Michael Petry

E-Mail:	michael.petry@tum.de
Telefon:	+49 89 3179 4285
Raum:	9377.01.113
Anschrift:	Airbus Defence and Space GmbH Michael Petry Abteilung Telecom Processing Germany (TSTCG-TL2) Willy-Messerschmitt-Straße 9 82024 Taufkirchen

Research Interests

Deep Learning
Information Theory
AI-designed PHY communication
5G/6G Non-Terrestrial-Network (NTN)
ML-augmented Network orchestration
FPGA AI Deployment
Finite-Element-Method physical simulations

Awards

IEEE ComSoc FOUR-MINUTE-THESIS (4MT) COMPETITION - Third Price

Projects

Machine Learning for Telecommunication Satellites (MaLeTeSa): This DLR-sponsored project aims to explore how artificial intelligence can benefit telecommunication satellites. It comprises two components. The first component focuses on exploring and developing machine-learning-based software and algorithms in the fields of wireless communication signal processing, anomaly detection, and network orchestration, while the other one aims at developing a space-grade System-on-Chip-based AI-Processor on which the algorithms shall be deployed on-board the satellite. The main focus of my doctorate is both developing AI-based RF algorithms and implementing them on the hardware platform. The result is a hybrid processing pipeline that comprises both neural networks and classic DSP components, which is then realized on the heterogeneous hardware platform. By distributing the processing steps between FPGA, AI-Engines (ASIC-like vector processors), and CPU, and ensuring optimal data transfer between those components, an efficient implementation is achieved.
Artificial Intelligence for Anti-Jamming (AJAI): In this ESA-sponsored project we explore how artificial intelligence-based techniques can be applied to achieving a robust satellite communication link that is particularly resilient to external signal jamming attacks. By focusing on partial band, multi-tone, follower, and sweeper jammer scenarios, we design a waveform comprising an AI-assisted feedback loop and implement it on the space-grade AI-processor hardware which is developed within the MaLeTeSa project (see above).
5G Autosat KI: In this DLR-sponsored project we implement a 3GPP standard-compliant 5G basestation (gNodeB) cellular stack on a System-on-Chip (FPGA, AI-Engines, CPU)-based space-grade hardware platform and augment it with AI processing capabilities. After completing the AI-related steps of this project (designing, training, and deployment of a proof-of-concept traffic prediction algorithm based on 5G user meta-data), I am focusing on extending the hardware setup with a high-performance RF interface to improve maximum communication speeds.

Publications

Petry, M., Parlier, B., Koch, A., & Werner, M. (2024). Auto-Regressive RF Synchronization Using Deep-Learning. IEEE International Conference on Machine Learning for Communication and Networking. [PDF]
Kiprit, G. N., Koch, A., Petry, M., & Werner, M. (2024). Graph Neural Networks for Anomaly Detection in Spacecraft. Proceedings of the First Joint European Space Agency SPAICE Conference / IAA Conference on AI in and for Space. [PDF]
Koch, A., Petry, M., & Werner, M. (2024). AI-augmented Anomaly Detection Pipeline for Real-Time Onboard Processing of Spacecraft Telemetry. Proceedings of the First Joint European Space Agency SPAICE Conference / IAA Conference on AI in and for Space. [PDF]
Koch, A., Petry, M., & Werner, M. (2024). Extended Framework and Evaluation for Multivariate Streaming Anomaly Detection with Machine Learning. Proceedings of MulTiSA 2024, the 1st Workshop on Multivariate Time Series Analytics in Conjunction with ICDE 24, 1–8. [PDF]
Petry, M., Koch, A., & Werner, M. (2023). Envisioning Physical Layer Flexibility Through the Power of Machine-Learning. GC Wkshps. [PDF]
Petry, M., Wuwer, G., Koch, A., Gest, P., Ghiglione, M., & Werner, M. (2023). Accelerated Deep-Learning Inference on the Versal adaptive SoC in the Space Domain. 2023 European Data Handling & Data Processing Conference (EDHPC), 1–8. https://doi.org/10.23919/EDHPC59100.2023.10396011 [Online]
Koch, A., Krstova, A., Hegwein, F., De Lera, M. C., Ales, F., Petry, M., Ali, R., Mallah, M., Hili, L., Ghiglione, M., & Werner, M. (2023). On-Board Anomaly Detection on a Flight-Ready System. 2023 European Data Handling & Data Processing Conference (EDHPC), 1–4. https://doi.org/10.23919/EDHPC59100.2023.10395967 [PDF] [Online]
Koch, A., Dax, G., Petry, M., Gomez, H., Raoofy, A., Saroliya, U., Ghiglione, M., Furano, G., Werner, M., Trinitis, C., & Langer, M. (2023). Reference Implementations for Machine Learning Application Benchmark. 2023 European Data Handling & Data Processing Conference (EDHPC), 1–3. https://doi.org/10.23919/EDHPC59100.2023.10396582 [PDF] [Online]
Koch, A., Petry, M., Ghiglione, M., Raoofy, A., Dax, G., Furano, G., Werner, M., Trinitis, C., & Langer, M. (2023). Machine Learning Application Benchmark. 20th ACM International Conference on Computing Frontiers (CF ’23), May, 2023, Bologna, Italy. https://doi.org/10.1145/3587135.3592769 [PDF]
Petry, M., Gest, P., Koch, A., Ghiglione, M., & Werner, M. (2023). Accelerated Deep-Learning inference on FPGAs in the Space Domain. 20th ACM International Conference on Computing Frontiers (CF ’23), May, 2023, Bologna, Italy. https://doi.org/10.1145/3587135.3592763 [PDF]
Petry, M., Koch, A., Werner, M., Hoch, U., Helfers, T., & Wiest, R. (2023). Machine Learning on Telecommunication Satellite. DATA SYSTEMS IN AEROSPACE - 2023 DASIA. [PDF]

Other Publications

Jewani, Y., Petry, M., Sanchez-Arias, R., Amezcua-Correa, R., & Habib, M. S. (2024). Accurate Loss Prediction of Realistic Hollow-Core Anti-Resonant Fibers Using Machine Learning. IEEE Journal of Selected Topics in Quantum Electronics, 30(6: Advances and Applications of Hollow-Core Fibers), 1–8. https://doi.org/10.1109/JSTQE.2024.3366476
Petry, M., & Habib, M. S. (2023). Random Design Variations of Hollow-core Anti-resonant Fibers: A Monte-Carlo Study. IEEE Journal of Selected Topics in Quantum Electronics, 1–10. https://doi.org/10.1109/JSTQE.2023.3321298
Petry, M., & Habib, M. S. (2023). Post-fabrication performance of nested hollow-core fibers with perturbed cladding structures. In B. Witzigmann, M. Osiński, & Y. Arakawa (Eds.), Physics and Simulation of Optoelectronic Devices XXXI (Vol. 12415, p. 124150L). SPIE. https://doi.org/10.1117/12.2647494 [Online]
Petry, M., Amezcua-Correa, R., & Habib, M. S. (2022). Random misalignment and anisotropic deformation of the nested cladding elements in hollow-core anti-resonant fibers. Opt. Express, 30(19), 34712–34724. https://doi.org/10.1364/OE.465329 [Online]
Petry, M., Markos, C., Correa, R. A., & Habib, M. S. (2022). Multi-mode guidance in enhanced inhibited coupling hollow-core anti-resonant fibers. Conference on Lasers and Electro-Optics, JTh3B.42. https://opg.optica.org/abstract.cfm?URI=CLEO_SI-2022-JTh3B.42 [Online]
Petry, M., & Habib, M. S. (2022). Random cladding misalignments and anisotropic deformations in nested hollow-core fibers. Optica Advanced Photonics Congress 2022, JW3A.55. https://opg.optica.org/abstract.cfm?URI=SOF-2022-JW3A.55 [Online]
Petry, M., & Habib, M. S. (2022). Analyzing random design imperfection in hollow-core anti-resonant fibers. Optica Advanced Photonics Congress 2022, JW3A.21. https://opg.optica.org/abstract.cfm?URI=Networks-2022-JW3A.21 [Online]
Petry, M., & Habib, M. S. (2022). Impact of random structural perturbations on Hollow-Core Anti-Resonant Fibers. 2022 IEEE Photonics Society Summer Topicals Meeting Series (SUM), 1–2. https://doi.org/10.1109/SUM53465.2022.9858234
Petry, M., & Habib, M. S. (2021). Anisotropic Nested Hollow-core Fiber Designs. 2021 IEEE Photonics Conference (IPC), 1–2. https://doi.org/10.1109/IPC48725.2021.9592982