Home/Programmes/Master’s degrees/Master's in AI Applied to Autonomous Navigation
Master’s degree · Bridge and navigationMaster's in AI Applied to Autonomous Navigation
This master's programme gives you command of artificial intelligence and machine learning techniques applied to maritime robotics. You will work on environment perception, sensor fusion, path planning and collision avoidance, with simulation and validation throughout the modules.
100% online1,500 hours11 modulesTaught in EnglishEnrol any time
What is this programme?
This master's degree is your gateway to maritime robotics. It trains you in artificial intelligence, machine learning and deep learning applied to the design and development of autonomous navigation systems for vessels. The focus is on creating perception, route planning and control algorithms that allow a vessel to navigate safely and efficiently in complex environments.
The programme stands out for its real projects, applying what you learn in simulations and prototypes of autonomous navigation; its comprehensive training, from AI theory to implementation in maritime control systems; and its use of cutting-edge tools, with current software and simulation platforms.
Programme highlights
- Intelligent navigation: AI algorithms for autonomous decision-making in complex maritime environments.
- Sensors and perception: use of LiDAR, radar and cameras to build accurate models of the environment.
- Simulation and testing: development and validation through advanced simulation and controlled trials.
- Regulation and ethics: the legal framework and ethical challenges of AI in maritime navigation.
- Practical projects: application in real autonomous navigation system projects.
- Advance your career in the maritime navigation of the future.
Study plan
01Implementation and Optimisation of Machine Learning Algorithms in Autonomous Navigation Systems136 h
Mathematical and statistical foundations (linear algebra, calculus, probability, Bayesian statistics); preprocessing of sensor data: noise, normalisation, balancing and anomalies in radar, LiDAR, cameras and GNSS; supervised, unsupervised and reinforcement architectures for dynamic maritime environments; classical algorithms: logistic regression, SVM, decision trees and random forests; deep networks and CNNs for object recognition in underwater and aerial imagery; reinforcement learning for real-time decisions (Q-learning and policy-based methods); hyperparameter optimisation (grid, Bayesian and evolutionary search); sensor fusion for robustness in adverse conditions; deployment on shipboard hardware: real time, power consumption and latency; validation with specific metrics, simulation and field trials.
02Advanced Integration of Smart Sensors and Data Processing in Autonomous Navigation Systems136 h
Fundamentals of smart sensors in maritime environments; multi-sensor architectures: design, integration and time synchronisation; advanced signal processing: adaptive filtering, fusion and noise reduction (LiDAR, radar, sonar); deep networks for real-time sensor classification and segmentation; dynamic calibration and self-adjustment of sensors to changing sea conditions; multimodal fusion: Bayesian techniques, EKF and neural networks; integration of IMU, high-precision GNSS and visual navigation; obstacle detection and tracking with heterogeneous sensors; distributed processing and edge computing; secure communication protocols between sensors and central systems.
03Advanced Machine Learning Strategies and Sensor Integration for High-Precision Autonomous Navigation Systems136 h
Fundamentals of ML (supervised, unsupervised and reinforcement) in embedded systems; deep neural networks: architectures, optimisation and regularisation for real time; probabilistic models and Bayesian inference for uncertainty; multimodal integration: LiDAR, radar, GNSS, RGB-D cameras, IMU and acoustic sensors; calibration and time synchronisation of heterogeneous sensors; CNNs for obstacles, maritime signage and environmental conditions; SLAM and semantic mapping in coastal and port environments; trajectory optimisation with deep reinforcement learning; error mitigation with EKF, particle filters and neural networks; hybrid architectures combining predictive models and reactive planning.
04Predictive Control, Trajectory Planning and Verification of Autonomous Navigation Systems (Simulation, Testing and Certification)136 h
Fundamentals of model predictive control (MPC): objective functions and constraints; kinematic and dynamic modelling of autonomous marine vehicles; optimal trajectory planning: search, heuristics and continuous optimisation; sensor integration for map generation and obstacle detection; resilient systems: uncertainty, fault detection and redundancy; advanced simulation: real time, digital twins and virtual environments; testing and verification: functional, formal and stress testing; certification: regulations, standards and audit protocols; MPC on embedded hardware for critical environments; professional practice and real case studies.
05Design and Architecture of Deep Neural Networks for Control in Intelligent Autonomous Navigation136 h
Network types: MLP, CNN, RNN, LSTM and Transformers; mathematical theory: activations, non-convex optimisation, regularisation and backpropagation; control agents with deep reinforcement learning; multi-sensor integration (LiDAR, radar, cameras, GNSS, IMU, sonar); hybrid architectures: networks with physical models and classical controllers; training and validation: synthetic and real datasets, data augmentation and overfitting control; attention mechanisms and explainability of decisions; optimisation on GPU, TPU and FPGA for low-latency inference; robustness and fault tolerance: adversarial learning and extreme conditions; practical cases and industrial frameworks, from simulation to open sea.
06Innovation in Machine Learning Algorithms, Sensor Integration and Predictive Control for High-Precision Autonomous Navigation Systems136 h
Advanced ML fundamentals with emphasis on dynamic maritime environments; perception algorithms: CNN, RNN and Transformers in real time; multi-sensor integration, including hyperspectral cameras; MPC for safe manoeuvres, route optimisation and disturbances; hybrid architectures: PID control combined with deep learning; collision detection and avoidance with deep RL and genetic algorithms; large-scale simulation with digital twins and high-fidelity simulators; real-time optimisation and parameter self-tuning; performance metrics: positional accuracy, efficiency, robustness and error tolerance; technical and regulatory aspects: interoperability, standards and protocols.
07Integrated Machine Learning, Advanced Sensing and Predictive Control Strategies for High-Performance Autonomous Navigation Systems136 h
Advanced ML fundamentals applied to dynamic maritime environments; deep learning for real-time obstacle recognition and classification; multispectral fusion: LiDAR, SAR radar, hyperspectral cameras and ultrasound; predictive time-series modelling: waves, currents and weather; MPC for stabilisation and manoeuvrability under high uncertainty; calibration and cross-validation of marine sensors; adaptive algorithms for continuous decisions with heterogeneous variables; digital simulation for training and testing AI models; edge computing and embedded systems for the autonomous bridge; cybersecurity and resilience against attacks and failures.
08Multimodal Perception Systems and Data Fusion for Autonomous Navigation in Dynamic Environments136 h
Fundamentals of multimodal perception and its challenges; sensor technologies: LiDAR, radar, RGB-D, ultrasound and inertial; signal processing: filtering, calibration and correction; probabilistic fusion: Kalman, particle filters and Bayesian networks; real-time mapping and 3D SLAM; detection and classification with CNN, RNN and Transformers; semantic segmentation and coastal obstacle detection; fusion of heterogeneous data: synchronisation, alignment and quality; decision-making based on multimodal perception; real-time implementation and parallelisation.
09Innovation and Development of Advanced Algorithms in Integrated Autonomous Navigation Systems136 h
Mathematical foundations: linear algebra, vector calculus and probability; multi-source perception algorithms; deep networks and reinforcement learning for maritime decisions; modelling and simulation of non-linear systems with adaptive control; advanced sensor fusion to estimate the state of the vehicle and its environment; resilient, redundant AI-based navigation systems; optimal real-time planning with safety and energy constraints; evaluation with high-realism simulators and virtual test benches; advanced computer vision for moving objects and obstacles; international regulations and standards for autonomous maritime systems.
10Regulation, Ethics and Certification of Autonomous Navigation136 h
The IMO MASS Code; levels of ship autonomy; COLREG and autonomous systems; legal liability of AI systems; the European Artificial Intelligence Regulation; certification by classification societies; remote control centres; the human factor in supervision; cybersecurity of autonomous ships; international pilot projects.
11Master's Final Project in AI Applied to Autonomous Navigation: Development of an Integrated Perception, Planning and Control System Based on Deep Neural Networks for Autonomous Vehicles in Complex Environments136 h
Definition of the final project: objectives, scope and evaluation criteria; advanced perception with LiDAR, RGB-D, radar and ultrasound; processing and fusion: cleaning, 3D reconstruction, segmentation and pose estimation; design of CNNs, RNNs and Transformers for detection and contextual interpretation; predictive models to anticipate the movements of human agents and vehicles; multi-objective planning with deep RL and search trees; kinematic and dynamic constraints for feasible, safe routes; adaptive and robust control (MPC, neural networks and hybrid methods); advanced simulation and virtual validation in edge cases; modular architecture, secure communication and redundant protocols.
Duration and format
1,500hours in total
11modules of 136 hours
100%online, at your own pace
Openenrolment all year round
At 10 hours a week you would finish in about 150 weeks; at 20 hours a week, in about 75.
What you will learn
- Implement advanced perception systems.
- Develop robust control algorithms.
- Optimise real-time decision-making.
- Integrate AI into complex navigation architectures.
- Ensure the reliability and safety of autonomous systems.
- Adapt navigation to dynamic and uncertain environments.
Career outcomes
- Engineer or data scientist in autonomous navigation: developing and applying AI algorithms for these systems.
- Marine robotics specialist: design, development and maintenance of underwater robots and autonomous marine vehicles.
- AI consultant for the maritime industry: advising companies on AI solutions for navigation and fleet management.
- Researcher in AI and navigation: new techniques to improve accuracy and safety.
- Autonomous navigation software developer: creating and maintaining control and monitoring software.
- Navigation simulation and modelling specialist: models and simulations to test and validate systems.
- R&D project manager in AI for navigation: planning and managing research projects.
- Navigation data analyst: analysing navigation system data to detect patterns and improve performance.
Entry requirements
- Academic or professional profile: a degree in computer engineering, mathematics, physics, robotics or a related field, or demonstrable professional experience in AI, robotics or autonomous navigation.
- Language skills: advanced technical English (B2 or higher) is recommended.
- Technical knowledge: solid skills in Python programming, linear algebra, calculus, statistics and machine learning.
- Documentation: up-to-date CV, copy of your qualification, academic transcript and a motivation letter on your interest in AI-based autonomous navigation.
- Technical requirements (online): a computer with adequate processing capacity (a GPU is recommended) and a high-speed internet connection. Enrolment is open all year round; admission is provisional until the committee validates your documentation.
How to enrol
Enrol online
Complete your enrolment on this page, or apply through admissions if you prefer to talk to us first.
Receive your access
We send you the details to enter the virtual campus and start the programme.
Study at your pace
Work through the modules when it suits you and complete the programme from anywhere in the world.
More programmes in Bridge and navigation
Master’s degreeBridge and navigation
Master's in Polar Exploration and Ice Navigation
This master's programme prepares you to lead expeditions and maritime operations in the most challenging environments on the planet. You will work with ice science, ic…
$3,597View programme →
Professional diplomaBridge and navigation
Professional Diploma in Dynamic Positioning (DP) and Offshore Support Vessels
This professional diploma prepares you to work with the dynamic positioning systems that keep vessels on station. You will work on reference sensors, redundancy classe…
$960View programme →
Master’s degreeBridge and navigation
Master's in Remote Operation of Autonomous Ships and the MASS Code
This master's programme prepares you to work in the new generation of autonomous and remotely operated ships. You will work on shore control centres, sensor fusion, co…
$2,950View programme →