aspects and challenges of unmanned aircraft systems safety assurance and certification for advanced operations
- Alharbi A, Petrunin I & Panagiotakopoulos D. (2021). Identification and characterization of traffic flow patterns for UTM application
- Sanchez Hernandez C, Ayo S & Panagiotakopoulos D. (2021). An explainable artificial intelligence (xAI) framework for improving trust in automated ATM tools
- Warrier A, Al-Rubaye S, Panagiotakopoulos D, Inalhan G & Tsourdos A. (2021). Seamless handover in urban 5G-UAV systems using entropy weighted method
- Alharbi A, Poujade A, Malandrakis K, Petrunin I, Panagiotakopoulos D, .... (2020). Rule-based conflict management for unmanned traffic management scenarios
- Ryan R, Al-Rubaye S, Braithwaite G & Panagiotakopoulos D. (2020). The legal framework of UTM for UAS
