Apply now
Master'sAutonomous, ADAS & Software-Defined Vehicle Applications open

Master’s in Visual-Inertial Odometry & Precise Positioning Engineering

Online master's programme of 1,900 hours in visual-inertial odometry and precise positioning engineering, structured in 12 modules covering state estimation, inertial sensors, geometric vision, VIO, high-precision GNSS, GNSS-VIO and LiDAR-inertial fusion, learning-based odometry, integrity, embedded implementation and validation, with an assigned technical tutor.

Duration1900 h
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

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.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Model inertial sensors and their errors.

02

Apply monocular and stereo visual odometry techniques.

03

Implement visual-inertial estimators.

04

Process high-precision GNSS observations.

05

Fuse GNSS, VIO and LiDAR using factor graphs.

06

Assess the integrity and robustness of navigation.

07

Develop a real-time precise positioning system.

Profile

Who it's for

  • Navigation engineers.
  • Localisation engineers.
  • 3D vision engineers.
  • GNSS systems engineers.
  • SLAM researchers.
  • Mobile robotics engineers.
  • Engineering or science graduates looking to enter the automotive sector.
Standards & tools

What you'll work with

  • ISO 26262 (functional safety of road vehicles)
  • ISO 21448 (safety of the intended functionality, SOTIF)
  • RTCM 10403.3 (differential GNSS services, RTCM 3)
  • IEEE 802.1AS (time synchronisation, gPTP)
  • ISO 8855 (vehicle dynamics coordinate systems and vocabulary)
  • ISO 23150 (sensor-to-fusion data interfaces)
  • NMEA 0183 (marine and GNSS data interface)
  • SAE J3016 (levels of driving automation)
  • ROS 2
  • GTSAM
  • RTKLIB
  • OpenCV
  • VINS-Fusion
Syllabus

12 modules · 1900 h

  1. 1.1The state estimation problem
  2. 1.2Pose representation in SE(3)
  3. 1.3Lie groups and their algebra
  4. 1.4Quaternions and rotations
  5. 1.5Gaussian noise models
  6. 1.6Filtering versus optimisation
  7. 1.7System observability
  8. 1.8ATE and RPE accuracy metrics
  9. 1.9EuRoC and KITTI datasets
  10. 1.10Case study: trajectory evaluation
  1. 2.1MEMS accelerometers and gyroscopes
  2. 2.2IMU error models
  3. 2.3Biases, scale and misalignment
  4. 2.4Allan variance
  5. 2.5IMU preintegration
  6. 2.6IMU calibration
  7. 2.7Tactical-grade IMUs
  8. 2.8Synchronisation with cameras
  9. 2.9Effect of vibrations
  10. 2.10Lab: IMU characterisation
  1. 3.1Feature detection
  2. 3.2ORB and SIFT descriptors
  3. 3.3KLT feature tracking
  4. 3.4Epipolar geometry in motion
  5. 3.5PnP pose estimation
  6. 3.6Bundle adjustment
  7. 3.7Monocular visual odometry
  8. 3.8Stereo visual odometry
  9. 3.9Scale and drift
  10. 3.10Practical: visual odometry with OpenCV
  1. 4.1Loose and tight coupling
  2. 4.2Multi-state MSCKF filter
  3. 4.3Visual-inertial EKF filters
  4. 4.4Sliding-window optimisation
  5. 4.5VINS-Mono and VINS-Fusion
  6. 4.6OKVIS and Basalt
  7. 4.7Visual-inertial initialisation and scale
  8. 4.8Marginalisation and the Schur complement
  9. 4.9Robustness and failure
  10. 4.10Workshop: running VINS-Fusion on EuRoC
  1. 5.1Code and phase observables
  2. 5.2RTK and ambiguity resolution
  3. 5.3PPP and PPP-RTK
  4. 5.4Galileo HAS service
  5. 5.5SSR state-space corrections
  6. 5.6Multipath in urban canyons
  7. 5.7Multi-band automotive receivers
  8. 5.8GNSS integrity
  9. 5.9Processing tools
  10. 5.10Lab: RTK positioning with RTKLIB
  1. 6.1Loosely coupled GNSS/VIO integration
  2. 6.2Tightly coupled integration with pseudoranges
  3. 6.3Factor graph optimisation
  4. 6.4GNSS factors in GTSAM
  5. 6.5Global alignment of VIO
  6. 6.6Handling signal outages
  7. 6.7Outlier detection
  8. 6.8Navigation in tunnels
  9. 6.9Evaluation in urban environments
  10. 6.10Practical: GNSS+VIO factor graph
  1. 7.1LiDAR-inertial with LIO-SAM
  2. 7.2FAST-LIO and iterated filters
  3. 7.3Distortion correction
  4. 7.4Fusion of LiDAR, vision and inertia
  5. 7.5Geometrically degenerate environments
  6. 7.6Comparison with VIO
  7. 7.7Mapping and relocalisation
  8. 7.8Real-time computational performance
  9. 7.9Multimodal benchmark datasets
  10. 7.10Workshop: FAST-LIO on an urban dataset
  1. 8.1Deep visual odometry
  2. 8.2SuperPoint learned features
  3. 8.3Matching with SuperGlue
  4. 8.4Learned monocular depth
  5. 8.5Learned inertial odometry
  6. 8.6Hybrid geometric and learned approaches
  7. 8.7Cross-domain generalisation
  8. 8.8Embedded deployment of networks
  9. 8.9Evaluation against classical methods
  10. 8.10Lab: SuperPoint in visual odometry
  1. 9.1Navigation integrity
  2. 9.2Protection levels
  3. 9.3Fault detection and exclusion
  4. 9.4Spoofing and jamming
  5. 9.5Robustness to dynamic scenes
  6. 9.6Poor lighting and texture
  7. 9.7Consistency monitoring
  8. 9.8Degraded states and graceful degradation
  9. 9.9Safety requirements
  10. 9.10Practical: VIO integrity monitor
  1. 10.1Embedded computing platforms
  2. 10.2C++ code optimisation
  3. 10.3GPU parallelisation
  4. 10.4Hardware synchronisation of sensors
  5. 10.5Integration in ROS 2
  6. 10.6Latency and real time
  7. 10.7System power consumption
  8. 10.8Regression testing
  9. 10.9Configuration management
  10. 10.10Workshop: deployment on NVIDIA Jetson
  1. 11.1Localisation in automated driving
  2. 11.2Delivery robots
  3. 11.3Drones and aerial vehicles
  4. 11.4Guidance of agricultural machinery
  5. 11.5Validation with reference systems
  6. 11.6Urban test campaigns
  7. 11.7Performance metrics
  8. 11.8Validation reports
  9. 11.9Comparison of commercial solutions
  10. 11.10Case study: validation on an urban route
  1. 12.1Definition of requirements and platform
  2. 12.2Sensor selection
  3. 12.3System calibration
  4. 12.4Estimator design
  5. 12.5GNSS integration
  6. 12.6Real-time implementation
  7. 12.7Experimental validation of the solution
  8. 12.8Conclusions and future work
  9. 12.9Master's Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

The programme 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 you can combine it with your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is ROS 2, GTSAM, RTKLIB, OpenCV and VINS-Fusion, in free, academic or evaluation versions. Testing is studied through real procedures for trajectory evaluation with public datasets, RTK positioning campaigns in the city and VIO validation against a reference system. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: ISO 26262, ISO 21448, RTCM 10403.3, IEEE 802.1AS, ISO 8855, ISO 23150, NMEA 0183, SAE J3016.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ISO 26262, ISO 21448 and RTCM 10403.3 applied to real cases, not as a theoretical annex.
Industry software:ROS 2, GTSAM, RTKLIB, OpenCV and VINS-Fusion, in free, academic or evaluation versions.
Master's Thesis with defence:A real-time precise positioning system combining VIO and GNSS, validated experimentally, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Requirements and sensors
Define the requirements and platform and select the sensors.
System calibration
Calibrate cameras, IMU and their time synchronisation.
Estimator design
Design the visual-inertial estimator and integrate GNSS in a factor graph.
Real-time implementation
Implement the solution in real time in ROS 2 on embedded hardware.
Master's Thesis
Validate the positioning solution experimentally, defended before a panel.
Career opportunities

Where this takes you

Navigation EngineerLocalisation Engineer3D Vision EngineerGNSS Systems EngineerSLAM ResearcherMobile Robotics Engineer
Admissions & scholarships

Requirements

  • University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • Internet connection and a computer capable of running the programme's 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.

Apply now Scholarships
FAQ

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 ROS 2, GTSAM, RTKLIB, OpenCV and VINS-Fusion, 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 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.

Keep exploring

Related programmes

See all in Autonomous, ADAS & Software-Defined Vehicle
Master's11,090 $

Master’s in C-V2X / ITS-G5 and Cooperative Perception Engineering

Online master's programme of 1,900 hours in C-V2X / ITS-G5 and cooperative perception engineering, structured in 12 modules covering C-ITS, ITS-G5 and C-V2X technologies, messages and…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master's7,730 $

Master’s in RTOS and Hypervisor Engineering in Automotive — Partitioning, Isolation and Mixed Criticality

Online master's programme of 1,900 hours in automotive RTOS and hypervisor engineering, structured in 12 modules covering real-time theory, RTOS on microcontrollers and application processors, automotive…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master's6,610 $

Master’s in AUTOSAR Adaptive, ROS 2 and DDS

Online master's programme of 1,900 hours in AUTOSAR Adaptive, ROS 2 and DDS. 12 modules covering software-defined vehicle architectures, service-oriented middleware, in-vehicle Ethernet and TSN, real-time…

12–14 monthsOnlineAutonomous, ADAS & Software-Defined Vehicle
Master’s in Visual-Inertial Odometry & Precise Positioning EngineeringEnrol
Related programmes

More in Autonomous, ADAS & Software-Defined Vehicle

Master’s in Risk-Based Scenarios and PEGASUS-Like EngineeringView programme →Master’s in Industrial OTA & SUMS EngineeringView programme →Master’s in Automotive RTOS and HypervisorsView programme →Master’s in AI Governance, AI Act & Privacy Engineering in ADView programme →Master’s in OTA, Diagnostics & Operations EngineeringView programme →Master’s in Optimal Control and MPC Engineering for Autonomous Vehicles — Constraints, Robustness and Real TimeView programme →

All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.