Better radar detection of hypersonic missiles, cyber cross-domain technology for defence systems and Graph Neural Networks (GNN) in tactical communications were areas of research worthy of the European Defence Agency’s first ever EDA Research, Technology, and Innovation Papers Awards. EDA rewarded three original and valuable defence-related papers covering technologies, processes and applications for enhanced future defence.
The winning entries have come up with ideas which, if implemented between now and 2035, could contribute to enhance specific EU defence capabilities.
EDA Deputy Chief Executive André Denk told the European Defence Innovation Days event, where the prizes were awarded: “EDA wants to attract young talent in the defence sector and retain unique specialised skills. We believe that this initiative will stimulate young innovators to widen their network.”
EDA received 20 submissions from many different institutions, mostly academia.
The list of winners, in alphabetical order are:
Pepijn COX, from the Radar Technology Department at TNO in The Hague (Netherlands), main author of a paper titled "Enhanced Radar Detection of Hypersonic Threats through the Application of Irregular Waveforms and Advanced Processing". Cox told the award ceremony that the ability to detect hypersonic missiles earlier would win valuable time to defend against such weapons. The combination of novel technologies extends the detection range, giving more reaction time.
Vasiliki DEMERTZI, from the Computer Science Department, School of Science International Hellenic University (Greece), main author of a paper titled “Prescriptive Auto-Maintenance Architecture for Trustworthy Cross-Domain-Implementation in Tech-Defence”. Demertzi told the award ceremony that her work in real-time data analytics could allow military systems to operate at peak performance, also improving their reliability and potentially allowing faster and more effective repairs.
Johannes LOEVENICH, from Secure Communication & Information at Thales (Germany), main author of a paper titled “GNN-based Deep Reinforcement Learning with Adversarial Training for Robust Optimization of Modern Tactical Communication Systems”. Loevenich told the award ceremony that his research sought to create a game-like environment and handle massive amounts of data from tactical systems to solve complex problems, for example in routing and cyber security.