Welcome 🇪🇺

Welcome to the 14th issue of the European Resilience Newsletter and thank you to those who already subscribed! Uwe and Jack (more about us at the end) started this newsletter to accelerate the building of the European DefenceTech ecosystem and fill a critical gap in European Resilience. We will keep the content bite-sized, frequent and free. We also openly invite guest content creators to contribute (see below for details on how to join). Our goal is to build an ecosystem of founders, operators, investors, and industry experts who are dedicated to enhancing European resilience through technology.

This time we welcome Gunin Singh as a guest author who writes about the counter drone stack. Gunin is completing his MSc in Analytics and Management at London Business School, has a degree in Mechanical Engineering from the Imperial College London and he we was a 1st Lieutenant Officer in the Singaporean Army working hands on with tactical drones.

In this three part series on the counter drone stack, we start with an introduction into drone detection towers. In the next issues we will deep dive into with real world applications and case studies as well as market demands and trends.

The Counter Drone Stack - Understanding Drone Detection Towers 🚀🌐

In the rapidly evolving landscape of modern warfare and security, the proliferation of drones has ushered in a new era of technological challenges and opportunities. The advent of unmanned aerial systems (UAS) in military applications has not only transformed the dynamics of surveillance and combat but also necessitated the development of sophisticated drone detection and countermeasure technologies. As drones become increasingly integral to national defence strategies, as seen in the conflict in the Ukraine and in other bases around the world, the importance of reliable drone detection systems, particularly drone detection towers, has surged to the forefront of security considerations.

Drone detection towers represent a critical frontline defence against the unauthorised use of drones, providing a blend of surveillance, detection, and, in many cases, countermeasures to neutralise potential threats. These systems harness a range of technologies—from radar and Radio-Frequency (RF) analysis to acoustic sensors—to identify and track unmanned aerial vehicles (UAVs) in a variety of environments and operational contexts. The development and deployment of these towers are a testament to the ongoing innovation in the field, reflecting both the growing complexity of drone technology and the diverse threats they pose.

Understanding Drone Detection Towers

The evolution of drone detection towers traces back to the rapid proliferation of drones and the subsequent need for airspace security enhancements. Initially, these systems were rudimentary, focusing mainly on detecting large, manned aircraft (e.g. Zeppelins in World War 1), with the very first detection tower using acoustic mirrors to reflect and detect sound via a microphone and a pair of headphones. [1] Amidst technological progress, manned aircraft have transitioned to UAVs like the Predator, and a new age of commercial drones have flooded the market in recent years. Drones have become more compact, affordable, and widely used. Moreover, the technology adopted, incorporating advanced radar, acoustic sensors, and camera systems to identify the smaller signature of drones, has also become more sophisticated. Over time, the integration of artificial intelligence and machine learning has significantly improved detection accuracy, enabling the differentiation between drones and other objects such as birds. Today's drone detection towers are sophisticated, capable of tracking multiple drones simultaneously, and are pivotal in safeguarding critical infrastructure, airports, and public events from unauthorised drone activities.

Drone detection towers can sit on a spectrum of detection and counter-UAS solutions. They can be fixed or mobile. The most basic form of drone towers function as detectors, indicating to the operator of the presence of a drone in the vicinity. Detection towers with counter UAS solutions are drones that can detect and employ countermeasures by deploying some or a combination of solutions. Every drone tower needs to know where an enemy/hostile drone is before deploying any countermeasures. The detection mechanisms are often a combination of the following [2]:

1. Radio Frequency (RF) Analysers: Detect and analyse drone-to-controller communications, identifying drone models and sometimes MAC addresses.

2. Optical Sensors (Cameras): Utilise light across wavelengths for day and night detection, with advancements in resolution and AI-powered detection.

3.  Infrared: Identifies and tracks drones based on their visual signature.

4. Acoustic Sensors (Microphones/Cameras): Detect drone noise, offering direction and rough triangulation.

5. Radar: Uses radio energy for object detection, with capabilities for constant tracking and handling multiple targets.

Each aforementioned detection method in isolation, has its limitations. As such, a combination of sensors are used in conjunction to mitigate such individual limitations. The aggregation of this sensor data is done using sensor fusion, a process of combining sensor data from various sources. The resulting output has less uncertainty, that would be possible when these sensors were used individually.

The flow map (Figure 1) breaks down the data processing journey into five distinct stages for perception and decision-making tasks. Initially, raw data is gathered from a diverse array of sensors. This data undergoes refinement in the second stage, where it is filtered and adjusted for spatial and temporal alignment, alongside uncertainty modelling. The refined data moves to the third stage for feature extraction, object detection, and clustering, creating detailed object representations including size, shape, and colour. The fourth stage focuses on identifying objects through their behaviours or unique characteristics, establishing a comprehensive understanding of their interactions. This nuanced information across the four stages is pivotal for the fifth stage, where decision-making processes are informed. Each stages’ output either contributes to enhancing perception or directly informs the decision-making layer, ensuring a cohesive and detailed analysis of sensor data. [3]

One of the key advancements in sensor fusion is the transition from traditional algorithms to deep learning-based approaches. Traditional sensor fusion methods have relied on statistical and probabilistic models to manage data imperfections such as inaccuracy and uncertainty. These methods also include knowledge-based methods (e.g., fuzzy logic), interval analysis methods, and evidential reasoning methods​​. However, the rise of deep learning has introduced new possibilities for sensor fusion, offering improved performance by leveraging complex neural network architectures to process and fuse data from various sensors. Deep learning approaches, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have become particularly prominent in autonomous driving applications and now in drones and drone detection, providing enhanced capabilities for environmental perception, localisation, and mapping​​. [3] [4] [5] [6]

The variety of counter-UAS mitigation strategies post-detection by drone towers encompasses both kinetic and non-kinetic solutions, tailored to specific scenarios and threats. These strategies aim to neutralise or mitigate the potential risks posed by unauthorised drones in sensitive or protected areas. Below is a list of possible solutions either in operation or in testing:

Sources: [7] [8]

The choice of strategy depends on several factors, including the specific security requirements, the environment in which the drone tower operates, the nature of the drone threat, and the legal and ethical considerations regarding drone mitigation. Integrating multiple countermeasures allows for a more robust defence against a wider range of UAS threats, enhancing the security posture of sensitive sites and infrastructures.

Part 2 coming soon!

The Baltic DefenseTech Network - Techchill 2024 🇱🇻

Jannic and I attended #Techchill2024 in Riga last week. I was on a panel with Nicholas Nelson from MD One Ventures, Kadri Tammai from NATO DIANA Estonian Accelerator, and Tomass Pildegovičs, from the NATO Strategic Communications Centre of Excellence. We discussed how investors see dual-use, what are the applications on the battlefield, and whether we would ever see an Anduril or Plantir scale VC-backed defence tech company in Europe.

Jannic was a member of a startup jury where saw strong pitches and innovative ideas from baltic startups. He was especially impressed by the quality of mission driven founders in the resilience space, building everything from secure communication platforms in demanding environments to underwater drones.

News That Caught Our Attention 👀

• Quantum Systems opens drone factory and development hub in Ukraine - Defence Industry Europe

• Google will provide AI to the military for disaster response - Washington Post

• From garage to global: new program fast-tracks Ukrainian defence startups - tech.eu

• Defence tech startups should avoid these 5 pitfalls - Global Corporate Venturing

Passionate and want to contribute? 👩🏻‍💻

The European Resilience Tech Newsletter is always looking for regular and guest authors, writers, reporters, content creators etc. If you like what you read, you are passionate about improving European resilience regardless of your background and want to contribute, just reach out to us!

European Resilience Tech Newsletter Team

Uwe Horstmann co-founded Project A Ventures in 2012 as General Partner and has built Project A to be a leading European early stage investor with over $1bn USD under management and having backed 100+ founders. In addition to Project A, Uwe serves as Reserve Officer in the German armed forces and advises the German Ministry of Defence in digital transformation issues.

Jack Wang is a software engineer turned product driven tech investor and joined Project A in 2021 to lead the firm’s deep tech investing, which have grown to include DefenceTech. Prior to joining Project A, Jack worked in a variety of organisations such as Amazon and Macquarie Group across Australia, US and UK / Europe. Jack holds a MBA from London Business School and Bachelors of Engineering (Bioinformatics, 1st) from UNSW, Australia.

Jannic Meyer joined Project A initially contributing to what is now known as the Project A Studio, partnering with founders at the pre-idea stage, where he covered a variety of topics ranging from energy infrastructure to dual-use robotics and led our investment in ARX Robotics. He is now part of the investment team at Project A covering all things resilience.

Project A Ventures is one of the leading early-stage tech investors in Europe with offices in Berlin and London. In addition to 1 billion USD assets under management, Project A supports its 100+ portfolio companies with a platform team over 140 functional experts in key areas such as software and product development, business intelligence, brand, design, marketing, sales and recruiting. Project A have backed founders of Trade Republic, WorldRemit, Sennder, KRY, Spryker, Catawiki, Unmind and Voi as well as founders building in European Resilience: