Master’s in Synthetic Data and Sensor Simulation Engineering
Online master's programme of 1,900 hours in synthetic data and sensor simulation engineering. 12 modules covering computer graphics for simulation, camera, LiDAR and radar modelling, environment simulators, automatic labelling, domain randomisation, generative models, closing the domain gap and synthetic tabular data under ISO 21448, ASAM OpenSCENARIO XML 1.3 and ASAM OpenDRIVE 1.8, with an assigned technical tutor.
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
Design synthetic data generation strategies.
Model cameras, LiDAR and radar in simulation.
Build scenarios with simulators and ASAM standards.
Generate high-quality automatic annotations.
Apply domain randomisation and generative models.
Close the gap between synthetic and real data.
Assess the validity and regulatory compliance of synthetic data.
Who it's for
- Synthetic data engineers building training datasets at scale.
- Sensor simulation engineers modelling cameras, LiDAR and radar.
- Perception engineers who need more and better training data.
- Computer vision engineers dealing with rare or costly-to-capture cases.
- 3D environment developers moving into simulation for AI.
- Virtual validation engineers testing perception systems in simulation.
- Engineering or science graduates looking to enter the automotive sector.
What you'll work with
- ISO 21448 (safety of the intended functionality, SOTIF)
- ASAM OpenSCENARIO XML 1.3 (dynamic driving scenario description)
- ASAM OpenDRIVE 1.8 (road network description)
- ASAM OSI 3 (Open Simulation Interface for sensor models)
- Regulation (EU) 2024/1689 (AI Act)
- Regulation (EU) 2016/679 (GDPR)
- UN Regulation No. 157 (Automated Lane Keeping Systems)
- ISO 34502 (scenario-based safety evaluation of automated driving)
- CARLA
- NVIDIA Isaac Sim
- Blender
- Unreal Engine
- SDV
12 modules · 1900 h
1.1Scarcity and cost of real data1.2Types of synthetic data1.3Physics-based simulation versus generative models1.4The domain gap between synthetic and real data1.5Use cases in vision, robotics and automotive1.6Synthetic tabular data and privacy1.7Economics of data generation1.8Risks and limitations1.9State of the art and industry1.10Case study: data strategy for a perception system
2.1The rendering pipeline2.2Rasterisation versus ray tracing2.3PBR materials and BRDFs2.4Global illumination and path tracing2.5Scenes and scene graphs2.6Scene description with OpenUSD2.7Unreal Engine and Unity2.8Procedural scene generation2.9Performance and GPU rendering2.10Lab: procedural scene in Blender with Python
3.1Pinhole camera model and distortion3.2Noise, exposure and dynamic range3.3Rolling shutter and motion blur3.4Event cameras3.5Infrared thermal cameras3.6Lens and optics simulation3.7Calibration of simulated cameras3.8Weather effects on the image3.9Validation against real cameras3.10Practical: simulating camera noise and distortion
4.1LiDAR operating principles4.2Scan patterns and resolution4.3Reflectivity and materials4.4Noise, dropouts and weather effects4.5FMCW radar principles4.6Ray-tracing radar simulation4.7Multipath and radar cross-section4.8OSI interface for sensors4.9Validation of sensor models4.10Lab: ray-tracing LiDAR simulator
5.1CARLA for autonomous driving5.2NVIDIA Isaac Sim and Omniverse5.3AirSim and aerial simulation5.4Gazebo and ROS5.5Scenarios with OpenSCENARIO5.6Road networks with OpenDRIVE5.7Traffic and pedestrian simulation5.8Simulation of industrial environments5.9Comparison of simulators5.10Workshop: scenario generation with CARLA
6.1Perfect ground truth in simulation6.2Bounding boxes, segmentation and depth6.3Optical flow and poses6.4Labelled point clouds6.5COCO and KITTI formats6.6Scene metadata6.7Quality control of annotations6.8Labelling rare cases6.9Class balance in generated data6.10Practical: segmentation dataset with automatic annotation
7.1Domain randomisation7.2Structured, context-aware randomisation7.3Variation of lighting, textures and poses7.4Distributions of scene parameters7.5Generating edge cases7.6Coverage of the operational design domain7.7Diversity metrics7.8Sampling guided by model performance7.9Large-scale datasets7.10Lab: domain randomisation for part detection
8.1Generative adversarial networks8.2Variational autoencoders for images8.3Diffusion models8.4Generation conditioned on text and maps8.5Synthetic-to-real image translation8.6Neural radiance fields8.7Gaussian splatting for realistic scenes8.8Video and 4D scene generation8.9Quality control of generated content8.10Workshop: synthetic-to-real adaptation with diffusion
9.1Unsupervised domain adaptation9.2Mixing real and synthetic data9.3Fine-tuning with little real data9.4Measuring the gap with FID and KID9.5Domain-invariant representations9.6Self-training and pseudo-labels9.7Validation on real data9.8Task-specific strategies9.9Ablation studies9.10Practical: mixed synthetic-real training
10.1CTGAN generators and copulas10.2Synthetic time series10.3Simulation of industrial processes10.4Differential privacy in synthetic data10.5Fidelity and utility metrics10.6Re-identification risks10.7Synthetic data in healthcare and finance10.8GDPR compliance10.9Open-source tools10.10Lab: synthetic tabular data with SDV
11.1Use of synthetic data under the AI Act11.2Validating perception systems with simulation11.3SOTIF and unknown scenarios11.4Credibility of simulations for type approval11.5UNECE requirements for automated driving11.6Biases introduced by simulation11.7Dataset documentation11.8Intellectual property of 3D assets11.9Synthetic data governance11.10Case study: validity argument for a synthetic dataset
12.1Defining the perception task12.2Designing the environment and sensors12.3Generating the synthetic dataset12.4Randomisation strategy12.5Model training12.6Evaluation on real data12.7Domain gap analysis12.8Conclusions on the usefulness of the dataset12.9Master's Thesis report12.10Master's Thesis: defence before a panel
How you'll learn
100% online training 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 you can combine the programme with your job.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is CARLA, NVIDIA Isaac Sim, Blender, Unreal Engine and SDV, in free, academic or evaluation versions. Real procedures are studied: generating perception datasets for autonomous driving, LiDAR and camera simulation, and synthetic-to-real domain adaptation. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: ISO 21448, ASAM OpenSCENARIO XML 1.3, ASAM OpenDRIVE 1.8, ASAM OSI 3, Regulation (EU) 2024/1689 (AI Act), Regulation (EU) 2016/679 (GDPR), UN Regulation No. 157 and ISO 34502.
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
- University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
- 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 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with CARLA, NVIDIA Isaac Sim, Blender, Unreal Engine and SDV, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. 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 in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.
A university degree in engineering, science or architecture (or equivalent professional experience), a computer able to run 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
Master’s in HPC & GPU Engineering for Simulation and AI
Online master's programme of 1,900 hours in HPC and GPU engineering for simulation and AI. 12 modules covering GPU architecture, CUDA programming, performance portability, distributed computing,…
Master’s in Real-Time Analytics and Stream Processing Engineering
Online master's programme of 1,900 hours in real-time analytics and stream processing: 12 modules covering event stream processing, distributed messaging, Apache Flink, streaming engines, real-time analytics,…
Master’s in Visual Analytics and Technical BI Engineering
Online master's programme of 1,900 hours in visual analytics and technical BI engineering. 12 modules covering visual analytics, perception and visual design, complex data visualisation, data…
More in Data, AI, Simulation & Analytics
All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships