Professional Master's Degree

Robotics
Professional Master's Degree
Robotics
» Modality: online
» Duration: 12 months
» Certificate: TECH Technological University
» Dedication: 16h/week
» Schedule: at your own pace
» Exams: online
Website: www.techtitute.com/us/engineering/professional-master-degree/master-robotics
Index

01 02
Introduction Objectives
p. 4 p. 8

03 04 05
Skills Course Management Structure and Content
p. 14 p. 18 p. 24

06 07
Methodology Certificate
p. 36 p. 44
01
Introduction
The progressive and unstoppable robotization and automation of more and more industries
and businesses has made robotics one of the most advanced fields of engineering in recent
years. From the viral videos of Boston Dynamics to the most cutting-edge drones, robots are
part of the popular ideology and daily life of many people. Engineers who wish to specialize
in this field must have a high level of expertise, as projects such as autonomous cars or
space exploration require the best professionals in the field. This TECH program gathers the
knowledge, precisely, of doctors in engineering and professionals specialized in robotics,
with experience in the academic and aerospace fields. A great opportunity to give a decisive
boost to your professional career with a 100% online teaching, free of face-to-face classes
and preset schedules.
 Introduction | 05

Become a specialist in Industry 4.0, industrial

process automation, robot planning algorithms and
much more content created by robotics experts”
 06 | Introduction

It is undeniable that robotics has driven the advancement of industry to levels that This Professional Master's Degree in Robotics contains the most complete and up-to-
were unimaginable just a few years ago. It is already common to talk about Machine date program on the market. The most important features include:
Learning or Artificial Intelligences, fields in which robotics can expand to offer almost Š Development of case studies presented by experts in robotic engineering
futuristic solutions to everyday or even medical problems, with robotic assistants in
Š The graphic, schematic, and practical contents with which they are created, provide
complex operations.
scientific and practical information on the disciplines that are essential for
All this generates an undeniable growth opportunity for professional engineers who professional practice
dedicate themselves to this field, as they will find a multitude of areas and projects Š Practical exercises where self-assessment can be used to improve learning
to which they can direct their careers. From the purely industrial field to aerospace
Š Its special emphasis on innovative methodologies
technologies and international programs, an appropriate specialization in robotics
Š Theoretical lessons, questions to the expert, debate forums on controversial topics, and
can mean a quantitative and qualitative leap in quality for the engineers in their own
individual reflection assignments
professional career.
Š Content that is accessible from any fixed or portable device with an
For this reason, TECH has assembled for this program a team of leaders in the
Internet connection
field of robotics, with extensive experience in numerous international projects of
great prestige and an impeccable academic curriculum. Precisely this teaching
profile means that the entire content of the program has a unique theoretical-
practical approach, where the engineer will not only find the latest developments in
robotics, Artificial Intelligence and Communication Systems, but also the practical
application of all this knowledge in real working environments.

Through numerous videos in detail, complementary readings, video summaries and

self-knowledge exercises, the engineer will obtain a global and specialized vision of Join a program in which you will be the
the current state of robotics, being able to incorporate to his resume a program that
positions him as a valuable asset for any company in the sector. All this, in addition,
one who decides how, where and when
with the advantage of being able to manage the Professional Master's Degree at to take on the entire course load, without
your own pace, without having to attend classes or fixed schedules of any kind. The
having to sacrifice your personal or
teaching is 100% online and allows the necessary flexibility to combine it with the
most demanding personal and professional activity. professional life to do so"
 Introduction | 07

Enroll now and don't miss the opportunity Get the boost your career needs by
to delve into the application of robotics incorporating this Professional Master's
to virtual and augmented reality Degree in your value proposal.
technologies, with virtual sensors
and mixed mobile applications"
Master the most advanced and
modern Robotics with topics
dedicated exclusively to visual SLAM,
computer vision and Visual Servoing.

The program’s teaching staff includes professionals from the sector who contribute
their work experience to this training program, as well as renowned specialists from
leading societies and prestigious universities.

Its multimedia content, developed with the latest educational technology, will provide
the professional with situated and contextual learning, i.e., a simulated environment that
will provide an immersive education programmed to learn in real situations.

The design of this program focuses on Problem-Based Learning, by means of which

the professionals must try to solve the different professional practice situations that are
presented throughout the program. For this purpose, the student will be assisted by an
innovative interactive video system created by renowned experts.
02
Objectives
The objective of this program could not be other than to offer the engineer the
most rigorous and current contents in Robotics. Therefore, throughout the 10
extensive modules of knowledge that make up this Professional Master's Degree,
there will be many references to real robotics cases. This casuistry has been
created by the teaching team itself, so that the engineer can incorporate the
knowledge of the subject to their daily work in the most practical and quickest
way possible.
 Objectives | 09

Thanks to TECH's advanced teaching

methodology, you will save many hours
of study time, which you can invest in the
large library of multimedia content created
specifically for this program"
 10 | Objectives

General Objectives

Š Understand the mathematical foundations for kinematic and dynamic

modeling of robots
Š Delve into the use of specific technologies for the creation of robot architectures,
robot modeling and simulation
Š Generate specialized knowledge on Artificial Intelligence
Š Develop the technologies and devices most commonly used in
industrial automation
Š Identify the limits of current techniques to identify bottlenecks in
robotic applications

You will have the full support of TECH's

technical and teaching team to help
you achieve your most ambitious
professional goals"
 Objectives | 11

Specific Objectives

Module 1. Robotics: Robot Design and Modeling Module 3. Robotics in the Automation of Industrial Processes
Š Delve into the use of Gazebo Simulation Technology Š Analyze the use, applications and limitations of industrial communication networks
Š Master the use of the URDF Robot Modeling language Š Establish machine safety standards for correct design
Š Develop specialized knowledge in the use of Robot Operating System technology Š Develop clean and efficient programming techniques in PLCs
Š Model and simulate manipulator robots, land mobile robots, air mobile robots and Š Propose new ways of organizing operations using state machines
model and simulate aquatic mobile robots Š Demonstrate the implementation of control paradigms in real PLC applications
Module 2. Intelligent Agents. Applying Artificial Intelligence to Robots Š Fundamentalize the design of pneumatic and hydraulic installations in automation
and Softbots Š Identify the main sensors and actuators in robotics and automation
Š Analyze the biological inspiration of Artificial Intelligence and intelligent agents
Module 4. Automatic Control Systems in Robotics
Š Assess the need for intelligent algorithms in today's society
Š Generate specialized knowledge for the design of nonlinear controllers
Š Determine the applications of advanced Artificial Intelligence techniques on
Š Analyze and study control problems
Intelligent Agents
Š Master control models
Š Demonstrate the strong connection between Robotics and Artificial Intelligence
Š Design nonlinear controllers for robotic systems
Š Establish the needs and challenges presented by Robotics that can be solved
Š Implement controllers and assess them in a simulator
with Intelligent Algorithms
Š Determine the different existing control architectures
Š Develop concrete implementations of Artificial Intelligence Algorithms
Š Examine the fundamentals of vision control
Š Identify Artificial Intelligence algorithms that are established in today's society and
their impact on daily life Š Develop state-of-the-art control techniques such as predictive control or
machine learning based control
 12 | Objectives

Module 5. Robot Planning Algorithms Module 7. Robot Visual Perception Systems with Automatic Learning
Š Establish the different types of planning algorithms Š Master the machine learning techniques most widely used today in academia
Š Analyze the complexity of motion planning in robotics and industry

Š Develop techniques for environment modeling Š Delve into the architectures of neural networks to apply them effectively
in real problems
Š Examine the pros and cons of different planning techniques
Š Reuse existing neural networks in new applications using transfer learning
Š Analyze centralized and distributed algorithms for robot coordination
Š Identify new fields of application of generative neural networks
Š Identify the different elements in decision theory
Š Analyze the use of learning techniques in other fields of robotics such as
Š Propose learning algorithms for solving decision problems localization and mapping
Module 6. Artificial Vision Techniques in Robotics: Š Develop current technologies in the cloud to develop neural
Image Processing and Analysis network-based technologies
Š Analyze and understand the importance of vision systems in robotics Š Examine the deployment of vision learning systems in real and
Š Establish the characteristics of the different perception sensors in order to choose embedded systems
the most appropriate ones according to the application Module 8. Visual SLAM. Robot Localization and Simultaneous Mapping
Š Determine the techniques for extracting information from sensor data by Computer Vision Techniques
Š Apply visual information processing tools Š Specify the basic structure of a Simultaneous Localization and Mapping
(SLAM) system
Š Design digital image processing algorithms
Š Identify the basic sensors used in Simultaneous Localization and Mapping
Š Analyze and predict the effect of parameter changes on
(visual SLAM)
algorithm performance
Š Establish the boundaries and capabilities of visual SLAM
Š Assess and validate the developed algorithms in terms of results
Š Compile the basic notions of projective and epipolar geometry to understand
imaging projection processes
Š Identify the main visual SLAM technologies: Gaussian Filters, Optimization and
Loop Closure Detection
Š Describe in detail the operation of the main visual SLAM algorithms
Š Analyze how to carry out the tuning and parameterization of SLAM algorithms
 Objectives | 13

Module 9. Application of Virtual and Augmented Reality Technologies

to Robotics
Š Determine the difference among the different types of realities
Š Analyze the current standards for modeling virtual elements
Š Examine the most commonly used peripherals in immersive environments
Š Define geometric models of robots
Š Assess physics engines for dynamic and kinematic modeling of robots
Š Develop Virtual Reality and Augmented Reality projects

Module 10. Robot Communication and Interaction Systems

Š Analyze current natural language processing strategies: heuristic, stochastic, neural
network-based, reinforcement-based learning
Š Assess the benefits and weaknesses of developing cross-cutting, or situation-
focused, interaction systems
Š Identify the environmental problems to be solved in order to achieve effective
communication with the robot
Š Establish the tools needed to manage the interaction and discern the type of
dialogue initiative to be pursued
Š Combine pattern recognition strategies to infer the intentions of the interlocutor
and respond in the best way to them
Š Determine the optimal expressiveness of the robot according to its
functionality and environment, and apply emotional analysis techniques to
adapt its response
Š Propose hybrid strategies for interaction with the robot: vocal, tactile and visual
03
Skills
The skills that the Robotics engineer must develop are multiple, so this Professional
Master's Degree focuses on vital issues such as robot planning algorithms, automatic
control systems, artificial intelligence applications and advanced robot design. All this in
order to gain not only a global understanding of all that modern robotics encompasses,
but also to acquire and hone the skills necessary to undertake the most ambitious
projects in this field.
 Skills | 15

You will have a set of skills in

Robotics highly sought after
in the most important projects
and industries internationally"
 16 | Skills

General Skills

Š Master today’s most widely used virtualization tools in use today

Š Design virtual robotic environments
Š Examine the techniques and algorithms underlying any AI algorithm
Š Design, develop, implement and validate perceptual systems for robotics

You will hone your strategic,

mathematical and analytical
determination to take on the
creation and definition of
complex robotics projects"
 Skills | 17

Specific Skills

Š Identify multimodal interaction systems and their integration with the rest of the
robot components
Š Implement own virtual and augmented reality projects
Š Propose applications in real systems
Š Examine, analyze and develop existing methods for path planning by a mobile robot
and a manipulator
Š Analyze and define strategies for the implementation and maintenance of
perception systems
Š Determine strategies for integration of a dialog system as part of basic
robot behavior
Š Analyze programming and device configuration skills
Š Examine control strategies used in different robotic systems
04
Course Management
Advances in robotics are unstoppable and professionals in this field are continually
renewing their knowledge and acquiring new ones to further advance their careers.
For this reason, TECH has called upon active Robotics experts with vast experience
in multidisciplinary projects of all kinds. Therefore, all the content provided by the
teaching team is based on the latest robotic news, including cutting-edge scientific
postulates and a practical approach to the current theoretical framework.
 Course Management | 19

Succeed with the best and acquire

the knowledge and skills you need to
embark on the robotics industry”
 20 | Course Management

Management

Dr. Ramón Fabresse, Felipe

Š Senior Software Engineer at Acurable
Š NLP Software Engineer at Intel Corporation
Š Software Engineer in CATEC, Indisys
Š Researcher in Aerial Robotics at the University of Seville
Š PhD Cum Laude in Robotics, Autonomous Systems and Telerobotics at the University of Seville
Š Degree in Computer Engineering at the University of Seville
Š Professional Master’s Degree in Robotics, Automation and Telematics at the University of Seville

Professors
Dr. Íñigo Blasco, Pablo Mr. Campos Ortiz, Roberto
Š Software Engineer at PlainConcepts Š Software Engineer Quasar Scence Resources
Š Founder of Intelligent Behavior Robots Š Software Engineer at the European Space Agency (ESA-ESAC) for the Solar
Š Robotics Engineer at CATEC Advanced Center for Aerospace Technologies Orbiter mission
Š Developer and Consultant at Syderis Š Content creator and Artificial Intelligence expert in the course: "Artificial Intelligence: The
Š PhD in Industrial Informatics Engineering at the University of Seville technology of the present-future" for the Andalusian Regional Government.
Š Degree in Computer Engineering at the University of Seville Euroformac Group

Š Professional Master’s Degree in Software Engineering and Technology Š Quantum Computing Scientist Zapata Computing Inc
Š Graduated in Computer Engineering at Carlos III University
Š Master in Computer Science and Technology at Carlos III University
 Course Management | 21

Mr. Rosado Junquera, Pablo J Dr. Pérez Grau, Francisco Javier

Š Engineer Specialist in Robotics and Automatization Š Head of the Perception and Software Unit at CATEC
Š R&D Automation and Control Engineer at Becton Dickinson & Company Š R&D Project Manager at CATEC
Š Amazon Logistic Control Systems Engineer at Dematic Š R&D Project Engineer at CATEC
Š Automation and Control Engineer at Aries Ingeniería y Sistemas Š Associate Professor at the University of Cadiz
Š Graduate in Energy and Materials Engineering at Rey Juan Carlos University Š Associate Professor at the University International of Andalucia
Š Master's Degree in Robotics and Automation at the Polytechnic University of Madrid Š Researcher in the Robotics and Perception group at the University of Zurich
Š Master's Degree in Industrial Engineering at the University of Alcalá Š Researcher at the Australian Centre for Field Robotics at the University of Sydney
Dr. Jiménez Cano, Antonio Enrique Š PhD in Robotics and Autonomous Systems from the University of Seville
Š Engineer at Aeronautical Data Fusion Engineer Š Graduate in Telecommunications Engineering and Computer and Network Engineering
Š Researcher in European projects (ARCAS, AEROARMS and AEROBI) at the University from the University of Seville
of Seville Dr. Ramon Soria, Pablo
Š Researcher in Navigation Systems at CNRS-LAAS Š Computational Vision Engineer at Meta
Š LAAS MBZIRC2020 System Developer Š Applied Science Team Leader and Senior Software Engineer at Vertical
Š Group of Robotics, Vision and Control (GRVC) of the University of Seville Engineering Solutions
Š PhD in Automatics, Electronics and Telecommunications at the University of Seville Š CEO and founder of Domocracy
Š Graduated in Automatic Engineering and Industrial Electronics at the University of Seville Š ACFR Researcher (Australia)
Š Degree in Technical Engineering in Computer Systems at the University of Seville Š Researcher in the GRIFFIN and HYFLIERS projects at the University of Seville
Dr. Alejo Teissière, David Š PhD in Computational Vision for Robotics at the University of Seville
Š Telecommunications Engineer.with Specialization in Robotics Š Graduated in Industrial Engineer, Robotics and Automatization from University of Seville
Š Postdoctoral Researcher in the European projects SIAR and NIx ATEX at Pablo de
Olavide University
Š Systems Developer at Aertec
Š PhD in Automation, Robotics and Telematics at the University of Seville
Š Graduated in Telecommunication Engineering at the University of Seville
Š Master's Degree in Automation, Robotics and Telematics from the University of Seville
 22 | Course Management

Dr. Caballero Benítez, Fernando

Š Researcher in the European projects COMETS, AWARE, ARCAS and SIAR
Š Degree in Telecommunications Engineering from the University of Seville
Š PhD in Telecommunications Engineering at the University of Seville
Š Full Professor of Systems Engineering and Automatics at the University of Seville
Š Associate editor of the journal Robotics and Automation Letters
Dr. Lucas Cuesta, Juan Manuel
Š Senior Software Engineer and Analyst at Indizen– Believe in Talent
Š Senior Software Engineer and Analyst at Krell Consulting and IMAGiNA
Artificial Intelligence
Š Software Engineer at Intel Corporation
Š Software Engineer at Intelligent Dialogue Systems
Š PhD in Electronic Systems Engineering for Intelligent Environments at the
Polytechnic University of Madrid
Š Graduate in Telecommunications Engineering at the Polytechnic University of Madrid
Š Master's Degree in Electronic Systems Engineering for Intelligent Environments at the
Polytechnic University of Madrid
 Course Management | 23

Enroll now and don't miss the

opportunity to delve into the
application of robotics to virtual and
augmented reality technologies,
with virtual sensors and mixed
mobile applications"
05
Structure and Content
The teaching team involved in the design of the entire syllabus has used the
Relearning methodology, favoring a progressive and natural teaching for the
whole program. This is achieved through a reiteration of the most important key
concepts in robotics and advanced engineering, so that the student does not have
to spend long hours of study to acquire this knowledge.
 Structure and Content | 25

You have within your reach the key to direct your

engineering career towards the field of robotics.
Don't waste this oportunity and enroll now"
 26 | Structure and Content

Module 1. Robotics: Robot Design and Modeling 1.7. Terrestrial Mobile Robots
1.7.1. Types of Terrestrial Mobile Robots
1.1. Robotics and Industry 4.0
1.7.2. Kinematics
1.1.1. Robotics and Industry 4.0
1.7.3. Dynamics
1.1.2. Application Fields and Use Cases
1.7.4. Simulation
1.1.3. Sub-Areas of Specialization in Robotics
1.8. Aerial Mobile Robots
1.2. Robot Hardware and Software Architectures
1.8.1. Types of Aerial Mobile Robots
1.2.1. Hardware Architectures and Real-Time
1.8.2. Kinematics
1.2.2. Robot Software Architectures
1.8.3. Dynamics
1.2.3. Communication Models and Middleware Technologies
1.8.4. Simulation
1.2.4. Robot Operating System (ROS) Software Integration
1.9. Aquatic Mobile Robots
1.3. Mathematical Modeling of Robots
1.9.1. Types of Aquatic Mobile Robots
1.3.1. Mathematical Representation of Rigid Solids
1.9.2. Kinematics
1.3.2. Rotations and Translations
1.9.3. Dynamics
1.3.3. Hierarchical State Representation
1.9.4. Simulation
1.3.4. Distributed Representation of the State in ROS (TF Library)
1.10. Bioinspired Robots
1.4. Robot Kinematics and Dynamics
1.10.1. Humanoids
1.4.1. Kinematics
1.10.2. Robots with Four or More Legs
1.4.2. Dynamics
1.10.3. Modular Robots
1.4.3. Underactuated Robots
1.10.4. Robots with Flexible Parts (Soft-Robotics)
1.4.4. Redundant Robots
1.5. Robot Modeling and Simulation Module 2. Intelligent Agents. Application of Artificial Intelligence to
1.5.1. Robot Modeling Technologies Robots and Softbots
1.5.2. Robot Modeling with URDF
2.1. Intelligent Agents and Artificial Intelligence
1.5.3. Robot Simulation
2.1.1. Intelligent Robots. Artificial Intelligence
1.5.4. Modeling with Gazebo Simulator
2.1.2. Intelligent Agents
1.6. Robot Manipulators
2.1.2.1. Hardware Agents Robots
1.6.1. Types of Manipulator Robots
2.1.2.2. Software Agents. Softbots
1.6.2. Kinematics
2.1.3. Robotics Applications
1.6.3. Dynamics
2.2. Brain-Algorithm Connection
1.6.4. Simulation
2.2.1. Biological Inspiration of Artificial Intelligence
2.2.2. Reasoning Implemented in Algorithms. Typology
2.2.3. Explainability of Results in Artificial Intelligence Algorithms
2.2.4. Evolution of Algorithms up to Deep Learning
 Structure and Content | 27

2.3. Search Algorithms in the Solution Space 2.9. Probabilistic Inference

2.3.1. Elements in Solution Space Searches 2.9.1. Probabilistic Inference
2.3.2. Solution Search Algorithms in Artificial Intelligence Problems 2.9.2. Types of Inference and Method Definition
2.3.3. Applications of Search and Optimization Algorithms 2.9.3. Bayesian Inference as a Case Study
2.3.4. Search Algorithms Applied to Machine Learning 2.9.4. Nonparametric Inference Techniques
2.4. Machine Learning 2.9.5. Gaussian Filters
2.4.1. Machine Learning 2.10. From Theory to Practice: Developing an Intelligent Robotic Agent
2.4.2. Supervised Learning Algorithms 2.10.1. Inclusion of Supervised Learning Modules in a Robotic Agent
2.4.3. Unsupervised Learning Algorithms 2.10.2. Inclusion of Reinforcement Learning Modules in a Robotic Agent
2.4.4. Reinforcement Learning Algorithms 2.10.3. Architecture of a Robotic Agent Controlled by Artificial Intelligence
2.5. Supervised Learning 2.10.4. Professional Tools for the Implementation of the Intelligent Agent
2.5.1. Supervised Learning Methods 2.10.5. Phases of the Implementation of AI Algorithms in Robotic Agents
2.5.2. Decision Trees for Classification
Module 3. Robotics in the Automation of Industrial Processes
2.5.3. Support Vector Machines
2.5.4. Artificial Neural Networks 3.1. Design of Automated Systems
2.5.5. Applications of Supervised Learning 3.1.1. Hardware Architectures
2.6. Unsupervised Learning 3.1.2. Programmable Logic Controllers
2.6.1. Unsupervised Learning 3.1.3. Industrial Communication Networks
2.6.2. Kohonen Networks 3.2. Advanced Electrical Design I: Automation
2.6.3. Self-Organizing Maps 3.2.1. Design of Electrical Panels and Symbology
2.6.4. K-Means Algorithm 3.2.2. Power and Control Circuits. Harmonics
2.7. Reinforcement Learning 3.2.3. Protection and Grounding Elements
2.7.1. Reinforcement Learning 3.3. Advanced Electrical Design II: Determinism and Safety
2.7.2. Agents Based on Markov Processes 3.3.1. Machine Safety and Redundancy
2.7.3. Reinforcement Learning Algorithms 3.3.2. Safety Relays and Triggers
2.7.4. Reinforcement Learning Applied to Robotics 3.3.3. Safety PLCs
2.8. Artificial Neural Networks and Deep Learning 3.3.4. Safe Networks
2.8.1. Artificial Neural Networks. Typology 3.4. Electrical Actuation
2.8.2. Applications of Neural Networks 3.4.1. Motors and Servomotors
2.8.3. Transformation from Machine Learning to Deep Learning 3.4.2. Frequency Inverters and Controllers
2.8.4. Deep Learning Applications 3.4.3. Electrically Actuated Industrial Robotics
 28 | Structure and Content

3.5. Hydraulic and Pneumatic Actuation

3.5.1. Hydraulic Design and Symbology
3.5.2. Pneumatic Design and Symbology
3.5.3. ATEX Environments in Automation
3.6. Transducers in Robotics and Automation
3.6.1. Position and Velocity Measurement
3.6.2. Force and Temperature Measurement
3.6.3. Presence Measurement
3.6.4. Vision Sensors
3.7. Programming and Configuration of Programmable Logic Controllers PLCs
3.7.1. PLC Programming: LD
3.7.2. PLC Programming: ST
3.7.3. PLC Programming: FBD and CFC
3.7.4. PLC Programming: SFC
3.8. Programming and Configuration of Equipment in Industrial Plants
3.8.1. Programming of Drives and Controllers
3.8.2. HMI Programming
3.8.3. Programming of Manipulator Robots
3.9. Programming and Configuration of Industrial Computer Equipment
3.9.1. Programming of Vision Systems
3.9.2. SCADA/Software Programming
3.9.3. Network Configuration
3.10. Automation Implementation
3.10.1. State Machine Design
3.10.2. Implementation of State Machines in PLCs
3.10.3. Implementation of Analog PID Control Systems in PLCs
3.10.4. Automation Maintenance and Code Hygiene
3.10.5. Automation and Plant Simulation

Module 4. Automatic Control Systems in Robotics

4.1. Analysis and Design of Nonlinear Systems
4.1.1. Analysis and Modeling of Nonlinear Systems
4.1.2. Feedback Control
4.1.3. Linearization by Feedback
 Structure and Content | 29

4.2. Design of Control Techniques for Advanced Non-linear Systems

4.2.1. Sliding Mode control
4.2.2. Lyapunov and Backstepping Control
4.2.3. Control Based on Passivity
4.3. Control Architectures
4.3.1. The Robotics Paradigm
4.3.2. Control Architectures
4.3.3. Applications and Examples of Control Architectures
4.4. Motion Control for Robotic Arms
4.4.1. Kinematic and Dynamic Modeling
4.4.2. Control in Joint Space
4.4.3. Control in Operational Space
4.5. Actuator Force Control
4.5.1. Force Control
4.5.2. Impedance Control
4.5.3. Hybrid Control
4.6. Terrestrial Mobile Robots
4.6.1. Equations of Motion
4.6.2. Control Techniques for Terrestrial Robots
4.6.3. Mobile Manipulators
4.7. Aerial Mobile Robots
4.7.1. Equations of Motion
4.7.2. Control Techniques in Aerial Robots
4.7.3. Aerial Manipulation
4.8. Control Based on Machine Learning Techniques
4.8.2. Control Using Supervised Learning
4.8.3. Control Using Reinforced Learning
4.8.4. Control by Unsupervised Learning
4.9. Vision-Based Control
4.9.1. Position-Based Visual Servoing
4.9.2. Image-Based Visual Servoing
4.9.3. Hybrid Visual Servoing
 30 | Structure and Content

4.10. Predictive Control 5.6. Coordination in Multi-Robot Systems I: Centralized System

4.10.1. Models and State Estimation 5.6.1. Multirobot Coordination Problem
4.10.2. MPC Applied to Mobile Robots 5.6.2. Collision Detection and Resolution: Trajectory Modification with
4.10.3. MPC Applied to UAVs Genetic Algorithms
5.6.3. Other Bio-Inspired Algorithms: Particle Swarm and Fireworks
Module 5. Robot Planning Algorithms 5.6.4. Collision Avoidance by Choice of Maneuver Algorithm
5.1. Classical Planning Algorithms 5.7. Coordination in Multi-Robot Systems II: Distributed Approaches I
5.1.1. Discrete Planning: State Space 5.7.1. Use of Complex Objective Functions
5.1.2. Planning Problems in Robotics. Robotic Systems Models 5.7.2. Pareto Front
5.1.3. Classification of Planners 5.7.3. Multi-Objective Evolutionary Algorithms
5.2. The Trajectory Planning Problem in Mobile Robots 5.8. Coordination in Multi-Robot Systems III: Distributed Approaches II
5.2.1. Forms of Environment Representation: Graphs 5.8.1. Order 1 Planning Systems
5.2.2. Search Algorithms in Graphs 5.8.2. ORCA Algorithm
5.2.3. Introduction of Costs in Networks 5.8.3. Addition of Kinematic and Dynamic Constraints in ORCA
5.2.4. Search Algorithms in Heavy Networks 5.9. Decision Planning Theory
5.2.5. Algorithms with any Angle Approach 5.9.1. Decision Theory
5.3. Planning in High Dimensional Robotic Systems 5.9.2. Sequential Decision Systems
5.3.1. High Dimensionality Robotics Problems: Manipulators 5.9.3. Sensors and Information Spaces
5.3.2. Direct/Inverse Kinematic Model 5.9.4. Planning for Uncertainty in Sensing and Actuation
5.3.3. Sampling Planning Algorithms PRM and RRT 5.10. Reinforcement Learning Planning Systems
5.3.4. Planning Under Dynamic Constraints 5.10.1. Obtaining the Expected Reward of a System
5.4. Optimal Sampling Planning 5.10.2. Mean Reward Learning Techniques
5.4.1. Problem of Sampling-Based Planners 5.10.3. Inverse Reinforcement Learning
5.4.2. RRT Probabilistic Optimality Concept
5.4.3. Reconnection Step: Dynamic Constraints Module 6. Artificial Vision Techniques in Robotics: Image Processing and Analysis
5.4.4. CForest. Parallelizing Planning 6.1. Computer Vision
5.5. Real Implementation of a Motion Planning System 6.1.1. Computer Vision
5.5.1. Global Planning Problem. Dynamic Environments 6.1.2. Elements of a Computer Vision System
5.5.2. Cycle of Action, Sensorization. Acquisition of Information 6.1.3. Mathematical Tools
from the Environment 6.2. Optical Sensors for Robotics
5.5.3. Local and Global Planning 6.2.1. Passive Optical Sensors
6.2.2. Active Optical Sensors
6.2.3. Non-Optical Sensors
 Structure and Content | 31

6.3. Image Acquisition Module 7. Robot Visual Perception Systems with Automatic Learning
6.3.1. Image Representation
7.1. Unsupervised Learning Methods applied to Computer Vision
6.3.2. Color Space
7.1.1. Clustering
6.3.3. Digitizing Process
7.1.2. PCA
6.4. Image Geometry
7.1.3. Nearest Neighbors
6.4.1. Lens Models
7.1.4. Similarity and Matrix Decomposition
6.4.2. Camera Models
7.2. Supervised Learning Methods Applied to Artificial Vision
6.4.3. Camera Calibration
7.2.1. “Bag of words” Concept
6.5. Mathematical Tools
7.2.2. Support Vector Machine
6.5.1. Histogram of an Image
7.2.3. Latent Dirichlet Allocation
6.5.2. Convolution
7.2.4. Neural Networks
6.5.3. Fourier Transform
7.3. Deep Neural Networks: Structures, Backbones and Transfer Learning
6.6. Image Preprocessing
6.6.1. Noise Analysis 7.3.1. Feature Generating Layers

6.6.2. Image Smoothing 7.3.3.1. VGG

6.6.3. Image Enhancement 7.3.3.2. Densenet
6.7. Image Segmentation 7.3.3.3. ResNet
6.7.1. Contour-Based Techniques 7.3.3.4. Inception
6.7.2. Histogram-Based Techniques 7.3.3.5. GoogLeNet
6.7.3. Morphological Operations 7.3.2. Transfer Learning
6.8. Image Feature Detection 7.3.3. The Data Preparation for Training
6.8.1. Point of Interest Detection 7.4. Artificial Vision with Deep Learning I: Detection and Segmentation
6.8.2. Feature Descriptors 7.4.1. YOLO and SSD Differences and Similarities
6.8.3. Feature Matching 7.4.2. Unet
6.9. 3D Vision Systems 7.4.3. Other Structures
6.9.1. 3D Perception 7.5. Computer Vision with Deep Learning II: Generative Adversarial Networks
6.9.2. Feature Matching between Images 7.5.1. Image Super-Resolution Using GAN
6.9.3. Multiple View Geometry 7.5.2. Creation of Realistic Images
6.10. Computer Vision based Localization 7.5.3. Scene Understanding
6.10.1. The Robot Localization Problem 7.6. Learning Techniques for Localization and Mapping in Mobile Robotics
6.10.2. Visual Odometry 7.6.1. Loop Closure Detection and Relocation
6.10.3. Sensory Fusion 7.6.2. Magic Leap. Super Point and Super Glue
7.6.3. Depth from Monocular
 32 | Structure and Content

7.7. Bayesian Inference and 3D Modeling

7.7.1. Bayesian Models and "Classical" Learning
7.7.2. Implicit Surfaces with Gaussian Processes (GPIS)
7.7.3. 3D Segmentation Using GPIS
7.7.4. Neural Networks for 3D Surface Modeling
7.8. End-to-End Applications of Deep Neural Networks
7.8.1. End-to-End System. Example of Person Identification
7.8.2. Object Manipulation with Visual Sensors
7.8.3. Motion Generation and Planning with Visual Sensors
7.9. Cloud Technologies to Accelerate the Development of Deep Learning Algorithms
7.9.1. Use of GPUs for Deep Learning
7.9.2. Agile Development with Google Colab
7.9.3. Remote GPUs, Google Cloud and AWS
7.10. Deployment of Neural Networks in Real Applications
7.10.1. Embedded Systems
7.10.2. Deployment of Neural Networks. Use
7.10.3. Network Optimizations in Deployment, Example with TensorRT

Module 8. Visual SLAM. Robot Localization and Simultaneous Mapping

by Artificial Vision Techniques
8.1. Simultaneous Localization and Mapping (SLAM)
8.1.1. Simultaneous Localization and Mapping. SLAM
8.1.2. SLAM Applications
8.1.3. SLAM Operation
8.2. Projective Geometry
8.2.1. Pin-Hole Model
8.2.2. Estimation of Intrinsic Parameters of a Chamber
8.2.3. Homography, Basic Principles and Estimation
8.2.4. Fundamental Matrix, Principles and Estimation
8.3. Gaussian Filters
8.3.1. Kalman Filter
8.3.2. Information Filter
8.3.3. Adjustment and Parameterization of Gaussian Filters
 Structure and Content | 33

8.4. Stereo EKF-SLAM

8.4.1. Stereo Camera Geometry
8.4.2. Feature Extraction and Search
8.4.3. Kalman Filter for Stereo SLAM
8.4.4. Stereo EKF-SLAM Parameter Setting
8.5. Monocular EKF-SLAM
8.5.1. EKF-SLAM Landmark Parameterization
8.5.2. Kalman Filter for Monocular SLAM
8.5.3. Monocular EKF-SLAM Parameter Tuning
8.6. Loop Closure Detection
8.6.1. Brute Force Algorithm
8.6.2. FABMAP
8.6.3. Abstraction Using GIST and HOG
8.6.4. Deep Learning Detection
8.7. Graph-SLAM
8.7.1. Graph-SLAM
8.7.2. RGBD-SLAM
8.7.3. ORB-SLAM
8.8. Direct Visual SLAM
8.8.1. Analysis of the Direct Visual SLAM Algorithm
8.8.2. LSD-SLAM
8.8.3. SVO
8.9. Visual Inertial SLAM
8.9.1. Integration of Inertial Measurements
8.9.2. Low Coupling: SOFT-SLAM
8.9.3. High Coupling: Vins-Mono
8.10. Other SLAM Technologies
8.10.1. Applications Beyond Visual SLAM
8.10.2. Lidar-SLAM
8.10.2. Range-only SLAM
 34 | Structure and Content

Module 9. Application of Virtual and Augmented Reality Technologies

to Robotics
9.1. Immersive Technologies in Robotics
9.1.1. Virtual Reality in Robotics
9.1.2. Augmented Reality in Robotics
9.1.3. Mixed Reality in Robotics
9.1.4. Difference between Realities
9.2. Construction of Virtual Environments
9.2.1. Materials and Textures
9.2.2. Lighting
9.2.3. Virtual Sound and Smell
9.3. Robot Modeling in Virtual Environments
9.3.1. Geometric Modeling
9.3.2. Physical Modeling
9.3.3. Model Standardization
9.4. Modeling of Robot Dynamics and Kinematics Virtual Physical Engines
9.4.1. Physical Motors. Typology
9.4.2. Configuration of a Physical Engine
9.4.3. Physical Motors in the Industry
9.5. Platforms, Peripherals and Tools Most Commonly Used in Virtual Reality
9.5.1. Virtual Reality Viewers
9.5.2. Interaction Peripherals
9.5.3. Virtual Sensors
9.6. Augmented Reality Systems
9.6.1. Insertion of Virtual Elements into Reality
9.6.2. Types of Visual Markers
9.6.3. Augmented Reality Technologies
9.7. Metaverse: Virtual Environments of Intelligent Agents and People
9.7.1. Avatar Creation
9.7.2. Intelligent Agents in Virtual Environments
9.7.3. Construction of Multi-User Environments for VR/AR
 Structure and Content | 35

9.8. Creation of Virtual Reality Projects for Robotics 10.5. Dialog Management: Heuristic/Probabilistic Strategies
9.8.1. Phases of Development of a Virtual Reality Project 10.5.1. Interlocutor's Intention
9.8.2. Deployment of Virtual Reality Systems 10.5.2. Template-Based Dialog
9.8.3. Virtual Reality Resources 10.5.3. Stochastic Dialog Management: Bayesian Networks
9.9. Creating Augmented Reality Projects for Robotics 10.6. Dialog Management: Advanced Strategies
9.9.1. Phases of Development of an Augmented Reality Project 10.6.1. Reinforcement-Based Learning Systems
9.9.2. Deployment of Augmented Reality Projects 10.6.2. Neural Network-Based Systems
9.9.3. Augmented Reality Resources 10.6.3. From Speech to Intention in a Single Network
9.10. Robot Teleoperation with Mobile Devices 10.7. Response Generation and Speech Synthesis
9.10.1. Mixed Reality on Mobile Devices 10.7.1. Response Generation: From Idea to Coherent Text
9.10.2. Immersive Systems using Mobile Device Sensors 10.7.2. Speech Synthesis by Concatenation
9.10.3. Examples of Mobile Projects 10.7.3. Stochastic Speech Synthesis
10.8. Dialog Adaptation and Contextualization
Module 10. Robot Communication and Interaction Systems
10.8.1. Dialog Initiative
10.1. Speech Recognition: Stochastic Systems 10.8.2. Adaptation to the Speaker
10.1.1. Acoustic Speech Modeling 10.8.3. Adaptation to the Context of the Dialogue
10.1.2. Hidden Markov Models 10.9. Robots and Social Interactions: Emotion Recognition, Synthesis and Expression
10.1.3. Linguistic Speech Modeling: N-Grams, BNF Grammars 10.9.1. Artificial Voice Paradigms: Robotic Voice and Natural Voice
10.2. Speech Recognition Deep Learning 10.9.2. Emotion Recognition and Sentiment Analysis
10.2.1. Deep Neural Networks 10.9.3. Emotional Voice Synthesis
10.2.2. Recurrent Neural Networks 10.10. Robots and Social Interactions: Advanced Multimodal Interfaces
10.2.3. LSTM Cells 10.10.1. Combination of Vocal and Tactile Interfaces
10.3. Speech Recognition: Prosody and Environmental Effects 10.10.2. Sign Language Recognition and Translation
10.3.1. Ambient Noise 10.10.3. Visual Avatars: Voice to Sign Language Translation
10.3.2. Multi-Speaker Recognition
10.3.3. Speech Pathologies
10.4. Natural Language Understanding: Heuristic and Probabilistic Systems
10.4.1. Syntactic-Semantic Analysis: Linguistic Rules
10.4.2. Comprehension Based on Heuristic Rules
10.4.3. Probabilistic Systems: Logistic Regression and SVM
10.4.4. Understanding Based on Neural Networks
06
Methodology
This academic program offers students a different way of learning. Our methodology
uses a cyclical learning approach: Relearning.
This teaching system is used, for example, in the most prestigious medical schools in
the world, and major publications such as the New England Journal of Medicine have
considered it to be one of the most effective.
 Methodology | 37

Discover Relearning, a system that abandons

conventional linear learning, to take you through
cyclical teaching systems: a way of learning that
has proven to be extremely effective, especially in
subjects that require memorization"
 38 | Methodology

Case Study to contextualize all content

Our program offers a revolutionary approach to developing skills and
knowledge. Our goal is to strengthen skills in a changing, competitive, and
highly demanding environment.

At TECH, you will experience a

learning methodology that is shaking
the foundations of traditional
universities around the world"

You will have access to a

learning system based on repetition,
with natural and progressive teaching
throughout the entire syllabus.
 Methodology | 39

A learning method that is different and innovative

This TECH program is an intensive educational program, created from scratch,
which presents the most demanding challenges and decisions in this field,
both nationally and internationally. This methodology promotes personal and
professional growth, representing a significant step towards success. The case
method, a technique that lays the foundation for this content, ensures that the
most current economic, social and professional reality is taken into account.

Our program prepares you to face new

challenges in uncertain environments
and achieve success in your career”

The case method is the most widely used learning system in the best faculties in the
world. The case method was developed in 1912 so that law students would not only
learn the law based on theoretical content. It consisted of presenting students with
real-life, complex situations for them to make informed decisions and value judgments
on how to resolve them. In 1924, Harvard adopted it as a standard teaching method.
The student will learn to solve What should a professional do in a given situation? This is the question that you are
complex situations in real business presented with in the case method, an action-oriented learning method. Throughout
environments through collaborative the program, the studies will be presented with multiple real cases. They will have to

activities and real cases. combine all their knowledge and research, and argue and defend
their ideas and decisions.
 40 | Methodology

Relearning Methodology
TECH effectively combines the Case Study methodology with a
100% online learning system based on repetition, which combines 8
different teaching elements in each lesson.

We enhance the Case Study with the best 100% online teaching
method: Relearning.

In 2019, we obtained the best learning

results of all online universities in the world.

At TECH, you will learn using a cutting-edge methodology designed

to train the executives of the future. This method, at the forefront of
international teaching, is called Relearning.

Our university is the only one in the world authorized to employ this
successful method. In 2019, we managed to improve our students'
overall satisfaction levels (teaching quality, quality of materials, course
structure, objectives...) based on the best online university indicators.
 Methodology | 41

In our program, learning is not a linear process, but rather a spiral (learn, unlearn,
forget, and re-learn). Therefore, we combine each of these elements concentrically.
This methodology has trained more than 650,000 university graduates with
unprecedented success in fields as diverse as biochemistry, genetics, surgery,
international law, management skills, sports science, philosophy, law, engineering,
journalism, history, and financial markets and instruments. All this in a highly
demanding environment, where the students have a strong socio-economic profile
and an average age of 43.5 years.

Relearning will allow you to learn with less effort and

better performance, involving you more in your training,
developing a critical mindset, defending arguments, and
contrasting opinions: a direct equation for success.

From the latest scientific evidence in the field of neuroscience, not only do we know
how to organize information, ideas, images and memories, but we know that the
place and context where we have learned something is fundamental for us to be able
to remember it and store it in the hippocampus, to retain it in our long-term memory.

In this way, and in what is called neurocognitive context-dependent e-learning, the

different elements in our program are connected to the context where the individual
carries out their professional activity.
 42 | Methodology

This program offers the best educational material, prepared with professionals in mind:

30%
Study Material
All teaching material is produced by the specialists who teach the course, specifically
for the course, so that the teaching content is highly specific and precise.
These contents are then applied to the audiovisual format, to create the TECH online
working method. All this, with the latest techniques that offer high quality pieces in each
and every one of the materials that are made available to the student.

Classes
There is scientific evidence suggesting that observing third-party experts can
be useful.
Learning from an Expert strengthens knowledge and memory, and generates
confidence in future difficult decisions.

Practising Skills and Abilities 10%

They will carry out activities to develop specific skills and abilities in each subject area.
Exercises and activities to acquire and develop the skills and abilities that a specialist
needs to develop in the context of the globalization that we are experiencing.

Additional Reading
8%
Recent articles, consensus documents and international guidelines, among others.
In TECH's virtual library, students will have access to everything they need to
complete their course.
 Methodology | 43

Case Studies
Students will complete a selection of the best case studies chosen specifically
for this program. Cases that are presented, analyzed, and supervised by the best
specialists in the world.

20%

Interactive Summaries
The TECH team presents the contents attractively and dynamically in multimedia
lessons that include audio, videos, images, diagrams, and concept maps in order to
reinforce knowledge.
This exclusive educational system for presenting multimedia content was awarded
by Microsoft as a "European Success Story".

25%
Testing & Retesting
We periodically evaluate and re-evaluate students’ knowledge throughout the
4% program, through assessment and self-assessment activities and exercises, so that
3% they can see how they are achieving their goals.
07
Certificate
The Professional Master’s Degree in Robotics guarantees students, in addition
to the most rigorous and up-to-date education, access to a Professional
Master’s Degree issued by TECH Technological University.
 Certificate | 45

Successfully complete this program and receive

your Postgraduate Certificate without having to
travel or fill out laborious paperwork"
 46 | Certificate

This Professional Master's Degree in Robotics contains the most complete and The diploma issued by TECH Technological University will reflect the qualification
up-to-date program on the market. obtained in the Professional Master's Degree, and meets the requirements commonly
demanded by labor exchanges, competitive examinations, and professional career
After the student has passed the assessments, they will receive their corresponding
evaluation committees.
Professional Master’s Degree issued by TECH Technological University via tracked
delivery*. Title: Professional Master's Degree in Robotics
Official Nº of Hours: 1,500 h.

*Apostille Convention. In the event that the student wishes to have their paper diploma issued with an apostille, TECH EDUCATION will make the necessary arrangements to obtain it, at an additional cost.
Professional Master’s
Degree
Robotics
» Modality: online
» Duration: 12 months
» Certificate: TECH Technological University
» Dedication: 16h/week
» Schedule: at your own pace
» Exams: online
Professional Master's Degree
Robotics