Master’s in Optimal Control and MPC for Autonomous Vehicles
Online master's programme of 1,900 hours in optimal control and MPC for autonomous vehicles. 12 modules covering vehicle modelling, optimal control theory, model predictive control, real-time optimisation, state estimation, trajectory planning, robustness and SOTIF, with an assigned technical tutor.
Master’s in Optimal Control and MPC for Autonomous Vehicles — studying from Singapore
Singapore is a leading testbed for autonomous vehicles, with public road trials of driverless shuttles and robotaxis in districts such as one-north and Punggol. The Land Transport Authority coordinates the regulatory framework for autonomous mobility, while the Centre for Advanced Robotics at Nanyang Technological University and the Singapore Autonomous Vehicle initiatives drive research. Engineers work on perception, sensor fusion, vehicle software and simulation. Employers include automotive tier-one suppliers, technology firms and research institutes active across the region.
Fees for Singapore: S$11,300 (Singapore dollar), with instalments and employer sponsorship available.
Relevant bodies in Singapore
Typical roles
Questions from Singapore
Which Singapore authorities govern autonomous vehicle testing, and does SEIUM's qualification help with that?
Singapore's autonomous vehicle trials are regulated by the Land Transport Authority (LTA), which issues approvals for testing on public roads. Engineers may also register with the Professional Engineers Board (PEB). SEIUM's qualifications are private qualifications, not state degrees, and not accredited by any national body. Whether they are recognised for these roles is for employers and the relevant authorities to decide.
Which Singapore employers hire for ADAS and software-defined vehicle work?
Opportunities exist with autonomous vehicle trial operators, mobility companies, automotive electronics suppliers, and software and systems firms serving the vehicle industry. Singapore's smart mobility push supports these roles. Employers generally value demonstrable software skills, such as projects in embedded code, simulation or safety validation. Your final project can show this, but hiring decisions rest with each employer.
Is this workable part-time from Singapore, and can it be funded by an employer?
Yes, the programme is 100% online and taught in English, so you can study from home in Singapore without any student visa. Expect a heavy load: a master's is 1,900 hours, a postgraduate diploma 800 hours and a specialist course 300 hours. Fees are payable in instalments, and employer sponsorship is possible, though approval depends on your company's training policy.
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
Formulate optimal control problems for vehicles.
Design model predictive controllers.
Solve numerical optimisation in real time.
Estimate the vehicle state with suitable filters.
Plan safe and feasible trajectories.
Analyse robustness against uncertainty.
Implement and validate the controller on an embedded system.
Who it's for
- Autonomous vehicle control engineers.
- Trajectory planning engineers.
- Optimisation engineers.
- State estimation engineers.
- Embedded control software engineers.
- ADAS validation engineers.
- Engineering or science graduates seeking to enter autonomous driving.
What you'll work with
- ISO 26262 (functional safety)
- ISO 21448 (SOTIF)
- UN Regulation No. 157 (ALKS)
- Implementing Regulation (EU) 2022/1426 (automated driving systems)
- UL 4600 (safety of autonomous products)
- ISO 34502 (scenario-based safety evaluation of automated driving)
- MATLAB (Model Predictive Control Toolbox)
- CasADi
- acados
- CARLA
- IPOPT
12 modules
1.1Kinematic models: bicycle and variants1.2Dynamic and tyre models1.3Linearisation and model validity1.4State space and discretisation1.5Controllability and observability1.6Lyapunov stability1.7PID control and its limits in tracking1.8Feedforward and feedback1.9Perception-planning-control architecture1.10Workshop: comparison of models
2.1Formulation of the optimal control problem2.2Pontryagin's maximum principle2.3Dynamic programming and the Bellman equation2.4Linear quadratic regulator2.5Optimal tracking and finite horizon2.6Terminal cost and stability2.7Constraints and multipliers2.8Analytical and numerical solutions2.9Robustness to uncertainty2.10Lab: LQR for lane keeping
3.1MPC formulation and receding horizon3.2Cost function and weights3.3State and actuation constraints3.4Stability and recursive feasibility3.5Linear versus non-linear MPC3.6Successive linearisation3.7Horizon and sampling period3.8Practical weight tuning3.9Trade-off between performance and computation3.10Lab: trajectory-tracking MPC
4.1Quadratic programming and solvers4.2Interior-point and active-set methods4.3Warm start and reuse of solutions4.4Problem conditioning4.5Code generation for embedded targets4.6Computation times and guarantees4.7Solver failures and fallback plans4.8Numerical precision4.9Profiling and optimisation4.10Lab: embedded solver
5.1Kalman filter and variants5.2Extended and unscented filters5.3Fusion of IMU, GNSS and odometry5.4Estimation of slip and sideslip5.5Sensor delays and synchronisation5.6Outlier detection5.7Observability in real conditions5.8Vehicle parameter estimation5.9Estimator validation5.10Lab: full state estimator
6.1Trajectory generation and curvature6.2Speed profiles and comfort6.3Local and global planning6.4Obstacle avoidance and margins6.5Planning-control coupling6.6Traffic rules as constraints6.7Behaviour at intersections6.8Replanning and stability6.9Interaction with other vehicles6.10Lab: local planner
7.1Tyre behaviour near saturation7.2Friction circle and force distribution7.3Lateral stability and understeer7.4Slip control7.5Evasive manoeuvres7.6Grip estimation7.7Control on low-grip surfaces7.8ESP intervention and coordination7.9Limits of autonomy7.10Lab: manoeuvre at the limit
8.1Sources of uncertainty in the vehicle8.2Robust control and uncertainty tubes8.3Stochastic MPC8.4Safety margins and soft constraints8.5Sensor degradation8.6Behaviour under failures8.7Introduction to formal verification8.8Worst-case analysis8.9Adversarial testing8.10Workshop: robust design of a controller
9.1Validation scenarios and catalogues9.2Performance and comfort metrics9.3High-fidelity simulation9.4HIL and test vehicle9.5Repeatability and conditions9.6Safety in tests with a driver9.7Track data analysis9.8Simulation-reality correlation9.9Documentation of results9.10Lab: validation campaign
10.1ISO 26262 applied to control10.2ISO 21448 and functional insufficiencies10.3Triggering conditions10.4Safety monitors and supervisors10.5Redundancy architectures10.6Transition to minimal risk condition10.7Validation evidence10.8Availability requirements10.9Interaction with the driver10.10Workshop: safety supervisor
11.1Allocation between CPU and accelerator11.2Timing requirements of the control loop11.3Arithmetic and precision11.4Memory management11.5Integration with the middleware11.6Diagnostics and logging11.7Unit testing of the controller11.8Coverage and evidence11.9Code maintenance11.10Lab: deployment on an embedded platform
12.1Definition of the case and requirements12.2Modelling and state estimation12.3Design of the optimal or predictive controller12.4Implementation and tuning12.5Validation in simulation12.6Testing in HIL or vehicle12.7Robustness and limits analysis12.8Safety evidence12.9Technical report and defence12.10Master's Thesis: final review with the tutor
How you'll learn
A 100% online programme on the SEIUM campus, with downloadable materials, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so it fits around your job.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is MATLAB (Model Predictive Control Toolbox), CasADi, acados, CARLA and IPOPT, in free, academic or evaluation versions. Testing is studied through real procedures for scenario-based simulation validation, closed-track testing and hardware-in-the-loop testing. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: ISO 26262, ISO 21448 (SOTIF), UN Regulation No. 157 (ALKS), Implementing Regulation (EU) 2022/1426, UL 4600 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'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.
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 will work with MATLAB (Model Predictive Control Toolbox), CasADi, acados, CARLA and IPOPT. Free, academic or evaluation versions are used, and your tutor indicates the free alternative where 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's 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 Vulnerable Road User Detection and Urban Safety Engineering
Online master's programme of 1,900 hours in vulnerable road user detection and urban safety, structured in 12 modules covering sensing, detection and intention prediction of pedestrians…
Master’s in ODD Definition and Operational Risk Management Engineering
Online master's programme of 1,900 hours in ODD definition and operational risk management engineering: 12 modules covering formal ODD specification, operational risk analysis, real-time ODD monitoring,…
Master’s in Human Factors & HMI Engineering
Online master's programme of 1,900 hours in human factors and HMI engineering, structured in 12 modules covering HMI design, driver distraction, warnings and alerts, interaction with…
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships