AI-based Interference Detection

Beyond detection: a system that thinks for itself

In an increasingly digitally connected world, technical systems across a wide range of industries rely on interference-free communication and precise signal processing. However, interference—whether intentional or unintentional—poses a growing challenge: it can disrupt processes, compromise safety, and cause economic damage.

Interference detection is therefore a key issue in areas such as mobility, aviation, defense, and critical infrastructure.

However, classic, rule-based methods reach their limits in real multipath environments: Reflections and signal mirroring distort measurement results and make reliable localization difficult.

Our solution takes a fundamentally different approach:

It is based on artificial intelligence (AI) that not only recognizes, but also learns, adapts, and improves with each implementation even in complex environments with multipath effects. 

Adaptive

Our AI automatically adapts to new environments, antennas and device configurations - for reliable detection even in mobile or dynamic scenarios.

Data-efficient

Compact AI models, fast processing, and minimal data transfer ensure low latency, low memory requirements, and high scalability.

Self-learning

New sources of interference are detected and characterized with just a few examples. Recurring patterns are given a unique ID—for quick response and targeted countermeasures..

Accurate

Our AI provides accurate information on the direction, distance, and power of interference sources—for informed decisions and rapid localization..

Our service offer

From research to application - we accompany you every step of the way

Detection

Reliable interference detection in real time

Localization

Precise determination of direction and distance – even in complex environments

Characterization

Detailed analysis of interference sources for targeted countermeasures

Fields of application

Cross-industry application – from mobility to defense

GNSS & Navigation

Detection and classification of GNSS interference such as jamming and spoofing – mobile and stationary.

Mobility

Legally compliant documentation of sources of interference on roads and in vehicle fleets.

Flight safety

Resilient communication through adaptive jammer characterization – for increased safety in air traffic.

Defense

Reliable localization and mitigation of interference signals—for real-time protection of critical systems.

Projects

 

DARCY

GNSS interference detection with machine learning and crowdsourcing

 

DARCII

Characterization and recognition of GNSS interference through federated learning

 

PaiL

Evaluation of model- and data-driven methods for locating GNSS disrupters in multipath environments

Publications

2025

Lucas Heublein, Thorsten Nowak, Tobias Feigl, Jaspar Pahl, and Felix Ott:

GNSS Jammer Direction Finding in Dynamic Scenarios Using an Inertial-based Multi-Antenna System

DGON Inertial Sensors and Applications (ISA)

 

Lucas Heublein, Christian Wielenberg, Thorsten Nowak, Tobias Feigl, Christopher Mutschler, and Felix Ott:

Attention-Based Fusion of IQ and FFT Spectrograms with AoA Features for GNSS Jammer Localization

In: IEEE Radar Conference

 

Ott F., Heublein, L., Feigl, T., Rügamer, A. & Mutschler, C.,

Metric-Based Few-Shot Learning With Triplet Selection for Adaptive GNSS Interference Classification

In: J-ISPIN, April 2025

 

Raichur, N., Heublein, L., Feigl, T., Nowak, T., Rügamer, A., Mutschler, C., & Ott, F. (2025):

Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning

In: Trans. on Machine Learning Research (TMLR), April 2025

 

Manjunath, H., Heublein, L., Feigl, T., & Ott, F. (2025):

Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization

In: IEEE Wireless Communications and Networking Conference (WCNC) March 2025

 

Heublein, L., Feigl, T., Nowak, T., Rügamer, A., Mutschler, C., & Ott, F. (2025):

Evaluating ML Robustness in GNSS Interference Classification, Characterization & Localization 

In: ICL-GNSS

2024

Gaikwad, N. S., Heublein, L., Raichur, N. L., Feigl, T., Mutschler, C., & Ott, F. (2024):

Federated Learning with MMD-based Early Stopping for Adaptive GNSS Interference Classification

In: IEEE/IFIP Network Operations and Management Symposium (NOMS) Mai 2024

 

Heublein, L., Feigl, T., Rügamer, A., & Ott, F. (2024):

Achieving Generalization in Orchestrating GNSS Interference Monitoring Stations Through Pseudo-Labeling

In: DGON Positioning and Navigation for Intelligent Transport Systems (POSNAV)

 

Ott, F., Heublein, L., Raichur, N. L., Feigl, T., Hansen, J., Rügamer, A., & Mutschler, C. (2024):

Few-Shot Learning with Uncertainty-Based Quadruplet Selection for Interference Classification in GNSS Data

In: 2024 International Conference on Localization and GNSS (ICL-GNSS) (pp. 1-7)

 

Heublein, L., Raichur, N. L., Feigl, T., Brieger, T., Heuer, F., Asbach, L., ... & Ott, F. (2024):

Evaluation of (Un-) Supervised Machine Learning Methods for GNSS Interference Classification with Real-World Data Discrepancies

In: Proceedings of the 37th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2024) (pp. 1260-1293)