Postgraduate Diploma in Sensor Robustness and Input Cleaning/Degradation
Online 800-hour Postgraduate Diploma in sensor robustness and input cleaning/degradation. 8 modules covering ISO 21448:2022 (SOTIF), ISO 26262:2018 and PyTorch. Assigned tutor and open enrolment.
Take the controls.
Run a real engineering trade-off from this programme. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Identify degradation modes of cameras, radar and LiDAR.
Design sensor cleaning and heating systems.
Develop occlusion and dirt detection algorithms.
Improve model robustness against degraded inputs.
Implement sensor health monitoring.
Plan environmental and fault-injection tests.
Integrate sensory degradation into SOTIF analysis.
Who it's for
- ADAS sensor engineer looking to specialise in Sensor Robustness and Input Cleaning/Degradation.
- Perception engineer looking to specialise in Sensor Robustness and Input Cleaning/Degradation.
- Validation engineer looking to specialise in Sensor Robustness and Input Cleaning/Degradation.
- Functional safety engineer looking to specialise in Sensor Robustness and Input Cleaning/Degradation.
- Vehicle integration engineer looking to specialise in Sensor Robustness and Input Cleaning/Degradation.
- Machine learning specialist looking to specialise in Sensor Robustness and Input Cleaning/Degradation.
- Graduates in engineering or sciences seeking to enter the automotive sector.
What you'll work with
- ISO 21448:2022 (SOTIF)
- ISO 26262:2018
- IEC 60529
- ISO 16750-3:2023
- ISO 20653:2023
- ISO/SAE 21434:2021
- ISO 16750-4:2023
8 modules · 800 h
1.1Dirt, mud and insects on sensors1.2Ice and condensation on optics1.3Lens ageing and misalignment1.4Vibration and motion blur1.5Interference between radar and LiDAR1.6Defective pixels and thermal noise1.7Saturation and dynamic range1.8Adversarial patches and physical tampering1.9Scratches and gravel damage1.10Case study: degradation catalogue for a fleet
2.1Fluid and air cleaning architecture2.2Nozzles, pumps and reservoirs2.3Heating for windows and radomes2.4Hydrophobic and oleophobic coatings2.5Integration into vehicle design2.6Fluid consumption and activation strategy2.7Cleaning efficacy tests2.8Maintenance in robotaxi fleets2.9Noise and discomfort for occupants2.10Practice: sizing a cleaning system
3.1Reference-free image quality3.2CNN-based camera dirt detection3.3Missing LiDAR points and their interpretation3.4Radar blockage diagnosis3.5Classification of contaminant type3.6Cleaning activation decision3.7False positives and availability3.8Diagnostic requirements under ISO 262623.9Verification after the cleaning cycle3.10Lab: dirty-lens classifier
4.1Benchmarks for common corruptions4.2Augmentation with realistic degradations4.3Adversarial training4.4Robust-attention architectures4.5Prior image restoration4.6Data imputation in point clouds4.7Redundancy and fault-tolerant fusion4.8Model stress testing4.9Robustness certification against perturbations4.10Lab: evaluation with synthetic corruptions
5.1Health indicators per sensor5.2Calibration drift detection5.3Cross-sensor comparison5.4Estimation of effective visibility5.5Perception reconfiguration5.6Driver warnings in the HMI5.7Event logging and telemetry5.8Predictive sensor maintenance5.9Fleet-level health aggregation5.10Practice: multisensor health monitor
6.1Splash and mud tests6.2Rain and fog chambers6.3IP protection ratings and environmental testing6.4Vibration and thermal shock6.5Fault injection in HIL6.6Degraded scenarios in simulation6.7Quantitative acceptance criteria6.8Traceability of robustness requirements6.9On-road durability testing6.10Case study: dirt test plan
7.1Functional limitations and SOTIF7.2Derived safety requirements7.3Degraded states and safe transition7.4Cybersecurity and sensor tampering7.5Sensing safety argument7.6Field incident review7.7System update after incidents7.8Documentation for type approval7.9ODD limits by sensor state7.10Workshop: sensor limitation analysis
8.1Selection of sensor and use case8.2Modelling relevant degradations8.3Cleaning system design8.4Occlusion detection algorithm8.5Model robustness strategy8.6Test and validation plan8.7Safety argument8.8Cost and maintenance analysis8.9Report and presentation8.10Final review with the tutor
How you'll learn
100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the intake, making it possible to combine with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is PyTorch, OpenCV, CARLA, dSPACE SCALEXIO, MATLAB, in free, academic or evaluation versions. Tests are studied using real procedures for classifying dirt on camera lenses, splash testing on a LiDAR module, and sensor fault injection on an HIL bench. Assessment is continuous per module plus the final integrating project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Identify degradation modes of cameras, radar and LiDAR.
Design sensor cleaning and heating systems.
Develop occlusion and dirt detection algorithms.
Improve model robustness against degraded inputs.
Implement sensor health monitoring.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient level of Spanish to follow technical standards reading.
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 comprises 800 hours in total, spread over 6 to 8 months. That is an average of 10 to 15 hours per week, compatible with full-time work.
The course uses PyTorch, OpenCV, CARLA, dSPACE SCALEXIO and MATLAB. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
A SEIUM Institute diploma upon passing the continuous assessment and the integrating project. It is an in-house qualification, not an official title issued by the Ministry.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised towards the advanced programme. Please consult the recognition policy when enrolling.
Related programmes
Postgraduate Diploma in Semantic Cartography and Risk-Prioritised Maps
Online Postgraduate Diploma of 800 hours in Semantic Cartography and Risk-Prioritised Maps. 8 modules covering Directive (EU) 2019/1936, Directive 2008/96/CE and QGIS. Dedicated tutor and enrolment…
Postgraduate Diploma in Microsim/Macrosim and Proxy Hardware
Online 800-hour Postgraduate Diploma in Microsim/Macrosim and Proxy Hardware. 8 modules covering FMI 3.0, ASAM OSI and SUMO. Assigned tutor and open enrolment.
Postgraduate Diploma in Benches, Rigs and Tooling for Mass Calibration
Online 800-hour Postgraduate Diploma in Benches, Rigs and Tooling for Mass Calibration. 8 modules covering IATF 16949:2016, ISO 14229-1:2020 (UDS) and Minitab. Assigned tutor and enrolment…
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships