Domain randomization course in aerospace AI
Online course of 300 hours in domain randomization in aerospace AI. 6 modules covering the simulation-to-reality gap, visual randomisation, dynamics randomisation, advanced methods, and validation and deployment, applying the EASA AI Concept Paper Issue 2, Regulation (EU) 2024/1689 and ISO/IEC 23894:2023 with NVIDIA Isaac Sim, Microsoft AirSim and PyTorch, with an assigned technical tutor.
Domain randomization course in aerospace AI — studying from the United States
The United States leads global aerospace, anchored by clusters in Seattle, Wichita, Hartford, Huntsville and the Houston area. Major employers such as Boeing, Lockheed Martin, RTX and GE Aerospace drive demand for engineers in airframes, propulsion, avionics and systems integration. Urban air mobility and commercial drone operations are expanding quickly, creating new roles in eVTOL design, airspace integration and UAS operations. Civil and military programs both rely heavily on certified design, testing and airworthiness processes, making this a strong field for engineers seeking complex, high-impact work.
Fees for the United States: US$610 (US Dollars), with instalments and employer sponsorship available.
Relevant bodies in the United States
Typical roles
Questions from the United States
Which professional bodies in the United States recognize engineers in aerospace, and does a private qualification help with licensing?
Aerospace engineering in the US is supported by bodies such as the American Institute of Aeronautics and Astronautics (AIAA) and ABET, which accredits engineering degree programs. Professional Engineer (PE) licensure is granted by individual state licensing boards, not by a federal body. SEIUM's qualifications are private and not state degrees, so they do not by themselves lead to PE licensure. Whether they are recognized for any purpose is decided by employers or the relevant professional body.
Do US employers in aerospace, drones or space value a private engineering postgraduate qualification?
Hiring in US aerospace and space companies, including defense contractors and drone firms, typically weighs accredited degrees, licenses, security clearances and hands-on experience heavily. A private online qualification is judged case by case by each employer, and its value depends on the skills it demonstrates and the candidate's track record. It should be seen as a way to build specialist knowledge rather than a guaranteed credential for any role.
Can I realistically study this from the United States while working full time, and how is it paid for?
The programmes are fully online and taught in English, so you can study from home and no student visa is needed. A master's requires about 1,900 hours, a postgraduate diplomas about 800 hours, and specialist courses about 300 hours, so planning weekly hours is essential. Fees can be paid in instalments, and some employers sponsor staff training, which you should confirm with your own employer.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Understand the causes of the gap between simulation and reality.
Design visual randomisations with suitable ranges.
Apply dynamics randomisation to flight models.
Use advanced methods such as ADR and domain adaptation.
Validate transfer through hardware testing and progressive trials.
Document generalisation in line with EASA guidance.
Develop an aerospace AI system made robust through randomisation.
Who it's for
- Machine learning engineers training models in simulation.
- Aerial robotics engineers.
- Reinforcement learning researchers.
- Simulation developers.
- Computer vision engineers.
- Autonomy engineers for drones and spacecraft.
- Engineering or science graduates aiming to join the drone and UAS sector.
What you'll work with
- EASA Artificial Intelligence Concept Paper Issue 2 (EASA guidance for machine learning applications)
- Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
- ISO/IEC 23894:2023 (AI risk management)
- ISO/IEC 22989:2022 (AI concepts and terminology)
- ISO/IEC 23053:2022 (framework for AI systems using machine learning)
- ISO/IEC TR 24029-1:2021 (assessment of the robustness of neural networks)
- NVIDIA Isaac Sim
- Microsoft AirSim
- Unreal Engine
- PyTorch
- Stable-Baselines3
6 modules
1.1Learning in simulation for aerospace systems1.2Causes of the sim2real gap1.3Domain adaptation versus randomisation1.4Generalisation and training distribution1.5Historical examples in robotics1.6Risks in critical applications1.7Transfer metrics1.8Simulators and their fidelity1.9Computational cost of variation1.10Case study: transfer failure in a drone
2.1Random textures and materials2.2Lighting and shadows2.3Camera position and parameters2.4Distractor objects2.5Noise, blur and artefacts2.6Weather conditions2.7Structured randomisation2.8Tools in Unreal and Isaac Sim2.9Automatic labelling2.10Lab: visual randomisation of a runway scene
3.1Mass and inertia parameters3.2Uncertain aerodynamic coefficients3.3Actuator delays and noise3.4Sensor noise and biases3.5Wind, gusts and turbulence3.6Friction and contacts during landing3.7Physically plausible variation ranges3.8Identification of real parameters3.9Curriculum-based randomisation3.10Practical exercise: flight policy with randomised dynamics
4.1Automatic domain randomisation (ADR)4.2Adversarial randomisation4.3Bayesian optimisation of distributions4.4Unsupervised domain adaptation4.5Combination with real data4.6Meta-learning and fast adaptation4.7Robust policies and robust control4.8Uncertainty estimation4.9Policy distillation4.10Workshop: ADR versus uniform comparison
5.1Hardware-in-the-loop testing5.2Progressive flight testing5.3Out-of-distribution monitoring5.4EASA requirements for machine learning5.5Coverage of the operational domain5.6Robustness and stress testing5.7Traceability of training data5.8Documentation of generalisation5.9Lessons from real deployments5.10Case study: visual landing of a drone
6.1Definition of the aerospace task6.2Simulation environment6.3Design of the randomisation6.4Model training6.5Evaluation in a real or surrogate domain6.6Robustness analysis6.7Comparison of strategies6.8Technical documentation6.9Report and presentation6.10Final project: final review with the tutor
How you'll learn
Training is 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within the intake, so the programme is compatible with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is NVIDIA Isaac Sim, Microsoft AirSim, Unreal Engine, PyTorch and Stable-Baselines3, in free, academic or evaluation versions. Tests are studied on real procedures: a visual runway detector trained on randomised scenes, a drone control policy robust to wind and sim2real evaluation with flight data. Assessment is continuous by module, plus the final integrating project.
Standards covered: EASA Artificial Intelligence Concept Paper Issue 2, Regulation (EU) 2024/1689, ISO/IEC 23894:2023, ISO/IEC 22989:2022, ISO/IEC 23053:2022, ISO/IEC TR 24029-1:2021.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- No prior qualification is required.
- Internet connection and a computer capable of running the programme software.
- English sufficient to read technical standards.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 300 hours over 3 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with NVIDIA Isaac Sim, Microsoft AirSim, Unreal Engine, PyTorch, Stable-Baselines3, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute certificate, awarded on passing the continuous assessment and the final project. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
No prior qualification is required; you need an internet connection, a computer capable of running the programme software and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Orbital dynamics simulation course
Online course of 300 hours in orbital dynamics simulation. 6 modules covering classical orbital mechanics, perturbations, numerical propagation, manoeuvres and transfers, and orbit determination and space…
Course on international space law
Online course of 300 hours in international space law. 6 modules covering the UN space treaties, ITU spectrum and orbit coordination, national space legislation, sustainability and…
Wind turbine inspection course using UAVs
Online course of 300 hours in UAV inspection of wind turbines, structured in 6 modules covering failure modes, sensors, automated flight planning, damage analysis and condition-based…
More in Aerospace, UAM, Drones & Space
All Aerospace, UAM, Drones & Space programmes → · How to apply · Fees & financing · Scholarships