Program

Instructors
Pedro Ridao Full Professor, UdG

Learning content and process
Learning aim
The subject introduces various industrial manipulators, as well as the most common actuators and sensors. Direct, inverse, and differential kinematics will be addressed for the most common industrial manipulators, as well as dynamics, trajectory planning, and tracking. The subject not only delves into theory but also covers the programming of these manipulators for industrial tasks.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO10. Apply key control and trajectory planning techniques for manipulators and autonomous vehicles.
Course content
1. Introduction to industrial manipulators
2. Coordinate systems
3. Forward Kinematics
4. Inverse Kinematics
5. Differential Kinematics
6. Dynamics
7. Trajectory Control and generation
8. Industrial Manipulators Programming
Assessment
Exercise resolution 10%
Labs 50%
Written tests 40%
TOTAL 100%
Main course reading
Corke, Peter I (2011). Robotics, vision and control : fundamental algorithms in Matlab . New York: Springer.
Siciliano, Bruno & Sciavicco, Lorenzo & Luigi, Villani & Oriolo, Giuseppe. (2011). Robotics: Modelling, Planning and Control.. Springer.

Instructors
Pedro Ridao Full Professor, UdG

Learning content and process
Learning aim
Probabilistic techniques for robot localization and the construction of maps of its environment. Bayesian estimation.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO5. Apply state-of-the-art algorithms for autonomous vehicle localization and navigation to specific field robotic applications.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
Course content
1. Introduction
2. Bayes Filter
3. Non Parametric Filters
4. Parametric Filters
5. EKF Map-based Localization
6. EKF Feature-based SLAM
Assessment
Examination 50%
Labs 40%
Problem Solving 10%
TOTAL 100%
Main course reading
Sebastian Thrun, Wolfram Burgard, Dieter Fox (2005). Probabilistic robotics. Massachusetts ; London: The MIT Press.
Yaakov Bar-Shalom and Xiao-Rong Li (1993). Estimation and Tracking: Principle Techniques, and software. Boston - London: Artech House.

Instructors
Marc Carreras Perez Associate Professors, UdG
Narcís Palomeras Associate Professors, UdG

Learning content and process
Learning aim
Algorithms to enable a robot to act autonomously: control architectures, behavior-based robotics, motion planning, robotics learning, and robotic exploration.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO5. Apply state-of-the-art algorithms for autonomous vehicle localization and navigation to specific field robotic applications.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO10. Apply key control and trajectory planning techniques for manipulators and autonomous vehicles.
Course content
1. Control architectures
2. Behaviour-based robotics.
3. Motion planning.
4. Robot learning.
Assessment
Examination 50%
Labs 50%
TOTAL 100%
Main course reading
Arkin, Ronald C.. (1998). Behavior-based robotics. London: MIT Press.
Choset, Howie M.. (2004). Principles of robot motion :. Cambridge, Massachusetts [etc.]: MIT Press.
Sutton, Richard S.. (2018). Reinforcement learning : (Second edition). Cambridge, Mass.: MIT Press.

Instructors
Nuno Ricardo Estrela Gracias Associate Professors, UdG
Rafael Garcia Campos Full professor, UdG

Learning content and process
Learning aim
Basic concepts of computer vision. Image formation and camera modeling. Camera calibration. Feature detectors and descriptors. Robust estimation in computer vision. Multi-view geometry. Structure from motion and optimization systems. Real-time computer vision and vision applied to robotic systems. Unconventional optical imaging systems.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO7. Evaluate fundamental computer-based perception techniques commonly used in intelligent robotics applications.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
Course content
1. Introduction 1.1. Course organization: Objectives, Overview, Contents, Bibliography, Evaluation, Practical Sessions
2. Basic concepts of Projective Geometry in Computer Vision; 2.1. Linear Algebra; 2.2. Points and vectors; 2.3. Translations and Rotations; 2.4. Homogeneous Coordinates; 2.5. Inverses and Transposes
3. Image formation and Camera Modelling; 3.1. Optical Sensors; 3.2. The pinhole model; 3.3. Intrinsic and extrinsic parameters; 3.4. Computing the calibration matrix; 3.5. Effect of camera lenses.
4. Image Primitives; 4.1. Interest point detectors; 4.2. Harris and Hessian detectors; 4.3. Similarity measures: SAD, SSD, Correlation; 4.4. Introduction to Scale invariant features
5. Feature detectors and descriptors; 5.1. Feature detectors; 5.2. Invariance; 5.3. Descriptors; 5.4. Review of SIFT
6. Robust Estimation in Computer Vision; 6.1. Probabilistic methods; 6.2. Computing the homography matrix; 6.3. Outlier rejection: Random Sampling Consensus; 6.4. Applications: Planar motion estimation, Mosaicing, etc.
7. Multiple view geometry; 7.1. The principle of Triangulation; 7.2. Stereo vision; 7.3. Epipolar geometry; 7.4. Computing the Fundamental matrix; 7.5. Trinocular constraints and n-camera constraints
8. Structure-from-Motion; 8.1. Review of SfM approaches; 8.2. Main components of 3D model creation pipeline
9. Real-time Computer Vision and Vision applied to Robotic systems; 9.1. Visual odometry; 9.2. Incremental approaches and visual SLAM; 9.3. Review and examples of applied to field Robotics
10. Non-conventional optical imaging systems; 10.1. Omnidirectional vision systems; 10.2. Multispectral and hyperspectral; 10.3. Event-based cameras, range gating and others.
Assessment
Examination 50%
Practical Sessions 50%
TOTAL 100%
Main course reading
Hartley, Richard (2003). Multiple view geometry in computer vision (2nd ed.). Cambridge [etc.]: Cambridge University Press.
Ma, Yi (2004). An Invitation to 3-D vision : from images to geometric models. New York [etc.]: Springer, cop.

Instructors
Nuno Ricardo Estrela Gracias Associate Professors, UdG
Rafael Garcia Campos Full professor, UdG

Learning content and process
Learning aim
Apply techniques of modelling and calibrating computer vision systems. Compute 3D information of the real world from 2D image projections Apply the principles of triangulation, stereovision, and multicamera geometry Understand the limitations of some feature detecting and feature matching algorithms and how to remove false data associations Basic working knowledge of Structure-from Motion and Visual Odometry Building creative proposals
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO3. Employ machine learning methods effectively in various contexts related to field robotics.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
Course content
1. Introduction
2. Linear prediction: Regression
3. Logistic Regression
4. Support Vector Machines
5. Decision Trees
6. Unsupervised learning: K-means Clustering
7. Unsupervised learning: PCA
8. Neural Networks
9. Convolutional Neural Networks
Assessment
Examination 50%
Lab assignments 50%
TOTAL 100%
Main course reading
Christopher M. Bishop (2006). Pattern Recognition and Machine Learning. Springer.

Instructors
Patryk Andrzej Cieslak Associate Professors, UdG

Learning content and process
Learning aim
The goal of autonomous mobile manipulation is the execution of complex manipulation tasks in potentially unstructured and dynamic environments. The course addresses the control theory challenges present in mobile manipulation systems. Specifically, it focuses on the multi-task control of large-scale redundant systems. This is a practical course centered around learning new algorithms through labs and a project.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO9. Conduct practical projects in the field of intelligent robotics.
LO10. Apply key control and trajectory planning techniques for manipulators and autonomous vehicles.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Differential kinematics of mobile manipulators
2. Resolved-rate motion control
3. Task-Priority kinematic control
4. Hands-on project
Assessment
Examination 20%
Hands-on Project + Oral Presentation 50%
Lab assignments 30%
TOTAL 100%
Main course reading
Peter Corke (2011). Robot Vision and control. Springer.
Ginaluca Antonelli (2018). Underwater Robots. Springer.
Siciliano, Bruno & Sciavicco, Lorenzo & Luigi, Villani & Oriolo, Giuseppe. (2012). Robotics: Modelling, Planning and Control.. Springer.

Instructors
Pere Ridao Rodriguez Full Professor, UdG
Roger Pi PhD, UdG

Learning content and process
Learning aim
The student will have a deep knowledge of SLAM (Simultaneous Localization and Mapping) algorithms based on particle filters and Kalman filters applied to field robots. The student will know how to localize a mobile robot or map its environment using noisy sensors. The student will understand the principles of simultaneously localizing a robot while mapping its environment. The student will be capable of developing applications using the major libraries and middlewares used in robotics and machine learning.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO5. Apply state-of-the-art algorithms for autonomous vehicle localization and navigation to specific field robotic applications.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO9. Conduct practical projects in the field of intelligent robotics.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Particle filter based SLAM
2. Reviewing and discussing the most relevant articles in the field
3. Extended Kalman filter based SLAM
4. Reviewing and discussing the most relevant articles in the field
5. Hands-on project
Assessment
Report and Document Writing 60%
Projects' Oral Presentation 20%
Exercise Resolution 20%
TOTAL 100%
Main course reading
Sebastian Thrun, Wolfram Burgard, Dieter Fox (2005). Probabilistic robotics. Massachusetts ; London: The MIT Press.
Yaakov Bar-Shalom and Xiao-Rong Li (1993). Estimation and Tracking: Principle Techniques, and software. Boston - London: Artech House.

Instructors
Nuno Gracias Associate Professors, UdG
Josep Forest Associate Professors, UdG

Learning content and process
Learning aim
The student will be familiar with the principles of image formation and can use the most common camera calibration methods. The student will understand the geometry of multiple camera views and can estimate three-dimensional structures from sequences of two-dimensional images. The student will have a broad knowledge of the major sensors and/or actuators found in robotics and autonomous vehicles. The student will be capable of developing applications using the major libraries and middlewares used in robotics and machine learning.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO3. Employ machine learning methods effectively in various contexts related to field robotics.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO7. Evaluate fundamental computer-based perception techniques commonly used in intelligent robotics applications.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO9. Conduct practical projects in the field of intelligent robotics.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Multi Camera Calibration and metrology
2. Map based Pose Estimation
3. 2D optical mapping
4. Hands-on project
Assessment
Report and Document Writing 60%
Projects' Oral Presentation 20%
Exercise Resolution 20%
TOTAL 100%
Main course reading
Hartley, Richard (2003). Multiple view geometry in computer vision (2nd ed.). Cambridge [etc.]: Cambridge University Press.
Christopher M. Bishop (2006). Pattern Recognition and Machine Learning. Springer.

Instructors
Narcís Palomeras Associate Professor, UdG

Learning content and process
Learning aim
The motion planning algorithms studied in Autonomous Systems will be extended to take into account differential constraints, moving obstacles, a priori unknown environments, ... The most important automatic exploration and inspection methods will be studied. Common manual and automatic task planning mechanisms will be introduced. Students will have to carry out a small group project, using one of the robots available in the laboratory, focused on some of the topics covered during the course.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO5. Apply state-of-the-art algorithms for autonomous vehicle localization and navigation to specific field robotic applications.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO9. Conduct practical projects in the field of intelligent robotics.
LO10. Apply key control and trajectory planning techniques for manipulators and autonomous vehicles.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Common extensions for motion planning algorithms
2. Motion planning with differential constraints
3. View planning, inspection, and automatic exploration
4. Formal and Automatic task planning methods
5. Hands-on project
Assessment
Test 20%
Seminars 5%
Laboratories 15%
Hands-on Project 35%
Oral Presentation 10%
Project Report 15%
TOTAL 100%
Main course reading
Howie Choset, Kevin M. Lynch, Seth Hutchinson, George A. Kantor, Wolfram Burgard, Lydia E. Kavraki and Sebastian Thrun (2005). Principles of Robot Motion Theory, Algorithms, and Implementations. The MIT Press.
Thrun, Sebastian; Burgard, Wolfram; Fox, Dieter (2005). Probabilistic robotics. Cambridge, Massachusetts ; London : The MIT Press.
Peter Corke (2011). Robot Vision and Control. Springer.

Instructors
Xavier Muñoz External Associate Professors, UdG

Learning content and process
Learning aim
The student will get a broad knowledge of how to communicate, motivate, and inspire, as well as how to build and lead teams. The student will understand what a business plan is and is capable of implementing one. The student will reach a basic understanding of the ethical issues related to the development of new technologies, such as robotics, artificial intelligence, and autonomous systems, as well as their social and legal consequences.
Course learning outcomes
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO4. Demonstrate knowledge of professional ethics and ethical principles pertaining to new technologies, applying them to real-world situations.
LO9. Conduct practical projects in the field of intelligent robotics.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Management, communication & leadership
2. From the idea to the market
3. Business plan
4. Case studies
5. Teamwork project
Assessment
Report and Document Writing 30%
Projects' Oral Presentation 50%
Exercise Resolution 20%
TOTAL 100%
Main course reading
"Roberto Verganti (2017). Overcrowded Designing Meaningful Products in a World Awash with Ideas. MIT press.
"Melissa A. Schilling, Ravi Shankar (2019). Strategic Management of Technological Innovation, Sixth Edition. Mc Graw Hill.

Instructors
Paul Andrew Doncaster Associate Professors, UdG
Narcis Palomeras Rovira Associate Professors, UdG

Learning content and process
Learning aim
Principles of Effective Scientific Writing, Scientific Publication Process, and Research Publication Ethics.
Course learning outcomes
LO4. Demonstrate knowledge of professional ethics and ethical principles pertaining to new technologies, applying them to real-world situations.
LO9. Conduct practical projects in the field of intelligent robotics.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Introduction to Scientific Writing and Resaerch Best Practices
2. Principles of effective writing
3. Peer reviewing and science dissemination
4. Issues in scientific writing
5. Principles of Research Ethics
6. Organization and formatting
7. The Publication process
Assessment
Test 20%
Practical Sessions 30%
Paper Writing Project 35%
Oral Presentation 15%
TOTAL 100%
Main course reading
M. Roig (2015). Avoiding Plagiarism, Self-plagiarism, and Other Questionable Writing Practices: A Guide to Ethical Writing, US Office of Research Integrity, 2015 (available online) . US Office of Research Integrity.
Stephen B. Heard (2016). The Scientist's Guide to Writing: How to Write More Easily and Effectively throughout Your Scientific Career. Princeton University Press.

The IFROS Master's program offers students the opportunity to enrich their studies by completing internships. While internships are not mandatory, we strongly encourage students to gain valuable hands-on experience in their field of interest, and to network with professionals in the industry. 

Internships can be completed at any of the universities in the consortium or at our partner companies. However, if a student finds an interesting company, they can also search for it on their own.

Instructors
Kristian Fenech PhD Assistant Professor, ELTE

Learning content and process
Learning aim
In this course practical problems are addressed with deep learning techniques. Architectures: auto-encoders, convolutional neural networks, recurrent neural networks, long short-term memory, residual networks, and highway networks. Image processing: image restoration and super-resolution, bounding boxes, objects, face, hand, body recognition. Speech processing: speaker identification, speaker de-identification, speech recognition and speech production. Motion and control: deep learning for motion via imitation, dynamic movement primitives. Deep methods for anomaly detection, optical flow, tracking, multi-modal tracking, information fusion and pattern completion.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO3. Employ machine learning methods effectively in various contexts related to field robotics.
LO7. Evaluate fundamental computer-based perception techniques commonly used in intelligent robotics applications.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
Course content
1. Non-parametric models
2. Kernel methods
3. Classifier evaluation
4. Dimensionality reduction
5. Neural networks
6. Semi-supervised learning
7. Inductive logic programming
8. Ensambles
9. Clustering
10. Deep learning
11. Reinforcement learning
Assessment
Individual assessment of attitude and ability in the laboratory or activity. 20%
Writen test 65%
Exersice Resolution 15%
TOTAL 100%
Main course reading
Grokking Deep Learning by Andrew W. Trask
Neural Networks and Deep Learning by Michael Nielsen

Instructors
Istenes Zoltán Associate Professor, ELTE

Learning content and process
Learning aim
Principles of autonomous vehicles, and self-driving cars. Hardware and software architectures. Sensors, interconnect networks, actuators, processing elements. Radars, LIDAR’s, cameras, ultrasonic, GPS, and other sensors. CAN, LIN, MOST, FlexRay vehicle interconnect networks and architectures. Intelligent transportation systems.
Course learning outcomes
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO12. Recognize capabilities and limitations of interconnected networks of sensors used in autonomous systems.
Course content
1. Principles of autonomous vehicles, and self-driving cars
2. Hardware and software architectures
3. Sensors, interconnect networks, actuators, processing elements
4. Radars, LIDAR’s, cameras, ultrasonic, GPS, and other sensors
5. CAN, LIN, MOST, FlexRay vehicle interconnect networks and architectures
6. Intelligent transportation systems
Assessment
Individual assessment of attitude and ability in the laboratory or activity. 30%
Writen test 15%
Reviews and documents writing 30%
Oral Presentations 20%
Exercices resolution 5%
TOTAL 100%
Main course reading
Ingemar J. Cox, Gordon T. Wilfong: Autonomous Robot Vehicles. • Springer Science & Business Media, 2012. ISBN 1461389976, 9781461389972
Dimitrakopoulos, G., & Demestichas, P. (2010). Intelligent transportation systems. IEEE Vehicular Technology Magazine, 5(1), 77-84.
Luettel, Thorsten, Michael Himmelsbach, and Hans-Joachim Wuensche. "Autonomous ground vehicles—Concepts and a path to the future." Proceedings of the IEEE 100.Special Centennial Issue (2012): 1831-1839.
Janai, Joel, et al. "Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art." arXiv preprint arXiv:1704.05519 (2017).
Fossen, Thor I., Kristin Y. Pettersen, and Henk Nijmeijer, eds. Sensing and Control for Autonomous Vehicles: Applications to Land, Water and Air Vehicles. Vol. 474. Springer, 2017.

Instructors
Eichhardt Iván Assistant Professor, ELTE

Learning content and process
Learning aim
Operation principles of 3D sensors. Active and passive 3D sensing for autonomous vehicles. Cameras, video cameras, depth cameras, LiDAR sensors, radars, sonars. Comparison of sensors, application areas, advantages and limitations. Sensor fusion on data and feature level and in state space. Camera LiDAR and camera-depth camera fusion. Sensor fusion and semantic segmentation.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO5. Apply state-of-the-art algorithms for autonomous vehicle localization and navigation to specific field robotic applications.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO7. Evaluate fundamental computer-based perception techniques commonly used in intelligent robotics applications.
LO12. Recognize capabilities and limitations of interconnected networks of sensors used in autonomous systems.
Course content
1. Operation principles of 3D sensors.
2. Active and passive 3D sensing for autonomous vehicles.
3. Cameras, depth cameras, LiDAR sensors, radars.
4. Comparison of sensors, application areas, advantages and limitations.
5. Sensor fusion on data and feature level and in state space.
6. Camera-LiDAR and camera-depth camera fusion.
Assessment
Individual assessment of attitude and ability in the laboratory or activity. 30%
Writen test 15%
Reviews and documents writing 30%
Oral Presentations 20%
Exercices resolution 5%
TOTAL 100%
Main course reading
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020). Computer vision for autonomous vehicles: Problems, datasets and state of the art. Foundations and Trends® in Computer Graphics and Vision, 12(1–3), 1-308.
Eichhardt, I., Chetverikov, D., & Janko, Z. (2017). Image-guided ToF depth upsampling: a survey. Machine Vision and Applications, 28(3), 267-282.
Grzegorzek, M., Theobalt, C., Koch, R., & Kolb, A. (Eds.). (2013). Time-of-Flight and Depth Imaging. Sensors, Algorithms and Applications: Dagstuhl Seminar 2012 and GCPR Workshop on Imaging New Modalities (Vol. 8200). Springer. ISBN: 978-3-642-44963-5 (Print), 978-3-642-44964-2 (Online).
H. Fourati, Ed. Multisensor Data Fusion: From Algorithms and Architectural Design to Applications, CRC Press, 2015, ISBN: 9781482263749.
Richard Hartley, Andrew Zisserman. Multiple View Geometry 2nd edition, Cambridge University Press, 2004. ISBN: 05215405182

Instructors
Istenes Zoltán Associate Professor, ELTE

Learning content and process
Learning aim
Students understand the specific aspects of intelligent field robots design and development.
Possess and understand the knowledge that provides a basis or opportunity to be original in the development and / or application of ideas, often in a research context.
Students are able to understand the specific aspect of intelligent field robots design and development.
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO3. Employ machine learning methods effectively in various contexts related to field robotics.
LO5. Apply state-of-the-art algorithms for autonomous vehicle localization and navigation to specific field robotic applications.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO7. Evaluate fundamental computer-based perception techniques commonly used in intelligent robotics applications.
LO9. Conduct practical projects in the field of intelligent robotics.
LO11. Apply principles of multimodal interaction.
Course content
During the lab, students will work in teams on intelligent field robot tasks. These tasks will be real life problems gathered from industrial as well as academic partners of the Faculty. The tasks will concern both basic and applied research and development under the supervision of experienced scientists.
Assessment
Report and ocuments writing 85
Oral Presentation 15
TOTAL 100
Main course reading
David Cook: Robot Building for Beginners, Third Edition, Apress Berkeley, CA, ISBN 978-1-4842-1360-5, 978-1-4842-1359-9
Bruno Siciliano, Oussama Khatib: Springer Handbook of Robotics, Springer-Verlag Berlin Heidelberg 2008, ISBN: 978-3-540-38219-5, 978-3-540-30301-5, DOI: https://doi.org/10.1007/978-3-540-30301-5

Instructors
Csató Lehel External Associate Professor, ELTE

Learning content and process
Learning aim
"They have comprehensive and up-to-date knowledge of general mathematical and computing principles
Possess the knowledge of specific tools and methods of Artificial Intelligence."
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO9. Conduct practical projects in the field of intelligent robotics.
Course content
1. Mathematical data models in artificial intelligence
2. Linear algebra, generalized linear models, mathematical representations; elements of probability theory, the normal distribution and the Mahalanobis distance
3. Likelihood estimations: from the maximum likelihood to MAP to Bayesian estimations. Their use in model optimization.
4. Likelihood approximations: from gradient to conjugate models
5. Unsupervised methods, the expectation maximization and clustering
6. Ensemble methods
7. Autoencoder models
Assessment
Individual assessment of attitude and ability in the laboratory or activity. 30%
Writen test 15%
Reviews and documents writing 30%
Oral Presentations 20%
Exercices resolution 5%
TOTAL 100%
Main course reading
"Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong: Mathematics for Machine Learning, Cambridge University Press, 2020 https://mml-book.github.io/"
"Zhang A, Lipton Z.C, Li M, Smola A.J: Dive into Deep Learning, arXiv preprint arXiv:2106.11342, 2021 https://d2l.ai/d2l-en.pdf"
"C.M. Bishop: Pattern Recognition and Neural Networks, Springer Verlag, 2006 https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf"

Instructors
Takács Rita Associate Professors, ELTE

Learning content and process
Learning aim
"During this course, students from abroad are introduced into the Hungarian education system, and the teaching/learning habits at Eötvös Loránd University, Faculty of Informatics.
In the frame of this course, we develop the communication and learning skills of the English-speaking students, which will critically contribute to their success at the university.
In addition, we help them in their social integration via international trainings. Since the efficient learning is greatly connected to the positive attitudes to the university courses, the course will help them to orient themselves better in the Hungarian education system. Students will obtain capabilities on how to learn successfully and efficiently and how to organize their time better between private life and studies. In addition, the course will focus on communities in the group and it will highlight to them the importance and advantages of working in groups instead of studying alone.
To accomplish this aim we will do practical trainings and outdoor programs to facilitate the social relationships among the students."
Course learning outcomes
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Time management
2. Stress management
3. Capatity Building
4. Soft and entrepreneurial skills
5. Learning methodology
6. Proactive Mindset
Assessment
Practice 100%
TOTAL 100%
Main course reading
John B. Bigg and Catherine Tang (2011): Teaching for Quality Learning at University: What the Student Does. Society of Research in Higher Education and Open University Press, Berkshire, England
Bowden J., F Marton, F. (1998) - The university of learning: Beyond quality and competence. Taylor and Francis Group
Hellsten, Meeri; Prescott, Anne (2004): Learning at University: The International Student Experience. International Education Journal, v5 n3 p344-351, 2004.

Learning content and process
Learning aim
Master's thesis on intelligent field robotic systems
Course learning outcomes
LO1. Program proficiently in the languages and libraries commonly utilised in the field of intelligent robotics.
LO2. Analyse problems associated with intelligent autonomous systems identifying the appropriate techniques and tools for effective problem-solving.
LO3. Employ machine learning methods effectively in various contexts related to field robotics.
LO4. Demonstrate knowledge of professional ethics and ethical principles pertaining to new technologies, applying them to real-world situations.
LO5. Apply state-of-the-art algorithms for autonomous vehicle localization and navigation to specific field robotic applications.
LO6. Recognize which are the primary sensors and actuators used in intelligent robotics, and when they are used.
LO7. Evaluate fundamental computer-based perception techniques commonly used in intelligent robotics applications.
LO8. Acquire deep knowledge of the mathematical foundations of algorithms used in intelligent robotic systems.
LO9. Conduct practical projects in the field of intelligent robotics.
LO10. Apply key control and trajectory planning techniques for manipulators and autonomous vehicles.
LO11. Apply principles of multimodal interaction.
LO12. Recognize capabilities and limitations of interconnected networks of sensors used in autonomous systems.
LO13. Evaluate various forms of inequality, including but not limited to sex, gender, race, religion, and their impact on individuals, societies, and institutions.
Course content
1. Analysis and case studies
2. Thesis writing
3. Bibliography study and reading
4. Seminars
Assessment
Reports and documentation writing 70%
Oral thesis presentation 30%
TOTAL 100%