Become an expert in Robotics and Computer Vision in 24 months with this TECH Global University Advanced master’s degree. Enroll now"

The rise of Artificial Intelligence and Robotics is changing the technological, economic and social landscape globally. In this context, specialization
in areas such as Machine Vision is crucial to keep up to date in an environment of rapid advances and disruptive changes. The increasing interaction between humans and machines, and the need to process visual information efficiently, requires highly skilled professionals to lead innovation and address the challenges. 

An ideal scenario for engineering professionals who want to advance an emerging sector. For this reason, TECH Global University has designed this Advanced master’s degree in Robotics and Artificial Vision, which provides comprehensive training in these emerging disciplines, covering topics such as Augmented Reality, Artificial Intelligence and visual information processing in machines, among others. 

A program that offers a theoretical-practical approach that allows graduates to apply their knowledge in real environments. All this, in addition, in a 100% online university degree, which allows students to adapt their learning to their personal and professional responsibilities. Thus, they will have access to high quality educational materials, such as videos, essential readings and detailed resources, providing them with a global vision of Robotics and Artificial Vision. 

Likewise, thanks to the Relearning method, based on the continuous repetition of the most important contents, the student will reduce the hours of study and will consolidate the most important concepts in a simpler way. 

A unique degree in the academic panorama that is also distinguished by the excellent team of specialists in this field, by the excellent team of specialists in this field. His excellent knowledge and experience and experience in the sector is evident in an advanced syllabus, which only TECH Global University.  

Become an innovation leader and address ethical and safety challenges in creating innovative and effective solutions in different industry sectors" 

This Advanced master’s degree in Robotics and Artificial Vision contains the most complete and up-to-date program on the market. The most important features include:  

• The development of case studies presented by IT experts
• The graphic, schematic, and practical contents with which they are created, provide scientific and practical information on the disciplines that are essential for professional practice
• Practical exercises where the self-assessment process can be carried out to improve learning
• Special emphasis on innovative methodologies in the development of Robots and Artificial Vision 
• Theoretical lessons, questions to the expert, debate forums on controversial topics, and individual reflection assignments 
• Content that is accessible from any fixed or portable device with an Internet connection 

Take advantage of the opportunity to study in a 100% online program, adapting your study time to your personal and professional circumstances"

Its teaching staff includes professionals from the field of Robotics, who bring to this program the experience of their work, as well as recognized specialists from reference 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 deliver an immersive learning experience, programmed to prepare in real situations. 

This program is designed around Problem-Based Learning, whereby students must try to solve the different professional practice situations that arise throughout the program. For this purpose, professionals will be assisted by an innovative interactive video system created by renowned and experienced experts.

Analyze through the best didactic material how to carry out the tuning and parameterization of SLAM algorithms" 

Delve whenever and wherever you want into the advances achieved in Deep learning" 

The Advanced master’s degree in Robotics and Artificial Vision is presented as an excellent option for engineering professionals looking to specialize in this cutting-edge field. The program modules are developed in a progressive order, allowing students to acquire knowledge gradually and efficiently. It also offers the opportunity to learn about robot design, programming and control, as well as machine vision algorithms and machine learning techniques, essential skills for success in this constantly evolving field, and all this with a Virtual Library, accessible 24 hours a day from any digital device with an internet connection.

Get a global view on Robotics and Machine Vision, thanks to access to high quality educational materials"

Module 1. Robotic. Robot Design and Modeling 

1.1. Robotics and Industry 4.0 

1.1.1. Robotics and Industry 4.0 
1.1.2. Application Fields and Use Cases 
1.1.3. Sub-Areas of Specialization in Robotics 

1.2. Robot Hardware and Software Architectures 

1.2.1. Hardware Architectures and Real-Time 
1.2.2. Robot Software Architectures 
1.2.3. Communication Models and Middleware Technologies 
1.2.4. Robot Operating System (ROS) Software Integration 

1.3. Mathematical Modeling of Robots 

1.3.1. Mathematical Representation of Rigid Solids 
1.3.2. Rotations and Translations 
1.3.3. Hierarchical State Representation 
1.3.4. Distributed Representation of the State in ROS (TF Library) 

1.4. Robot Kinematics and Dynamics 

1.4.1. Kinematics 
1.4.2. Dynamics 
1.4.3. Underactuated Robots 
1.4.4. Redundant Robots 

1.5. Robot Modeling and Simulation 

1.5.1. Robot Modeling Technologies 
1.5.2. Robot Modeling with URDF 
1.5.3. Robot Simulation 
1.5.4. Modeling with Gazebo Simulator 

1.6. Robot Manipulators 

1.6.1. Types of Manipulator Robots 
1.6.2. Kinematics 
1.6.3. Dynamics 
1.6.4. Simulation 

1.7. Terrestrial Mobile Robots 

1.7.1. Types of Terrestrial Mobile Robots 
1.7.2. Kinematics 
1.7.3. Dynamics 
1.7.4. Simulation 

1.8. Aerial Mobile Robots 

1.8.1. Types of Aerial Mobile Robots 
1.8.2. Kinematics 
1.8.3. Dynamics 
1.8.4. Simulation 

1.9. Aquatic Mobile Robots 

1.9.1. Types of Aquatic Mobile Robots 
1.9.2. Kinematics 
1.9.3. Dynamics 
1.9.4. Simulation 

1.10. Bioinspired Robots 

1.10.1. Humanoids 
1.10.2. Robots with Four or More Legs 
1.10.3. Modular Robots 
1.10.4. Robots with flexible parts (Soft-Robotics) 

Module 2. Intelligent Agents. Application of Artificial Intelligence to robots and softbots

2.1. Intelligent Agents and Artificial Intelligence 

2.1.1. Intelligent Robots. Artificial Intelligence 
2.1.2. Intelligent Agents 

2.1.2.1. Hardware Agents. Robots 
2.1.2.2. Software Agents. Softbots 

2.1.3. Robotics Applications 

2.2. Brain-Algorithm Connection 

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 

2.3. Search Algorithms in the Solution Space 

2.3.1. Elements in Solution Space Searches 
2.3.2. Solution Search Algorithms in Artificial Intelligence Problems 
2.3.3. Applications of Search and Optimization Algorithms 
2.3.4. Search Algorithms Applied to Machine Learning 

2.4. Machine Learning 

2.4.1. Machine Learning 
2.4.2. Supervised Learning Algorithms 
2.4.3. Unsupervised Learning Algorithms 
2.4.4. Reinforcement Learning Algorithms 

2.5. Supervised Learning 

2.5.1. Supervised Learning Methods 
2.5.2. Decision Trees for Classification 
2.5.3. Support Vector Machines 
2.5.4. Artificial Neural Networks 
2.5.5. Applications of Supervised Learning 

2.6. Unsupervised Learning 

2.6.1. Unsupervised Learning 
2.6.2. Kohonen Networks 
2.6.3. Self-Organizing Maps 
2.6.4. K-Means Algorithm 

2.7. Reinforcement Learning 

2.7.1. Reinforcement Learning 
2.7.2. Agents Based on Markov Processes 
2.7.3. Reinforcement Learning Algorithms 
2.6.4. Reinforcement Learning Applied to Robotics 

2.8. Probabilistic Inference 

2.8.1. Probabilistic Inference 
2.8.2. Types of Inference and Method Definition 
2.8.3. Bayesian Inference as a Case Study 
2.8.4. Nonparametric Inference Techniques 
2.8.5. Gaussian Filters 

2.9. From Theory to Practice: Developing an Intelligent Robotic Agent 

2.9.1. Inclusion of Supervised Learning Modules in a Robotic Agent 
2.9.2. Inclusion of Reinforcement Learning Modules in a Robotic Agent 
2.9.3. Architecture of a Robotic Agent Controlled by Artificial Intelligence 
2.9.4. Professional Tools for the Implementation of the Intelligent Agent 
2.9.5. Phases of the Implementation of AI Algorithms in Robotic Agents  

Module 3. Deep Learning  

3.1. Artificial Intelligence  

3.1.1. Machine Learning  
3.1.2. Deep Learning  
3.1.3. The Explosion of Deep Learning Why Now?  

3.2. Neural Networks  

3.2.1. The Neural Network  
3.2.2. Uses of Neural Networks  
3.2.3. Linear Regression and Perceptron  
3.2.4. Forward Propagation  
3.2.5. Backpropagation  
3.2.6. Feature Vectors  

3.3. Loss Functions  

3.3.1. Loss Functions  
3.3.2. Types of Loss Functions  
3.3.3. Choice of Loss Functions  

3.4. Activation Functions  

3.4.1. Activation Function  
3.4.2. Linear Functions  
3.4.3. Non-Linear Functions  
3.4.4. Output vs. Hidden Layer Activation Functions  

3.5. Regularization and Normalization  

3.5.1. Regularization and Normalization  
3.5.2. Overfitting and Data Augmentation  
3.5.3. Regularization Methods: L1, L2 and Dropout  
3.5.4. Normalization Methods: Batch, Weight, Layer 

3.6. Optimization  

3.6.1. Gradient Descent  
3.6.2. Stochastic Gradient Descent  
3.6.3. Mini Batch Gradient Descent  
3.6.4. Momentum  
3.6.5. Adam  

3.7. Hyperparameter Tuning and Weights  

3.7.1. Hyperparameters  
3.7.2. Batch Size vs. Learning Rate Vs. Step Decay  
3.7.3. Weights  

3.8. Evaluation Metrics of a Neural Network  

3.8.1. Accuracy  
3.8.2. Dice Coefficient  
3.8.3. Sensitivity Vs. Specificity/Recall vs. Precision  
3.8.4. ROC Curve (AUC)  
3.8.5. F1-Score  
3.8.6. Matrix Confusion  
3.8.7. Cross-Validation  

3.9. Frameworks and Hardware  

3.9.1. Tensor Flow  
3.9.2. Pytorch  
3.9.3. Caffe  
3.9.4. Keras  
3.9.5. Hardware for the Learning Phase   

3.10. Creation of a Neural Network-Training and Validation

3.10.1. Dataset  
3.10.2. Network Construction  
3.10.3. Education  
3.10.4. Visualization of Results  

Module 4. Robotics in the Automation of Industrial Processes 

4.1. Design of Automated Systems 

4.1.1. Hardware Architectures 
4.1.2. Programmable Logic Controllers 
4.1.3. Industrial Communication Networks 

4.2. Advanced Electrical Design I: Automation 

4.2.1. Design of Electrical Panels and Symbology 
4.2.2. Power and Control Circuits Harmonics 
4.2.3. Protection and Grounding Elements 

4.3. Advanced Electrical Design II: Determinism and Safety 

4.3.1. Machine Safety and Redundancy 
4.3.2. Safety Relays and Triggers 
4.3.3. Safety PLCs 
4.3.4. Safe Networks 

4.4. Electrical Actuation 

4.4.1. Motors and Servomotors 
4.4.2. Frequency Inverters and Controllers 
4.4.3. Electrically Actuated Industrial Robotics 

4.5. Hydraulic and Pneumatic Actuation 

4.5.1. Hydraulic Design and Symbology 
4.5.2. Pneumatic Design and Symbology 
4.5.3. ATEX Environments in Automation 

4.6. Transducers in Robotics and Automation 

4.6.1. Position and Velocity Measurement 
4.6.2. Force and Temperature Measurement 
4.6.3. Presence Measurement 
4.6.4. Vision Sensors 

4.7. Programming and Configuration of Programmable Logic Controllers PLCs 

4.7.1. PLC Programming: LD 
4.7.2. PLC Programming: ST 
4.7.3. PLC Programming: FBD and CFC 
4.7.4. PLC Programming: SFC 

4.8. Programming and Configuration of Equipment in Industrial Plants 

4.8.1. Programming of Drives and Controllers 
4.8.2. HMI Programming 
4.8.3. Programming of Manipulator Robots 

4.9. Programming and Configuration of Industrial Computer Equipment 

4.9.1. Programming of Vision Systems 
4.9.2. SCADA/Software Programming 
4.9.3. Network Configuration 

4.10. Automation Implementation 

4.10.1. State Machine Design 
4.10.2. Implementation of State Machines in PLCs 
4.10.3. Implementation of Analog PID Control Systems in PLCs 
4.10.4. Automation Maintenance and Code Hygiene 
4.10.5. Automation and Plant Simulation 

Module 5. Automatic Control Systems in Robotics 

5.1. Analysis and Design of Nonlinear Systems 

5.1.1. Analysis and Modeling of Nonlinear Systems 
5.1.2. Feedback Control 
5.1.3. Linearization by Feedback 

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

5.2.1. Sliding Mode control 
5.2.2. Lyapunov and Backstepping Control 
5.2.3. Control Based on Passivity 

5.3. Control Architectures 

5.3.1. The Robotics Paradigm 
5.3.2. Control Architectures 
5.3.3. Applications and Examples of Control Architectures 

5.4. Motion Control for Robotic Arms 

5.4.1. Kinematic and Dynamic Modeling 
5.4.2. Control in Joint Space 
5.4.3. Control in Operational Space 

5.5. Actuator Force Control 

5.5.1. Force Control 
5.5.2. Impedance Control 
5.5.3. Hybrid Control 

5.6. Terrestrial Mobile Robots 

5.6.1. Equations of Motion 
5.6.2. Control Techniques for Terrestrial Robots 
5.6.3. Mobile Manipulators 

5.7. Aerial Mobile Robots 

5.7.1. Equations of Motion 
5.7.2. Control Techniques in Aerial Robots 
5.7.3. Aerial Manipulation 

5.8. Control Based on Machine Learning Techniques 

5.8.1. Control Using Supervised Learning 
5.8.2. Control Using Reinforced Learning 
5.8.3. Control Using Non-Supervised Learning 

5.9. Vision-Based Control 

5.9.1. Position-Based Visual Servoing 
5.9.2. Image-Based Visual Servoing 
5.9.3. Hybrid Visual Servoing 

5.10. Predictive Control 

5.10.1. Models and State Estimation 
5.10.2. MPC Applied to Mobile Robots 
5.10.3. MPC Applied to UAVs

Module 6. Planning Algorithms in Robots 

6.1. Classical Planning Algorithms 

6.1.1. Discrete Planning: State Space 
6.1.2. Planning Problems in Robotics. Robotic Systems Models 
6.1.3. Classification of Planners 

6.2. The Trajectory Planning Problem in Mobile Robots 

6.2.1. Forms of Environment Representation: Graphs 
6.2.2. Search Algorithms in Graphs 
6.2.3. Introduction of Costs in Networks 
6.2.4. Search Algorithms in Heavy Networks 
6.2.5. Algorithms with any Angle Approach 

6.3. Planning in High Dimensional Robotic Systems 

6.3.1. High Dimensionality Robotics Problems: Manipulators 
6.3.2. Direct/Inverse Kinematic Model 
6.3.3. Sampling Planning Algorithms PRM and RRT 
6.3.4. Planning Under Dynamic Constraints 

6.4. Optimal Sampling Planning 

6.4.1. Problem of Sampling-Based Planners 
6.4.2. RRT* Probabilistic Optimality Concept 
6.4.3. Reconnection Step: Dynamic Constraints 
6.4.4. CForest. Parallelizing Planning 

6.5. Real Implementation of a Motion Planning System 

6.5.1. Global Planning Problem. Dynamic Environments 
6.5.2. Cycle of Action, Sensorization. Acquisition of Information from the Environment 
6.5.3. Local and Global Planning 

6.6. Coordination in Multi-Robot Systems I: Centralized System 

6.6.1. Multirobot Coordination Problem 
6.6.2. Collision Detection and Resolution: Trajectory Modification with Genetic Algorithms 
6.6.3. Other Bio-Inspired Algorithms: Particle Swarm and Fireworks 
6.6.4. Collision Avoidance by Choice of Maneuver Algorithm 

6.7. Coordination in Multi-Robot Systems II: Distributed Approaches I 

6.7.1. Use of Complex Objective Functions 
6.7.2. Pareto Front 
6.7.3. Multi-Objective Evolutionary Algorithms 

6.8. Coordination in Multi-Robot Systems III: Distributed Approaches II 

6.8.1. Order 1 Planning Systems 
6.8.2. ORCA Algorithm 
6.8.3. Addition of Kinematic and Dynamic Constraints in ORCA 

6.9. Decision Planning Theory 

6.9.1. Decision Theory 
6.9.2. Sequential Decision Systems 
6.9.3. Sensors and Information Spaces 
6.9.4. Planning for Uncertainty in Sensing and Actuation 

6.10. Reinforcement Learning Planning Systems 

6.10.1. Obtaining the Expected Reward of a System 
6.10.2. Mean Reward Learning Techniques 
6.10.3. Inverse Reinforcement Learning  

Module 7. Computer Vision  

7.1. Human Perception  

7.1.1. Human Visual System  
7.1.2. Color  
7.1.3. Visible and Non-Visible Frequencies  

7.2. Chronicle of the Computer Vision  

7.2.1. Principles  
7.2.2. Evolution  
7.2.3. The Importance of Computer Vision  

7.3. Digital Image Composition  

7.3.1. The Digital Image  
7.3.2. Types of Images  
7.3.3. Color Spaces  
7.3.4. RGB  
7.3.5. HSV and HSL  
7.3.6. CMY-CMYK  
7.3.7. YCbCr  
7.3.8. Indexed Image  

7.4. Image Acquisition Systems  

7.4.1. Operation of a Digital Camera  
7.4.2. The Correct Exposure for Each Situation  
7.4.3. Depth of Field  
7.4.4. Resolution  
7.4.5. Image Formats  
7.4.6. HDR Mode  
7.4.7. High Resolution Cameras  
7.4.8. High-Speed Cameras  

7.5. Optical Systems  

7.5.1. Optical Principles  
7.5.2. Conventional Lenses  
7.5.3. Telecentric Lenses  
7.5.4. Types of Autofocus Lenses  
7.5.5. Focal Length  
7.5.6. Depth of Field  
7.5.7. Optical Distortion  
7.5.8. Calibration of an Image  

7.6. Illumination Systems  

7.6.1. Importance of Illumination  
7.6.2. Frequency Response  
7.6.3. LED Illumination  
7.6.4. Outdoor Lighting  
7.6.5. Types of Lighting for Industrial Applications. Effects  

7.7. 3D Acquisition Systems  

7.7.1. Stereo Vision  
7.7.2. Triangulation  
7.7.3. Structured Light  
7.7.4. Time of Flight  
7.7.5. Lidar  

7.8. Multispectrum  

7.8.1. Multispectral Cameras  
7.8.2. Hyperspectral Cameras  

7.9. Non-Visible Near Spectrum  

7.9.1. IR Cameras  
7.9.2. UV Cameras  
7.9.3. Converting From Non-Visible to Visible by Illumination  

7.10. Other Band Spectrums  

7.10.1. X-Ray  
7.10.2. terahertz 

Module 8. Applications and State-of-the-Art 

8.1. Industrial Applications  

8.1.1. Machine Vision Libraries  
8.1.2. Compact Cameras  
8.1.3. PC-Based Systems  
8.1.4. Industrial Robotics  
8.1.5. Pick and place 2D  
8.1.6. Bin Picking  
8.1.7. Quality Control  
8.1.8. Presence Absence of Components  
8.1.9. Dimensional Control  
8.1.10. Labeling Control  
8.1.11. Traceability  

8.2. Autonomous Vehicles  

8.2.1. Driver Assistance  
8.2.2. Autonomous Driving  

8.3. Artificial Vision for Content Analysis  

8.3.1. Filtering by Content  
8.3.2. Visual Content Moderation  
8.3.3. Tracking Systems  
8.3.4. Brand and Logo Identification  
8.3.5. Video Labeling and Classification  
8.3.6. Scene Change Detection  
8.3.7. Text or Credits Extraction  

8.4. Medical Application  

8.4.1. Disease Detection and Localization  
8.4.2. Cancer and X-Ray Analysis  
8.4.3. Advances in Artificial Vision Due to Covid-19  
8.4.4. Assistance in the Operating Room  

8.5. Spatial Applications  

8.5.1. Satellite Image Analysis  
8.5.2. Computer Vision for the Study of Space  
8.5.3. Mission to Mars  

8.6. Commercial Applications  

8.6.1. Stock Control  
8.6.2. Video Surveillance, Home Security  
8.6.3. Parking Cameras  
8.6.4. Population Control Cameras  
8.6.5. Speed Cameras  

8.7. Vision Applied to Robotics  

8.7.1. Drones  
8.7.2. AGV  
8.7.3. Vision in Collaborative Robots  
8.7.4. The Eyes of the Robots  

8.8. Augmented Reality  

8.8.1. Operation  
8.8.2. Devices  
8.8.3. Applications in the Industry  
8.8.4. Commercial Applications  

8.9. Cloud Computing  

8.9.1. Cloud Computing Platforms  
8.9.2. From cloud computing to production  

8.10. Research and State-of-the-Art  

8.10.1. Commercial Applications  
8.10.2. What's Cooking?  
8.10.3. The Future of Computer Vision  

Module 9. Artificial Vision Techniques in Robotics: Image Processing and Analysis 

9.1. Computer Vision 

9.1.1. Computer Vision 
9.1.2. Elements of a Computer Vision System 
9.1.3. Mathematical Tools 

9.2. Optical Sensors for Robotics 

9.2.1. Passive Optical Sensors 
9.2.2. Active Optical Sensors 
9.2.3. Non-Optical Sensors 

9.3. Image Acquisition 

9.3.1. Image Representation 
9.3.2. Color Space 
9.3.3. Digitizing Process 

9.4. Image Geometry 

9.4.1. Lens Models 
9.4.2. Camera Models 
9.4.3. Camera Calibration 

9.5. Mathematical Tools 

9.5.1. Histogram of an Image 
9.5.2. Convolution 
9.5.3. Fourier Transform 

9.6. Image Preprocessing 

9.6.1. Noise Analysis 
9.6.2. Image Smoothing 
9.6.3. Image Enhancement 

9.7. Image Segmentation 

9.7.1. Contour-Based Techniques 
9.7.3. Histogram-Based Techniques 
9.7.4. Morphological Operations 

9.8. Image Feature Detection 

9.8.1. Point of Interest Detection 
9.8.2. Feature Descriptors 
9.8.3. Feature Matching 

9.9. 3D Vision Systems 

9.9.1. 3D Perception 
9.9.2. Feature Matching between Images 
9.9.3. Multiple View Geometry 

9.10. Computer Vision based Localization 

9.10.1. The Robot Localization Problem 
9.10.2. Visual Odometry 
9.10.3. Sensory Fusion  

Module 10. Robot Visual Perception Systems with Automatic Learning

10.1. Unsupervised Learning Methods applied to Computer Vision 

10.1.1. Clustering 
10.1.2. PCA 
10.1.3. Nearest Neighbors 
10.1.4. Similarity and Matrix Decomposition 

10.2. Supervised Learning Methods Applied to Computer Vision 

10.2.1. Concept “Bag of words” 
10.2.2. Support Vector Machine 
10.2.3. Latent Dirichlet Allocation 
10.2.4. Neural Networks 

10.3. Deep Neural Networks:: Structures, Backbones and Transfer Learning 

10.3.1. Feature Generating Layers 

10.3.3.1. VGG 
10.3.3.2. Densenet 
10.3.3.3. ResNet 
10.3.3.4. Inception 
10.3.3.5. GoogLeNet 

10.3.2. Transfer Learning 
10.3.3. The Data Preparation for Training 

10.4. Computer Vision with Deep Learning I: Detection and Segmentation

10.4.1. YOLO and SSD Differences and Similarities 
10.4.2. Unet 
10.4.3. Other Structures 

10.5. Computer Vision with Deep Learning II: Generative Adversarial Networks 

10.5.1. Image Super-Resolution Using GAN 
10.5.2. Creation of Realistic Images 
10.5.3. Scene Understanding 

10.6. Learning Techniques for Localization and Mapping in Mobile Robotics 

10.6.1. Loop Closure Detection and Relocation 
10.6.2. Magic Leap. Super Point and Super Glue 
10.6.3. Depth from Monocular 

10.7. Bayesian Inference and 3D Modeling 

10.7.1. Bayesian Models and "Classical" Learning 
10.7.2. Implicit Surfaces with Gaussian Processes (GPIS) 
10.7.3. 3D Segmentation Using GPIS 
10.7.4. Neural Networks for 3D Surface Modeling 

10.8. End-to-End Applications of Deep Neural Networks 

10.8.1. End-to-End System. Example of Person Identification 
10.8.2. Object Manipulation with Visual Sensors 
10.8.3. Motion Generation and Planning with Visual Sensors 

10.9. Cloud Technologies to Accelerate the Development of Deep Learning Algorithms 

10.9.1. Use of GPUs for Deep Learning 
10.9.2. Agile development with Google IColab 
10.9.3. Remote GPUs, Google Cloud and AWS 

10.10. Deployment of Neural Networks in Real Applications 

10.10.1. Embedded Systems 
10.10.2. Deployment of Neural Networks. Use 
10.10.3. Network Optimizations in Deployment, Example with TensorRT

Module 11. Visual SLAM. Robot Localization and Simultaneous Mapping by Computer Vision Techniques 

11.1. Simultaneous Localization and Mapping (SLAM) 

11.1.1. Simultaneous Localization and Mapping. SLAM 
11.1.2. SLAM Applications 
11.1.3. SLAM Operation 

11.2. Projective Geometry 

11.2.1. Pin-Hole Model 
11.2.2. Estimation of Intrinsic Parameters of a Chamber 
11.2.3. Homography, Basic Principles and Estimation 
11.2.4. Fundamental Matrix, Principles and Estimation 

11.3. Gaussian Filters 

11.3.1. Kalman Filter 
11.3.2. Information Filter 
11.3.3. Adjustment and Parameterization of Gaussian Filters 

11.4. Stereo EKF-SLAM 

11.4.1. Stereo Camera Geometry 
11.4.2. Feature Extraction and Search 
11.4.3. Kalman Filter for Stereo SLAM 
11.4.4. Stereo EKF-SLAM Parameter Setting 

11.5. Monocular EKF-SLAM 

11.5.1. EKF-SLAM Landmark Parameterization 
11.5.2. Kalman Filter for Monocular SLAM 
11.5.3. Monocular EKF-SLAM Parameter Tuning 

11.6. Loop Closure Detection 

11.6.1. Brute Force Algorithm 
11.6.2. FABMAP 
11.6.3. Abstraction Using GIST and HOG 
11.6.4. Deep Learning Detection 

11.7. Graph-SLAM 

11.7.1. Graph-SLAM 
11.7.2. RGBD-SLAM 
11.7.3. ORB-SLAM 

11.8. Direct Visual SLAM 

11.8.1. Analysis of the Direct Visual SLAM algorithm 
11.8.2. LSD-SLAM 
11.8.3. SVO 

11.9. Visual Inertial SLAM 

11.9.1. Integration of Inertial Measurements 
11.9.2. Low Coupling: SOFT-SLAM 
11.9.3. High Coupling: Vins-Mono 

11.10. Other SLAM Technologies 

11.10.1. Applications Beyond Visual SLAM 
11.10.2. Lidar-SLAM 
11.10.3. Range-only SLAM  

Module 12. Application of Virtual and Augmented Reality Technologies to Robotics 

12.1. Immersive Technologies in Robotics 

12.1.1. Virtual Reality in Robotics 
12.1.2. Augmented Reality in Robotics 
12.1.3. Mixed Reality in Robotics 
12.1.4. Difference between Realities 

12.2. Construction of Virtual Environments 

12.2.1. Materials and Textures 
12.2.2. Lighting 
12.2.3. Virtual Sound and Smell 

12.3. Robot Modeling in Virtual Environments 

12.3.1. Geometric Modeling 
12.3.2. Physical Modeling 
12.3.3. Model Standardization 

12.4. Modeling of Robot Dynamics and Kinematics Virtual Physical Engines 

12.4.1. Physical Motors. Typology 
12.4.2. Configuration of a Physical Engine 
12.4.3. Physical Motors in the Industry 

12.5. Platforms, Peripherals and Tools Most Commonly Used in Virtual Reality 

12.5.1. Virtual Reality Viewers 
12.5.2. Interaction Peripherals 
12.5.3. Virtual Sensors 

12.6. Augmented Reality Systems 

12.6.1. Insertion of Virtual Elements into Reality 
12.6.2. Types of Visual Markers 
12.6.3. Augmented Reality Technologies 

12.7. Metaverse: Virtual Environments of Intelligent Agents and People 

12.7.1. Avatar Creation 
12.7.2. Intelligent Agents in Virtual Environments 
12.7.3. Construction of Multi-User Environments for VR/AR 

12.8. Creation of Virtual Reality Projects for Robotics 

12.8.1. Phases of Development of a Virtual Reality Project 
12.8.2. Deployment of Virtual Reality Systems 
12.8.3. Virtual Reality Resources 

12.9. Creating Augmented Reality Projects for Robotics 

12.9.1. Phases of Development of an Augmented Reality Project 
12.9.2. Deployment of Augmented Reality Projects 
12.9.3. Augmented Reality Resources 

12.10. Robot Teleoperation with Mobile Devices 

12.10.1. Mixed Reality on Mobile Devices 
12.10.2. Immersive Systems using Mobile Device Sensors 
12.10.3. Examples of Mobile Projects 

Module 13. Robot Communication and Interaction Systems 

13.1. Speech Recognition: Stochastic Systems 

13.1.1. Acoustic Speech Modeling 
13.1.2. Hidden Markov Models 
13.1.3. Linguistic Speech Modeling: N-Grams, BNF Grammars 

13.2. Speech Recognition Deep Learning 

13.2.1. Deep Neural Networks 
13.2.2. Recurrent Neural Networks 
13.2.3. LSTM Cells 

13.3. Speech Recognition: Prosody and Environmental Effects 

13.3.1. Ambient Noise 
13.3.2. Multi-Speaker Recognition 
13.3.3. Speech Pathologies 

13.4. Natural Language Understanding: Heuristic and Probabilistic Systems 

13.4.1. Syntactic-Semantic Analysis: Linguistic Rules 
13.4.2. Comprehension Based on Heuristic Rules 
13.4.3. Probabilistic Systems: Logistic Regression and SVM 
13.4.4. Understanding Based on Neural Networks 

13.5. Dialog Management: Heuristic/Probabilistic Strategies 

13.5.1. Interlocutor's Intention 
13.5.2. Template-Based Dialog 
13.5.3. Stochastic Dialog Management: Bayesian Networks 

13.6. Dialog Management: Advanced Strategies 

13.6.1. Reinforcement-Based Learning Systems 
13.6.2. Neural Network-Based Systems 
13.6.3. From Speech to Intention in a Single Network 

13.7. Response Generation and Speech Synthesis 

13.7.1. Response Generation: From Idea to Coherent Text 
13.7.2. Speech Synthesis by Concatenation 
13.7.3. Stochastic Speech Synthesis 

13.8. Dialogue Adaptation and Contextualization 

13.8.1. Dialogue Initiative 
13.8.2. Adaptation to the Speaker 
13.8.3. Adaptation to the Context of the Dialogue 

13.9. Robots and Social Interactions:Emotion Recognition, Synthesis and Expression

13.9.1. Artificial Voice Paradigms: Robotic Voice and Natural Voice 
13.9.2. Emotion Recognition and Sentiment Analysis 
13.9.3. Emotional Voice Synthesis 

13.10. Robots and Social Interactions: Advanced Multimodal Interfaces 

13.10.1. Combination of Vocal and Tactile Interfaces 
13.10.2. Sign Language Recognition and Translation 
13.10.3. Visual Avatars: Voice to Sign Language Translation  

Module 14. Digital Image Processing 

14.1. Computer Vision Development Environment  

14.1.1. Computer Vision Libraries  
14.1.2. Programming Environment  
14.1.3. Visualization Tools  

14.2. Digital image Processing  

14.2.1. Pixel Relationships  
14.2.2. Image Operations  
14.2.3. Geometric Transformations  

14.3. Pixel Operations  

14.3.1. Histogram  
14.3.2. Histogram Transformations  
14.3.3. Operations on Color Images  

14.4. Logical and Arithmetic Operations  

14.4.1. Addition and Subtraction  
14.4.2. Product and Division  
14.4.3. And/Nand  
14.4.4. Or/Nor  
14.4.5. Xor/Xnor  

14.5. Filters  

14.5.1. Masks and Convolution  
14.5.2. Linear Filtering  
14.5.3. Non-Linear Filtering  
14.5.4. Fourier Analysis  

14.6. Morphological Operations  

14.6.1. Erosion and Dilation  
14.6.2. Closing and Opening  
14.6.3. Top Hat and Black Hat  
14.6.4. Contour Detection  
14.6.5. Skeleton  
14.6.6. Hole Filling  
14.6.7. Convex Hull  

14.7. Image Analysis Tools  

14.7.1. Edge Detection  
14.7.2. Detection of Blobs  
14.7.3. Dimensional Control  
14.7.4. Color Inspection  

14.8. Object Segmentation  

14.8.1. Image Segmentation  
14.8.2. Classical Segmentation Techniques  
14.8.3. Real Applications  

14.9. Image Calibration  

14.9.1. Image Calibration  
14.9.2. Methods of Calibration  
14.9.3. Calibration Process in a 2D Camera/Robot System  

14.10. Image Processing in a Real Environment  

14.10.1. Problem Analysis  
14.10.2. Image Processing  
14.10.3. Feature Extraction  
14.10.4. Final Results

Module 15. Advanced Digital Image Processing 

15.1. Optical Character Recognition (OCR)  

15.1.1. Image Pre-Processing  
15.1.2. Text Detection  
15.1.3. Text Recognition  

15.2. Code Reading  

15.2.1. 1D Codes  
15.2.2. 2D Codes  
15.2.3. Applications  

15.3. Pattern Search  

15.3.1. Pattern Search  
15.3.2. Patterns Based on Gray Level  
15.3.3. Patterns Based on Contours  
15.3.4. Patterns Based on Geometric Shapes  
15.3.5. Other Techniques  

15.4. Object Tracking with Conventional Vision  

15.4.1. Background Extraction  
15.4.2. Meanshift  
15.4.3. Camshift  
15.4.4. Optical Flow  

15.5. Facial Recognition  

15.5.1. Facial Landmark Detection  
15.5.2. Applications  
15.5.3. Facial Recognition  
15.5.4. Emotion Recognition  

15.6. Panoramic and Alignment  

15.6.1. Stitching  
15.6.2. Image Composition  
15.6.3. Photomontage  

15.7. High Dynamic Range (HDR) and Photometric Stereo  

15.7.1. Increasing the Dynamic Range  
15.7.2. Image Compositing for Contour Enhancement  
15.7.3. Techniques for the Use of Dynamic Applications  

15.8. Image Compression  

15.8.1. Image Compression  
15.8.2. Types of Compressors  
15.8.3. Image Compression Techniques  

15.9. Video Processing  

15.9.1. Image Sequences  
15.9.2. Video Formats and Codecs  
15.9.3. Reading a Video 
15.9.4. Frame Processing  

15.10. Real Application of Image Processing  

15.10.1. Problem Analysis  
15.10.2. Image Processing  
15.10.3. Feature Extraction  
15.10.4. Final Results

Module 16. 3D Image Processing 

16.1. 3D Imaging  

16.1.1. 3D Imaging  
16.1.2. 3D Image Processing Software and Visualizations  
16.1.3. Metrology Software  

16.2. Open 3D  

16.2.1. Library for 3D Data Processing  
16.2.2. Features  
16.2.3. Installation and Use  

16.3. The Data  

16.3.1. Depth Maps in 2D Image  
16.3.2. Pointclouds  
16.3.3. Normal  
16.3.4. Surfaces  

16.4. Visualization  

16.4.1. Data Visualization  
16.4.2. Controls  
16.4.3. Web Display  

16.5. Filters  

16.5.1. Distance Between Points, Eliminate Outliers  
16.5.2. High Pass Filter  
16.5.3. Downsampling  

16.6. Geometry and Feature Extraction  

16.6.1. Extraction of a Profile  
16.6.2. Depth Measurement  
16.6.3. Volume  
16.6.4. 3D Geometric Shapes  
16.6.5. Shots  
16.6.6. Projection of a Point  
16.6.7. Geometric Distances  
16.6.8. Kd Tree  
16.6.9. Features 3D  

16.7. Registration and Meshing  

16.7.1. Concatenation  
16.7.2. ICP  
16.7.3. Ransac 3D  

16.8. 3D Object Recognition  

16.8.1. Searching for an Object in the 3D Scene  
16.8.2. Segmentation
16.8.3. Bin Picking  

16.9. Surface Analysis  

16.9.1. Smoothing  
16.9.2. Orientable Surfaces  
16.9.3. Octree  

16.10. Triangulation  

16.10.1. From Mesh to Point Cloud  
16.10.2. Depth Map Triangulation  
16.10.3. Triangulation of unordered PointClouds

Module 17. Convolutional Neural Networks and Image Classification 

17.1. Convolutional Neural Networks  

17.1.1. Introduction  
17.1.2. Convolution 
17.1.3. CNN Building Blocks  

17.2. Types of CNN Layers  

17.2.1. Convolutional  
17.2.2. Activation  
17.2.3. Batch Normalization  
17.2.4. Polling  
17.2.5. Fully Connected  

17.3. Metrics  

17.3.1. Matrix Confusion  
17.3.2. Accuracy  
17.3.3. Precision  
17.3.4. Recall  
17.3.5. F1 Score  
17.3.6. ROC Curve  
17.3.7. AUC  

17.4. Main Architectures  

17.4.1. AlexNet  
17.4.2. VGG  
17.4.3. Resnet  
17.4.4. GoogleLeNet  

17.5. Image Classification  

17.5.1. Introduction  
17.5.2. Analysis of Data  
17.5.3. Data Preparation  
17.5.4. Model Training  
17.5.5. Model Validation  

17.6. Practical Considerations for CNN Training  

17.6.1. Optimizer Selection  
17.6.2. Learning Rate Scheduler  
17.6.3. Check Training Pipeline  
17.6.4. Training with Regularization  

17.7. Best Practices in Deep Learning  

17.7.1. Transfer Learning  
17.7.2. Fine Tuning  
17.7.3. Data Augmentation  

17.8. Statistical Data Evaluation  

17.8.1. Number of datasets  
17.8.2. Number of Labels  
17.8.3. Number of Images  
17.8.4. Data Balancing  

17.9. Deployment  

17.9.1. Saving and Loading Models  
17.9.2. Onnx  
17.9.3. Inference  

17.10. Case Study: Image Classification  

17.10.1. Data Analysis and Preparation  
17.10.2. Testing the Training Pipeline  
17.10.3. Model Training  
17.10.4. Model Validation

Module 18. Object Detection 

18.1. Object Detection and Tracking  

18.1.1. Object Detection  
18.1.2. Case Uses  
18.1.3. Object Tracking  
18.1.4. Case Uses  
18.1.5. Occlusions, Rigid and Non-Rigid Poses  

18.2. Evaluation Metrics  

18.2.1. IOU - Intersection Over Union  
18.2.2. Confidence Score  
18.2.3. Recall  
18.2.4. Precision  
18.2.5. Recall–Precision Curve  
18.2.6. Mean Average Precision (mAP)  

18.3. Traditional Methods  

18.3.1. Sliding Window  
18.3.2. Viola Detector  
18.3.3. HOG  
18.3.4. Non Maximal Supresion (NMS)  

18.4. Datasets  

18.4.1. Pascal VC  
18.4.2. MS Coco  
18.4.3. ImageNet (2014)  
18.4.4. MOTA Challenge  

18.5. Two Shot Object Detector  

18.5.1. R-CNN  
18.5.2. Fast R-CNN  
18.5.3. Faster R-CNN  
18.5.4. Mask R-CNN  

18.6. Single Shot Object Detector   

18.6.1. SSD  
18.6.2. YOLO  
18.6.3. RetinaNet  
18.6.4. CenterNet  
18.6.5. EfficientDet  

18.7. Backbones  

18.7.1. VGG  
18.7.2. ResNet  
18.7.3. Mobilenet  
18.7.4. Shufflenet  
18.7.5. Darknet  

18.8. Object Tracking  

18.8.1. Classical Approaches  
18.8.2. Particulate Filters  
18.8.3. Kalman  
18.8.4. Sorttracker  
18.8.5. Deep Sort  

18.9. Deployment  

18.9.1. Computing Platform  
18.9.2.  Choice of Backbone  
18.9.3. Choice of Framework  
18.9.4. Model Optimization  
18.9.5. Model Versioning  

18.10. Study: detection and tracking of people   

18.10.1. Detection of People  
18.10.2. Monitoring of People  
18.10.3. Re-Identification  
18.10.4. Counting People in Crowds 

Module 19.  Image Segmentation with Deep Learning 

19.1. Object Detection and Segmentation  

19.1.1. Semantic Segmentation  

19.1.1.1. Semantic Segmentation Use Cases  

19.1.2. Instantiated Segmentation  

19.1.2.1. Instantiated Segmentation Use Cases  

19.2. Evaluation Metrics  

19.2.1. Similarities with Other Methods  
19.2.2. Pixel Accuracy  
19.2.3. Dice Coefficient (F1 Score)  

19.3. Cost Functions  

19.3.1. Dice Loss  
19.3.2. Focal Loss  
19.3.3. Tversky Loss  
19.3.4. Other Functions  

19.4. Traditional Segmentation Methods  

19.4.1. Threshold Application with Otsu and Riddlen  
19.4.2. Self-Organized Maps  
19.4.3. GMM-EM Algorithm  

19.5. Semantic Segmentation Applying Deep Learning: FCN  

19.5.1. FCN  
19.5.2. Architecture  
19.5.3. FCN Applications  

19.6. Semantic Segmentation Applying Deep Learning: U-NET  

19.6.1. U-NET  
19.6.2. Architecture  
19.6.3. U-NET Application  

19.7. Semantic Segmentation Applying Deep Learning: Deep Lab  

19.7.1. Deep Lab  
19.7.2. Architecture  
19.7.3. Deep Lab Application  

19.8. Instantiated segmentation applying Deep Learning: Mask RCNN  

19.8.1. Mask RCNN  
19.8.2. Architecture  
19.8.3. Application of a Mask RCNN  

19.9. Video Segmentation  

19.9.1. STFCN  
19.9.2. Semantic Video CNNs  
19.9.3. Clockwork Convnets  
19.9.4. Low-Latency  

19.10. Point Cloud Segmentation  

19.10.1. The Point Cloud  
19.10.2. PointNet  
19.10.3. A-CNN  

Module 20. Advanced image segmentation and advanced computer vision techniques 

20.1. Database for General Segmentation Problems   

20.1.1. Pascal Context  
20.1.2. CelebAMask-HQ  
20.1.3. Cityscapes Dataset  
20.1.4. CCP Dataset  

20.2. Semantic segmentation in medicine  

20.2.1. Semantic segmentation in medicine  
20.2.2. Datasets for medical problems  
20.2.3. Practical Applications  

20.3. Annotation Tools  

20.3.1. Computer Vision Annotation Tool  
20.3.2. LabelMe  
20.3.3. Other Tools  

20.4. Segmentation tools using different Frameworks  

20.4.1. Keras  
20.4.2. Tensorflow v2  
20.4.3. Pytorch  
20.4.4. Others  

20.5. Semantic Segmentation Project. The Data, Phase 1  

20.5.1. Problem Analysis  
20.5.2. Input Source for Data  
20.5.3. Data Analysis  
20.5.4. Data Preparation  

20.6. Semantic Segmentation Project. Training, Phase 2  

20.6.1. Algorithm Selection  
20.6.2. Education  
20.6.3. Assessment  

20.7. Semantic Segmentation Project. Results, Phase 3  

20.7.1. Fine Tuning  
20.7.2. Presentation of The Solution  
20.7.3. Conclusions  

20.8. Autoencoders  

20.8.1. Autoencoders
20.8.2. Architecture of an Autoencoder  
20.8.3. Noise Removal Autoencoders  
20.8.4. Automatic Coloring Autoencoder  

20.9. Generative Adversarial Networks (GANs)  

20.9.1. Generative Adversarial Networks (GANs)  
20.9.2. DCGAN Architecture  
20.9.3. Conditional GAN Architecture  

20.10. Enhanced Generative Adversarial Networks  

20.10.1. Overview of the Problem  
20.10.2. WGAN  
20.10.3. LSGAN  
20.10.4. ACGAN 

Differentiate yourself from the rest of your competitors by acquiring specialized skills in a field with great growth potential"