II Edition

04 OCT 2021 ––––– 03 OCT 2022

Master Science in Intelligent Avionics 

APPLICATION PERIOD OPENING

01 ———   JUN 2021

~

APPLICATION PERIOD CLOSING

15 ———   SEP 2021

l

MIA REGISTRATION PERIOD

16 SEP ———   03 OCT 2021

2021-2022

Master Program

MODULE 1. Aerospace Systems and Avionics

The module 1 of the master is an introduction module that provides the student with the technical knowledge necessary to understand how the different systems of an aircraft work, such as the landing gear system, hydraulic, electrical, mission…

Description:

1. Aircraft Systems: General Systems, Landing Gear, Aircraft Systems: Propulsion Systems, Electrical Systems

Teacher— Víctor Fernandez Seijo (Airbus)

Total Credits— 1.20

Total Hours— 12.00

2. Development of Avionic Systems

Teacher— Vance Hilderman y Florentino Hernanz (Doymus)

Credits— 2.00

Hours— 20.00

Module 1. Total credits— 3.20

MODULE 2. System Engineering

The objective of this module is to provide the concepts and basic knowledge of systems engineering. It will be focused on the processes, methodologies, and tools for any aircraft design and system integration project.

Description:

1. Management Process: Feasibility, Integration Management, Configuration Management, Risk Management, Quality Assurance, Agile Management 

Teacher— Alfonso Alcol (Occar)

Credits— 0.80

Hours— 8.00

2. Technical Process: Planning & Concept, Requirements Capture, Architecture Definition, Design, Build, Testing (Verification), Validation

Teacher— José Miguel Castillo (Clue)

Credits— 1.20

Hours— 12.00

3. Specific Process: EN9100. Certification vs qualification. DOA. Airworthiness regulations- part 21. Aircraft Equipment specification, selection and validation. Part 21 cascades to design suppliers. V&V and SDRL. Technical Signatures Management

Teacher— Almudena Guil (Airbus)

Credits— 1.00

Hours— 10.00

Module 2. Total credits— 3.00

MODULE 3. Mathematics for Intelligent Systems

In this module a scientific training will be taught in the basic and applied aspects of mathematics. It is a preparation and training for the use of the theoretical and practical knowledge acquired, in order to face the subsequent specialized studies that will be taught in the specific modules of the master.

 

Description:

1. Linear Algebra: Vectors, Matrices, Diagonalisation, Orthogonality

2. Calculus: Review, Linear Regression, Logarithmic Regression,Optimisation

3. Statistics: Descriptive Statistics, Probability Theory, Inference Statistics, Bayesian Statistics

Teacher— Luis Parras y Carlos del Pino (UMA)

Total credits— 4.50

Total Hours— 45.00

Module 3. Total credits— 4.50

MODULE 4. Real-Time Programming

This module has the objective of transmitting the characteristics and requirements of the real-time systems, and to deal with aspects such as design and programming of these. The module will deal mainly with the development of the temporal requirements of systems that interact with a physical environment with deterministic time response.

 

 Description:

1. Real-Time Operating Systems: Process Management, Memory Management, Time Management, Health Monitoring. POSIX

Teacher— Daniel Garrido y Manuel Díaz (UMA)

Credits— 2.60

Hours— 26.00

2. Virtual Memory HW

Teacher— Roberto Vargas (Clue)

Credits— 1.50

Hours— 15.00

3. Introduction to caches and their implications in real-time systems

Teacher— Dr. Leonidas Kosmidis (BSC)

Credits— 1.00

Hours— 10.00

4. Introduction to PikeOS

Teacher— Javier Reina (Clue)

Credits— 0.40

Hours— 4.00

Module 4. Total credits— 5.50

MODULE 5. Artificial Intelligence

The objective of this subject is to transmit the bases and methodology of artificial intelligence. For this, the student will be introduced to the different concepts, techniques and fundamental algorithms of the artificial intelligence, as well as the practical application of this knowledge.

Description:

1. AI: Intro, Intelligent agents, Uninformed search, Heuristic search, A* algorithm, Adversarial Search, Constraint Satisfaction Problems, Machine Learning, Reinforcement Learning, Bayesian Thinking

Teacher— Ezequiel López Rubio y Miguel Angel Molina (UMA)

Credits— 2.50

Hours— 25.00

2. AI applications: Real-Time Analytics, Adaptive Flight Control, Autonomous Flying, Predictive Maintenance

Teacher— Miguel Martín (Airbus)

Credits— 1.60

Hours— 16.00

Module 5. Total credits— 4.10

MODULE 6. Distributed Systems
MODULE 7. Embedded Neural Networks

The module 7 consist of two distinct parts. The first part performs the study of systems based on FPGA or ASIC. The second part makes a study of the different advanced architectures of computers, responsible for describing different basic structures which are present in most of the current computers as graphic and neural processors.

 

Description:

1. FPGA/ASIC: Intro to VHDL, Architecture, Parallelism, Optimization, Training 

Teacher— Damián Sánchez (Clue)

Credits— 2.40

Hours— 24.00

2. GPU: Intro to CUDA C, GPU Parallelism, Grids, Blocks, Threads, Memory Handling, Optimization, Learning, Inference 

Teacher— Manuel Ujaldón (NVIDIA)

Credits— 2.50

Hours— 25.00

Module 7. Total credits— 4.90

MODULE 8. Data Analytics and Machine Learning

In this module, the participants will study  the fundamental concepts to introduce the student to the world of data science (Data Analytics). The objective is to define their usual concepts and put them into practice with real application examples. In addition, the study of machine learning is included in this module, giving a vision of the techniques and learning algorithms existing nowadays.

 

Description:

1. Data Analytics: Intro, Data Wrangling, Exploratory Data Analysis, Data Visualisation

2. Machine Learning: Regression Methods, Classification Methods, Time-Series Forecasting, Neural Networks, Graphical Methods, Unsupervised Learning

Teacher— Manuel Baena/ Manuel Enciso / José del Campo / Gonzalo Ramos (UMA)

Total Credits— 4.50

Total Hours— 45.00

3. Machine Learning with MATLAB

Teacher— Paz Tárrega (Mathworks)

Credits— 2.00

Hours— 20.00

Module 8. Total credits— 6.50

MODULE 9. Deep Learning

The student will have a broad view of the main techniques and most used methods as well as a full training in the field of the application of the tools of Deep Learning and  the management and decision-making in different contexts. At the same time, the student will obtain a global vision of the main lines of research in this field.

 

Description:

1. Deep Learning: Intro to Deep Neural Networks, Hyper-parameter Tuning, Regularization, Optimization, Convolutional Neural Networks, Recurrent Neural Networks 

Teacher— Ezequiel López Rubio UMA

Credits— 2.50

Hours— 25.00

Module 9. Total credits— 2.50

 

MODULE 10. Autonomous Flight and Computer Vision

The module 10 is focused on the study of methods and practices for the automatic control of manned and unmanned aerial vehicles. In particular, the student will be introduced to the application of non-linear control methods based on artificial intelligence techniques, which will be studied in previous modules, to meet the specific flight criteria and mission currently demanded by the aerospace market.

 

Description:

1. Computer Vision:  Image Processing, Keypoint detection, Image Adquisition, Image Formation, Camera Calibration, Stereo Vision 

Teacher— Javier González y Galindo Andrade (UMA)

Credits— 2.00

Hours— 20.00

2. Autonomous Systems: Sensor Fusion, Localisation, Path Planning, Control

3. Self-flying: Intro to autonomous flight,  3D Motion Planning, Control, Estimation, Vehicles dynamics

Teacher— Jesus Morales y Jesus Gómez (UMA)

Total Credits— 2.50

Total Hours— 25.00

Module 10. Total credits— 4.50

 

MODULE 11. Practical Work

During the practical training the student will be on apprenticeship in the installations of Clue Technologies. A tutor will be assigned and a specific project to do during this internship period. At the end of this module, the student must present a report of the work done.

Description:

1. Internship in Clue Technologies and a specific practical work to be developed by Teams supervised by Clue expert

Teacher— José Miguel Castillo (Clue)

Credits— 10.80

Hours— 108

Module 11. Total credits— 10.80

MODULE 12. Final Project

The final project or final master’s project consists in the development of a complete project under the supervision of an industrial or academic tutor. The work must be focused on a topic chosen by the student and bring together the knowledge acquired during the development of the master. The final master’s work will be an oral presentation.

 

Description:

1. Development of a complete on-board intelligent system design project under the supervision of a Clue or UMA advisor.

Teacher— Nicolás Guil (UMA)

Credits— 6.00

Hours— 60.00

Module 12. Total credits— 6.00