| Supervisor | CVLab, Mathieu Salzmann |
| Primary Contact | Andrew Price |
| Type of Project | Master thesis, 1 student |
| Duration | 1 Semester |
Recommended
This project is suitable for a student interested in the space sector, hands on experiments, and/or electromagnetic radiation.
Context
CVLab and the Space Centre are currently engaged in research supporting deploying machine learning algorithms on edge devices in-orbit. This includes power constraints, bandwidth constraints, explainable AI, and improving fault-tolerance of machine learning algorithms.
With funding secured from ESA and the Swiss Space Office, we will perform some radiation experiments at CERN or the PSI Proton Irradiation Facility. A machine learning algorithm will be deployed to multiple edge devices and exposed to radiation for validation against simulated conditions. When exposed in such a manner, single event upsets can cause bit flips in the algorithm resulting in reduced performance or even outright failure.
Project scope
The student will support the scheduling and performance of radiation experiments and subsequent validation against simulated results. The student will develop an understanding of each of three hardware devices to analyze the propagation of faults through the device.
Expected outcomes
-
Completion of proton radiation experiments on three different edge devices (GPU, CPU and FPGA).
-
Thesis / report.
List of tasks and tentative planning
-
Familiarize self with literature; effect of radiation on hardware.
-
Support Radiation Experiments.
-
Analyze fault propagation through the devices.
-
Comparison of experimental results to simulated results.
Requirements
-
Excellent python programming; C is an asset
-
Experience with FPGAs or Verilog is an asset
-
Independent methodical worker, ability to troubleshoot
-
Good communication skills in English
Type of Work
20% Theory, 40% Experiments, 30% Analysis, 10% Documentation
Contact
Andrew Price, [email protected]
References
-
Sources of Single Event Effects in the NVIDIA Xavier SoC Family under Proton Irradiation https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9897236
-
Proton Evaluation of Single Event Effects in the NVIDIA GPU Orin SoM: Understanding Radiation Vulnerabilities Beyond the SoC https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10616076
-
Using ensemble learning to improve radiation tolerance of CNNs in space applications https://zenodo.org/records/13885495