Postgraduate Diploma in VIO and Robust Localisation in GNSS-Denied Areas
Online 800-hour Postgraduate Diploma in VIO and Robust Localisation in GNSS-Denied Areas. 8 modules covering ISO 26262:2018, ISO 21448:2022 (SOTIF) and OpenVINS. 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 scenarios and causes of GNSS loss.
Apply visual geometry to motion estimation.
Implement visual-inertial odometry systems.
Increase the robustness of VIO under adverse conditions.
Localise the vehicle on prior maps.
Integrate complementary localisation sources.
Validate localisation in areas without GNSS coverage.
Who it's for
- Localisation engineer who wants to specialise in VIO and Robust Localisation in GNSS-Denied Areas.
- Computer vision engineer who wants to specialise in VIO and Robust Localisation in GNSS-Denied Areas.
- Robotics engineer who wants to specialise in VIO and Robust Localisation in GNSS-Denied Areas.
- Sensor fusion engineer who wants to specialise in VIO and Robust Localisation in GNSS-Denied Areas.
- SLAM researcher who wants to specialise in VIO and Robust Localisation in GNSS-Denied Areas.
- Embedded software engineer who wants to specialise in VIO and Robust Localisation in GNSS-Denied Areas.
- Engineering or science graduates seeking to enter the automotive sector.
What you'll work with
- ISO 26262:2018
- ISO 21448:2022 (SOTIF)
- ISO 23374-1:2023
- EN 16803-1:2020
- Reglamento ONU n.º 157
- ISO 34503:2023
- IEEE 802.15.4z-2020
8 modules · 800 h
1.1Tunnels, car parks and urban canyons1.2GNSS loss, degradation and spoofing1.3Continuity requirements1.4Alternative navigation sensors1.5Dead reckoning with odometry1.6Infrastructure-supported localisation1.7Taxonomy of localisation methods1.8Performance metrics1.9Maximum admissible time without correction1.10Case study: GNSS losses on a route
2.1Camera models and projection2.2Feature detection and tracking2.3Epipolar geometry and essential matrix2.4Triangulation2.5PnP and pose estimation2.6RANSAC and robust estimation2.7Bundle adjustment2.8Monocular and stereo visual odometry2.9Direct versus indirect methods2.10Laboratory: stereo visual odometry
3.1IMU pre-integration3.2MSCKF-based VIO3.3Optimisation-based VIO3.4OKVIS and VINS-Mono3.5OpenVINS3.6Initialisation and observability3.7Sliding windows and marginalisation3.8EuRoC and TUM-VI datasets3.9Online estimation of time offset3.10Laboratory: OpenVINS on EuRoC
4.1Variable lighting and darkness4.2Rejection of dynamic objects4.3Low-texture environments4.4Motion blur and rolling shutter4.5IMU failures4.6Detection of estimation failure4.7Safe reinitialisation4.8Event and thermal cameras4.9Use of lines and planes as features4.10Practice: VIO with dynamic objects
5.1Visual maps and relocalisation5.2Place recognition with NetVLAD5.3Localisation in LiDAR maps5.42D-3D correspondences5.5Lightweight semantic maps5.6Underground car parks5.7Updating the localisation map5.8Accuracy versus map cost5.9Day and night appearance changes5.10Laboratory: visual relocalisation in a map
6.1Radar odometry6.2UWB and beacons6.3Vehicle and wheel model6.4Magnetic maps6.55G signals for localisation6.6Multisensor fusion with factor graphs6.7Outdoor-to-indoor transition6.8Integrity without GNSS6.9Adaptive source selection6.10Practice: fusion of VIO and wheel odometry
7.1Ground truth reference systems7.2ATE and RPE metrics7.3Tunnel trials7.4Real-time embedded execution7.5Safety requirements for localisation7.6SOTIF analysis of localisation7.7Reference urban datasets7.8Performance report7.9Long-duration and drift testing7.10Case study: validation in an underground car park
8.1Chosen GNSS-free scenario8.2Sensor selection8.3VIO system configuration8.4Relocalisation strategy8.5Fusion with complementary sources8.6Accuracy assessment8.7Robustness analysis8.8System documentation8.9Report and presentation8.10Final review with the tutor
How you'll learn
Fully 100% online training on the SEIUM Institute campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the enrolment period, which makes it compatible with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is OpenVINS, VINS-Fusion, ROS 2, OpenCV, GTSAM, in free, academic or evaluation versions. Tests are studied using real VIO evaluation procedures in tunnels and car parks, visual relocalisation on a prior map, and fusion of VIO with wheel odometry. 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 scenarios and causes of GNSS loss.
Apply visual geometry to motion estimation.
Implement visual-inertial odometry systems.
Increase the robustness of VIO under adverse conditions.
Localise the vehicle on prior maps.
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 Spanish to follow technical standards documentation.
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 consists of 800 hours in total, spread over 6 to 8 months. That is an average of 10 to 15 hours per week, compatible with a full-time job.
You will work with OpenVINS, VINS-Fusion, ROS 2, OpenCV, GTSAM. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
A SEIUM Institute own diploma upon passing continuous assessment and the integrating project. It is in-house training, not an official Ministry qualification.
Yes. Modules passed in a course or Postgraduate Diploma in the same area are recognised towards the advanced programme. Check the recognition policy when enrolling.
Related programmes
Postgraduate Diploma in Map-Based Prediction and Danger Hotspots
Online 800-hour Postgraduate Diploma in Map-Based Prediction and Danger Hotspots. 8 modules covering ISO 21448:2022 (SOTIF), ISO/PAS 8800:2024 and PyTorch. Assigned tutor and open enrolment.
Postgraduate Diploma in External Signalling (eHMI) and Passenger Acceptance
Online 800-hour Postgraduate Diploma in External Signalling (eHMI) and Passenger Acceptance. 8 modules covering ISO/TR 23049:2018, SAE J3134 and Unity. Assigned tutor and open enrolment.
Postgraduate Diploma in Non-Conventional Cameras: Event/Thermal/Multispectral
Online 800-hour Postgraduate Diploma in Non-Conventional Cameras: Event/Thermal/Multispectral. 8 modules covering ISO 21448:2022 (SOTIF), ISO 26262:2018 and OpenCV. Assigned tutor and open enrolment.
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships