Threat Analysis

AMDC has 10 years experience in the analyses of all kinds of air threats, based on open sources. Our special focus is on

˙Ballistic Missiles
˙Hypersonic Missiles
˙Anti-Ship Missiles
˙Small Unmanned Aircraft Systems

Our analyses begin with the estimation of technical data, based on the technological development status of the threat element. Based on these data we calculate the performance with own simulation tools or develop appropriate 3- or 6-DoF-simulations. In addition we are able to calculate or measure Radar Cross Sections and IR-signatures.

In the area of small Unmanned Aircraft Systems (UAS < 150 kg) we examine the kinematic performance of typical airframe configurations like fixed wing, delta wing, x-wing, multicopter and monocopter. For this purpose we develop simulations and build high performance UAS to perform flight tests, mainly for validation purposes. We can also provide or develop automatic target systems for all kinds of small UAS airframes.

Flight performance evaluation with multicopter

Close

Air Defence System Conception and Analysis

A Ground Based Air Defence (GBAD) System consists of the following main subsystems:

˙BMC3I (Battle Management, Command, Control, Communication, Intelligence)
˙Sensors
˙Effectors

AMDC specialists have more than 20 years experience in all subsystems of GBAD Missile Systems. The conception of a new GBAD Missile System begins with the definition of the operational requirements. This includes mainly the protection mission and the air threat to be covered.

Based on the threat analyses, a first system concept is developed and adequate functional requirements are derived. The next step covers mainly the performance analysis, based on calculation and simulation tools and the assessment of the GBAD system concept. This includes the consideration of the GBAD Missile System as part of a superordinate air defence architecture. Dependent on the assessment results, the system concept is changed or further developed in more detail.

Currently AMDC focuses on concepts for Counter-UAS systems. On the future battlefield, a lot of small Unmanned Aircraft Systems (< 20 kg) will be used for different missions. This might include autonomous combat UAS, based on AI-applications. Since this threat is growing very quickly, C-UAS defence systems become more and more important.

The robust defence against Small UAS is difficult, because of the small size of these UAS, which makes them hard to detect. AMDC specialists believe that advanced radars with good clutter suppression and classification functionalities are best suited for C-UAS systems. These radars – potentially complemented with small reconnaissance UAS – can provide a reliable detection of small UAS. The advanced radar of C-UAS systems used for area defence should be combined with laser, missiles or interceptor UAS to provide a reliable protection.

Close

Counter-UAS Applications

In the last decades Unmanned Aircraft Systems (UAS) have gained high acceptance and application variety in both: military institutions and paramilitary organizations. With a low radar cross section, low infrared signature, high autonomy and swarming capabilities they represent a significant threat to current military assets. Hence, the activities of AMDC GmbH in the field of Counter-UAS applications extend from providing Class 1 Unmanned Aircraft Target Systems (UATS) for training purposes to the research on potential C-UAS Effectors.

Unmanned Aircraft Target System

CWe offer UA Target Systems with excellent performance characteristics:
˙ Autonomous flight
˙ High precision, low altitude flight
˙ Flight safety system onboard

Flight performance evaluation with multicopter

Counter-UAS Effectors

We research and develop new approaches to encounter the UAS threat, given by low-cost and easily available Unmanned Aircraft (UA).

In the future, laser systems might be the backbone for Counter-UAS systems. However C-UAS-laser systems are not yet available and they are complex and heavy.

C-UAS system with Interceptor-UA

From our point of view, in certain cases the use of a Interceptor-UA could be beneficial for the defence against small drones. The interceptor-UA could be guided to the target by ground based sensors or even by a human being. After approaching the target it would use an AI-onboard system to detect and attack the small drone. All phases of the defence can be under the control of a ground operator.

Our experimental Interceptor-UA platform provides high-maneuvering capabilities (> 4 g) and a top speed of > 40 m/s to intercept all kinds of Class-1 UA with a total mass of up to 25 kg. It can operate at ranges of up to 5 km from the deployment position.

Interceptor-UA in flight

The main advantages of Interceptor-UA are the potential use in urban terrain and the low system price in comparison to high performance weapons. With an appropriate impact mechanism, the risk of collateral damage will be very low.

In addition such an Interceptor-UA can be used for supplementary applications, like reconnaissance or monitoring, supported by AI onboard systems.

In November 2020 first tests on target engagement were performed. These included engagements of hovering but also slowly maneuvering / evasive targets. Within the flight campaign crucial functions of the entire system and especially navigation and control algorithms were verified.

Close

AI-based Military Object Recognition

The applications for AI are increasing not only in the civilian sector, but also in the military domain. Object detection, classification and tracking are some of the relevant applications for defence purposes.

Dataset for Military Objects

Training an AI model to detect military objects requires an extensive dataset. The dataset must contain a large number of labelled images. As there often is only limited open source data available, we developed a synthetic training data generation pipeline to create the necessary datasets.

Whenever possible, we complement the synthetically generated training data with as many real and manually labelled images as available, to increase the accuracy of the trained AI model.

Sample Synthetic Images

Object Detection

AMDC Military Object Detection is based on state-of-the-art Object Detection Model Architectures, such sas YOLO, SSD or FasterRCNN, which we carefully modify and customly train to satisfy the challenging requirements of military applications. Our models are specifically optimized to provide a very high accuracy and, at the same time, allow for sufficient refresh rates on current embedded systems, such as NVidia Jetson Modules or the latest FPGAs.

Object Detection in Sample Images

Tank Detection

Starting in 2018 AMDC develops and trains object detectors that can classify tanks along with other objects such as people, trucks, cars, motorcycles, and others. The video on the right shows the “Proof of Concept”, detecting tanks in different publicly available footage.

Proof of Concept

Close