Dr. Marina AlcoverAcademic director focused on measurable results and operational excellence in maritime education. Integrates IMO/STCW regulations and ISO 21001/9001 f
Masters · 1600 h · 11 modules
Master's in AI applied to Autonomous Navigation
Is your gateway to the future of maritime robotics. Master the techniques of Artificial Intelligence, Machine Learning, and Deep Learning applied to the design and development of autonomous navigation systems for vessels. Learn…
Duration1600 h
FormatOnline
Starts16 November
Places20 / 20
Prior knowledge
Prior Knowledge Assessment
These are the skills this programme builds. Tick the ones you already have and we will tell you which part of the syllabus is really for you.
Your profile
Tick what you already know to see your result.
Programme overview
What is the Master’s in AI applied to Autonomous Navigation?
The Master's in AI Applied to Autonomous Navigation is your gateway to the future of maritime robotics. Master the techniques of Artificial Intelligence, Machine Learning, and Deep Learning applied to the design and development of autonomous navigation systems for vessels. Learn to create perception, route planning, and control algorithms to ensure safe and efficient navigation in complex environments.
Differentiating Advantages
- Development of real-world projects: Apply your knowledge in simulations and prototypes of autonomous navigation.
- Comprehensive training: Covers everything from AI theory to its implementation in maritime control systems.
- Expert instructors: Learn from industry and academic leaders with extensive experience in AI and naval robotics.
- Networking: Connect with industry professionals and explore career opportunities in innovative companies.
- Cutting-edge tools: Use state-of-the-art software and simulation platforms for your development.
Programme type
Master's Degree
Study mode
Online
Duration
1,600 hours
Modules
11
Programme highlights
- Intelligent Navigation: Master AI algorithms for autonomous decision-making in complex maritime environments.
- Sensors and Perception: Delve into the use of LiDAR, radar, and cameras for creating accurate environmental models.
- Simulation and Testing: Learn to develop and validate autonomous navigation systems through advanced simulation and testing in controlled environments.
- Regulation and Ethics: Understand the legal framework and ethical challenges associated with AI in maritime navigation.
- Practical Projects: Apply your knowledge to real-world navigation system development projects. Autonomous.
- Boost your career in the future of maritime navigation with the Master in AI applied to Autonomous Navigation.
Curriculum
Programme Structure
The programme is structured in 11 modules, listed below in order of study.
01
Implementation and optimisation of machine learning algorithms in autonomous navigation systems
- Mathematical and statistical fundamentals for machine learning applied to autonomous navigation: linear algebra, differential calculus, probability and Bayesian statistics
- Pre-processing and cleaning of sensory data: filtering of noise, normalization, balancing and detection of anomalies in radar, LiDAR, cameras and GNSS data
- Design of supervised, unsupervised and reinforced model architectures adapted to maritime dynamic environments
- Practical implementation of classic algorithms: Logistic regression, SVM, decision trees and Random Forest for obstacle detection and route classification
- Deep neural networks and convolutional architectures (CNN) for object recognition and processing of underwater and aerial images
- Reinforcement learning models for real-time decision-making in autonomous navigation, including Q-Learning and policy-based methods
- Hyperparameter optimisation using advanced techniques: grid search, Bayesian optimisation and evolutionary algorithms to maximise system accuracy and efficiency
- Integration of sensor fusion algorithms to improve system robustness and resilience in harsh and uncertain environments
- Deployment of models in embedded hardware: real-time computing considerations, energy consumption and latency in autonomous navigation systems
- Performance validation and testing: specific metrics for stand-alone navigation, simulations in virtual environments, and real-field testing
02
Advanced integration of intelligent sensors and data processing in autonomous navigation systems
- Intelligent Sensor Fundamentals: Types, Physical Principles and Operational Features in Maritime Environments
- Multi-sensory systems architecture: design, integration and timing for autonomous navigation
- Advanced signal processing: Adaptive filtering, data fusion and noise reduction for LiDAR, radar and sonar sensors
- Implementation of deep neural networks for real-time sensory data classification and segmentation
- Dynamic calibration algorithms and sensor self-tuning to ensure precision in changing sea conditions
- Multimodal sensory fusion: Bayesian techniques, extended Kalman filters and neural networks for robust estimation of states
- Integration of inertial sensors (IMU), high-precision GNSS and visual navigation systems for positioning optimisation
- Obstacle detection and monitoring models using data from heterogeneous sensors
- Distributed processing and Edge computing to minimise latency and maximise energy efficiency in autonomous marine platforms
- Communication protocols and standards for secure and reliable data transmission between sensors and central systems
03
Advanced machine learning and sensory integration strategies for high-precision autonomous navigation systems
- Basics of Machine Learning for Autonomous Navigation: Supervised, non-supervised and reinforcement algorithms applied to shipped systems
- Deep Neural Networks (DNN): Advanced architectures, specific optimisation and regularization for on-board real-time processing
- Probabilistic and Bayesian inference models for uncertainty in perception and decision making in dynamic marine environments
- Multimodal sensory integration: fusion of data from LiDAR, radar, GNSS, RGB-D cameras, IMUs and acoustic sensors for robust perception
- Algorithms for calibration and time synchronisation of heterogeneous sensors on autonomous maritime mobile platforms
- Convolutional neural networks (CNN) for detection and recognition of obstacles, maritime signalling and analysis of environmental conditions
- Application of advanced SLAM (Simultaneous Localization and Mapping) techniques and semantic mapping for navigation in coastal and port environments
- Path optimisation based on deep reinforcement learning for safe and efficient autonomous manoeuvres in complex scenarios
- Evaluation and mitigation of sensory errors using advanced Bayesian filters: Extended Kalman Filter (EKF), Particle Filter (PF) and its combination with neural networks
- Hybrid system architectures for the integration of predictive models and reactive planning in autonomous decision-making
04
Predictive control, trajectory planning and verification of autonomous navigation systems (simulation, testing and certification)
- Predictive Control Fundamentals in Autonomous Systems: Model Predictive Control (MPC), Target Functions and Constraints in Maritime Navigation
- Dynamic modelling of autonomous vehicles: mathematical representation of maritime systems, kinematic and dynamic modelling, and adaptation to variable environments
- Optimal trajectory planning: search algorithms, heuristic search, continuous optimisation and its application in autonomous sea routes
- Integration of sensors for planning: LiDAR, radar, GNSS and camera data fusion for precise generation of maps and obstacles
- Resilient Autonomous Navigation Systems: Uncertainty Management, Failure Detection, and Redundant Strategy Design
- Advanced simulation for system validation: real-time simulation tools, digital twins and virtual environments for control and planning tests
- Test and verification methodologies: functional tests, formal validation and stress tests under real and extreme conditions
- Certification of autonomous systems in navigation: international regulations, technical standards and audit protocols for approval of autonomous control systems
- Implementation of predictive embedded hardware control: Computational optimisation, latency, and robust design for critical marine environments
- Professional practices and case studies: Detailed analysis of real implementations, lessons learned and best practices in predictive control and trajectory planning
05
Design and architecture of deep neural networks for control in intelligent autonomous navigation
- Fundamentals and types of deep neural networks: multilayer perceptrons, convolutional networks (CNN), recurring networks (RNN), LSTM and Transformers applied to navigation systems
- Advanced mathematical theory for the design of neural architectures: activation functions, non-convex optimisation, regularization, backpropagation and stochastic descending gradient
- Design and parameterization of control agents based on Deep Reinforcement Learning for decision-making in dynamic environments of autonomous navigation
- Multi-sensory integration in neural networks: processing and fusion of data from LiDAR, radar, cameras, GNSS, IMU and sonars for robust environmental perception
- Hybrid architectures for predictive control: Combination of neural networks with physical models and classic controllers to ensure safety and operational efficiency
- Advanced training and validation techniques: Management of synthetic and real datasets, data augmentation techniques, class balance and strategies to avoid overfitting in maritime contexts
- Implementation of automatic attention systems and interpretation mechanisms (explainability) for the explanation of decisions of neural networks in autonomous navigation
- Computational and hardware optimisation: GPUs, TPUs and FPGAS implementation to ensure real-time inference and low latency on shipped systems
- Robustness and fault tolerance: error detection and mitigation techniques, adversarial learning and testing in extreme conditions (adverse climate, electromagnetic interference)
- Pilots and industrial frameworks for the implementation of deep neural networks in autonomous navigation platforms: from simulation to open sea validation
06
Innovation in machine learning algorithms, sensory integration and predictive control for high-precision autonomous navigation systems
- Advanced Machine Learning Fundamentals Applied to Autonomous Navigation: Supervised, unsupervised and reinforced learning, with emphasis on adaptation in dynamic maritime environments
- Design and Innovation in Algorithms for Environmental Perception: Convolutional Neural Networks (CNN), Recurring Networks (RNNs) and Transformers for real-time sensory processing
- Advanced multi-sensory integration: fusion of data from LiDAR, radar, hyperspectral cameras, GNSS systems and inertial sensors for precise digital model construction
- Model-based predictive control (MPC) for safe manoeuvres, route optimisation and adaptive response to hydrodynamic and meteorological disturbances
- Control Hybrid Architecture Design: Combination of classic PID control with deep learning techniques to improve energy stability and efficiency
- Implementation of collision evasion and detection systems using Deep Reinforcement-based trajectory planning algorithms and genetic algorithms
- Large-scale model simulation and training: creation of digital environments for virtual validation using digital twins and high-fidelity maritime simulators
- Real-time optimisation and parameter autotuning: Adaptive mechanisms for precision maintenance in changing operating environment conditions
- Key performance evaluation and metrics in autonomous navigation: positional precision, computational efficiency, failure robustness and tolerance to sensory errors
- Technical and regulatory aspects for the safe and reliable integration of intelligent systems in maritime platforms: interoperability, standards and specialised communication protocols
07
Integrated machine learning strategies, advanced sensory and predictive control for high-performance autonomous navigation systems
- Advanced Machine Learning Fundamentals for Autonomous Navigation: Supervised, Non-Supervised and Reinforcement Algorithms Applied to Dynamic Maritime Environments
- Implementation of deep learning (deep learning) for real-time obstacle recognition and classification
- Multispectral sensory fusion: LiDAR data integration, synthetic aperture radar (SAR), hyperspectral cameras and ultrasound sensors for environmental perception
- Predictive modelling based on time series to anticipate patterns of waves, sea currents and adverse weather conditions
- Design and optimisation of model-based predictive control (MPC) for active stabilisation and manoeuvreability of autonomous boats in high uncertainty scenarios
- Calibration and cross validation protocols of specialised maritime sensors to ensure precision and redundancy
- Integration of adaptive and autonomous algorithms for continuous decision making in navigation systems with multiple heterogeneous variables
- Robust digital simulation: creating realistic virtual environments for training and testing of AI models applied to complex sea routes
- Advanced embedded system architectures and edge computing for real-time processing and reduction of latencies on the stand-alone bridge
- Cyber security strategies and operational resilience in autonomous platforms against attacks and failures of sensors or actuators
08
Multimodal perception systems and data fusion for autonomous navigation in dynamic environments
- Fundamentals of Multimodal Perception: Principles, Sensory Modalities and Challenges in Dynamic Environments
- Sensor technologies for autonomous navigation: LiDAR, radar, RGB-D cameras, ultrasound and inertial sensors
- Advanced signal processing: Filtering, calibration and data correction External sensor
- Sensory fusion based on probabilistic models: Kalman filters, Particle Filters and Bayesian networks for robust integrations
- Real-time mapping and generation of 3D spatial representations: SLAM (Simultaneous location and mapping) and its variants
- Detection and classification of objects using deep learning: CNN, RNN and Transformers architectures applied to navigation
- Semantic segmentation algorithms and obstacle detection in complex coastal and maritime scenarios
- Heterogeneous data fusion: temporal synchronisation, spatial alignment, and multi-source quality assessment
- Decision-making methods based on multimodal perception for safe and efficient autonomous manoeuvres
- Real-time implementation: embedded hardware, computational optimisation, and parallelization techniques
09
Innovation and development of advanced algorithms in integrated autonomous navigation systems
- Mathematical and statistical fundamentals applied to autonomous navigation: linear algebra, vector calculation and probability theory
- Design and optimisation of multi-source perception algorithms: LiDAR data integration, radar, cameras and inertial sensors
- Deep neural networks and reinforced learning for decision making in dynamic marine environments
- Modelling and simulation of kinematic and dynamic systems of autonomous maritime vehicles using non-linear systems and adaptive control
- Implementation of advanced sensory fusion algorithms for precision improvement in vehicle status and environment estimation
- Development of AI-based resilient and redundant navigation systems for mitigation of failures and robustness against external interference
- Application of optimum real-time route planning algorithms considering environmental, safety and energy efficiency constraints
- Evaluation and validation by high realism simulators and test benches in virtual maritime environments
- Integration of advanced computational vision techniques for recognition, sorting and tracking of mobile objects and obstacles
- International regulations, standards and protocols for the implementation of autonomous systems in the maritime field: practical application and regulatory challenges
10
Regulations, ethics and certification of autonomous navigation
- IMO mass code
- Levels of autonomy of ships
- Colreg and autonomous systems
- Legal responsibility of AI systems
- European Artificial Intelligence Regulation
- Certification by classification companies
- remote control centres
- human factor in supervision
- Cybersecurity of autonomous ships
- International pilot projects
11
Master’s Final Project in AI applied to Autonomous Navigation
- Definition and specifications of the final work: Objectives, scope, and exhaustive evaluation criteria for a comprehensive autonomous system.
- Advanced Perception: Multimodal integration of LiDAR sensors, RGB-D cameras, radar and ultrasonic sensors for robust real-time environment recognition.
- Sensory processing and fusion: algorithms for data cleansing, 3D reconstruction, semantic segmentation and pose estimation by supervised and unsupervised learning.
- Deep neural networks: Design and optimisation of CNN, RNN, and Transformers architectures for contextual interpretation and detection of dynamic and static objects.
- Development of predictive models for anticipation of movements and behaviours of human agents and vehicles in unstructured environments.
- Path planning: Formulation and resolution of multi-objective optimisation problems in high-dimensional spaces, using deep reinforcement learning techniques and search tree-based algorithms.
- Incorporation of kinematic and dynamic restrictions to guarantee the viability and safety of the route in urban, maritime or complex air scenarios.
- Adaptive and robust control: Implementation of predictive control algorithms based on models, neural networks and hybrid methods for stabilisation and efficient manoeuvreability of the autonomous vehicle.
- Advanced simulation and virtual validation: Realistic simulation platforms with connected digital environments to evaluate performance, resilience, and behaviour in limit cases.
- System integration and architecture: Modular and scalable design for synergistic coupling of perception, planning and control, with secure communication and redundant protocols.
Workload
Study Time and Workload
1600 hours of study, online and at your own pace. Move the slider to the hours a week you can really put in.
Hours a week8
Weeks to finish—
You finish around—
Who it is for
Naval and software engineers seeking to specialize in the development and implementation of autonomous systems for ships.Merchant marine officers and captains interested in understanding and leading the transition to autonomous navigation.Researchers and academics wishing to delve deeper into AI and machine learning algorithms applied to the maritime environment.Maritime and technology compa
Faculty
Academic direction and faculty
The teaching team at Navalis: working professionals who deliver and oversee the institute's programmes.
Eng. Diego Cifuentes
Cap. Javier Abaroa (MCA)
Dr. Pau Ferrer
Dr. Nuria Llobregat
Eng. Javier Bañuls
Eng. Sofía Marquina
Eng. Tomás Riera
Verified reviews
Student Reviews
Reviews collected and verified by Opynio, not written by us.
Outcomes
Learning Outcomes
- 01Implement advanced perception systems
- 02Develop robust control algorithms
- 03Optimize real-time decision-making
- 04Integrating AI into complex navigation architectures
- 05Ensuring the reliability and safety of autonomous systems
- 06Adapting navigation to dynamic and uncertain environments
Careers
Career Opportunities
01```html
02Autonomous Navigation Data Engineer/Scientist: Development and application of AI algorithms for autonomous navigation systems.
03Marine Robotics Specialist: Design, development, and maintenance of underwater robots and autonomous marine vehicles.
04AI Consultant for the Maritime Industry: Advising companies on the implementation of AI solutions for navigation and fleet management.
05AI and Navigation Researcher: Development of new techniques and algorithms to improve the accuracy and safety of autonomous navigation.
06Software Developer for Autonomous Navigation Systems: Creation and maintenance of software for the control and monitoring of autonomous vehicles.
07Navigation Systems Simulation and Modeling Specialist: Development of models and simulations to test and validate autonomous navigation systems.
08AI R&D Project Manager for Navigation: Planning and managing research and development projects in the field of autonomous navigation.
09Navigation Data Analyst: Analyzing data collected by navigation systems to identify patterns and improve performance.
Questions
Entry Requirements
Land, air, sea and space vehicles.
Yes. The itinerary includes ECDIS/Radar-ARPA/BRM with harbor, ocean, fog, storm, and SAR scenarios.
Online with live sessions; hybrid option for simulator/practical placements through agreements.
To autonomous navigation in the four areas: air, land, sea and space.
Recommended functional SMCP. We offer support materials for standard phraseology.
Yes, with a relevant degree or experience in maritime/port operations. The admissions interview will confirm suitability.
Optional (3–6 months) through Companies & Collaborations and the Alumni Network.
Simulator practice (rubrics), defeat plans, SOPs, checklists, micro-tests and applied TFM.
A degree from Navalis Magna Institute + operational portfolio (tracks, SOPs, reports and KPIs) useful for audits and employment.
Online admissions
Admissions Process
No waiting for a phone call. If your documents are complete, you can pay in the same session.
Entry requirements
```htmlAcademic/Professional Profile:Bachelor's/Undergraduate Degree in Computer Engineering, Mathematics, Physics, Robotics or related field; Demonstrable professional experience in AI development, robotics, or autonomous navigation.Language proficiency:Advanced technical English (B2 or higher) is recommended for understanding documentation and participating in international projects.Technical skills:Solid knowledge of programming (Python), linear algebra, calculus, statistics, and machine learning algorithms.Documentation: Updated CV, copy of degree, academic transcript, cove
Questions?
Frequently Asked Questions
Leave your details and admissions will write back. If you already know this is the one, go straight to the application and pay in the same session.