Intelligent Robotics

Code:

M.EIC041

Acronym:

RI

Keywords
Classification	Keyword
OFICIAL	Artificial Intelligence

Instance: 2024/2025 - 1S

Active?	Yes
Responsible unit:	Department of Informatics Engineering
Course/CS Responsible:	Master in Informatics and Computing Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
M.EIC	37	Syllabus	2	-	6	39	162

Teaching language

English

Objectives

• To understand the basic concepts of Robotics and the context of Artificial Intelligence in Robotics.


• To study methods of perception and sensorial interpretation (emphasizing computer vision), which allow creating precise world estates and mobile robots’ localization methods.


• To study the methods which allow mobile robots to navigate in familiar or unfamiliar environments using Planning and Navigation algorithms.


• To study the fundamentals of human-robot interaction, robot learning, cooperative robotics and robot teams construction.


• To analyze the main national and international robotics competitions, the more realistic robot simulators and the more advanced robotic platforms available in the market.


• Improve the ability to communicate regarding scientific and technical issues.


• Promote healthy scientific approach.

Learning outcomes and competences

At the end of this Curricular Unit, students should be able to:

• Define Autonomy for Robotics
• Define Intelligent Robotic System (IRS)
• Explain relation of Artificial Intelligence (AI) and IRSs
• Identify applications for Intelligent Robotic Systems
• List and use classical Robotic Architectures
• Know the current State of the Art in Robotics
• Know frequently used sensors and actuators and perception interpretation methods for robotics
• Evaluate usage of vision systems compared to other sensors
• Use methodologies from: Data Fusion, AI, data processing and vision processing in order to build perceptions of the world state
• Know and use methods for Localization, Mapping, Planning, and Navigation in robotics
• Know and use one or more robotic systems or simulators
• Know and use interaction, learning and cooperation methodologies for robotics.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Experience in computer language programming is needed.
Frequently used languages include C++ and Python.
Preferably, basic knowledge in Artificial Intelligence.

Program

1. Introduction to Intelligent Robotics:
   Basic Concepts of Robotics, Artificial Intelligence in Robotics; Areas and Applications of Intelligent Robots; Perception-Decision-Action Loop; Architectures for Robotic Agents; Robotic Competitions; Simulation and Robotic Simulators; History, Evolution, and Current Trends in Intelligent Robotics.


2. Robotics Middleware and ROS: 
   Middleware and Robotics Middleware; Robotics Middleware Projects; Introduction to ROS – Robot Operating System; ROS Architecture; ROS Console Commands; Creating ROS Packages; ROS C++ Client Library; ROS Simulation; Visualizations and User Interface Tools; ROS Bags.


3. Perception and Sensorial Interpretation: 
   Types of Sensors for Mobile Robots; Proximity/Contact Sensors; Position/Movement Sensors; Robot Vision (Cameras, Depth Sensors, Digital Image, Color Spaces, Image Processing, Image Analysis; Robot Hearing; Uncertainty Analysis and Representation; Sensor Fusion Techniques.


4. Locomotion and Action: 
   Actuators for Mobile Robots; Locomotion Modes and Mechanisms; Wheeled Mobile Robots; Legged Mobile Robots and Biped Walking; Robot Manipulators and its Control; Mobile Robots Kinematics and Motion Control; Simulation of Robot Locomotion and Action.


5. Localization and Mapping: 
   Creation, Representation and Update of Maps and World States; Metric Maps and Topological Maps; Markov, Gaussian and Grid Localization; Kalman Filters and Extended Kalman Filters (EKF) Localization; Particle Filters and Monte-Carlo Localization; SLAM – Simultaneous Localization and Mapping; Methods for SLAM (EKF-SLAM, FastSLAM and Graph SLAM).


6. Planning and Navigation: 
   Path Planning in Known/Unknown Environments; Cellular Decomposition; Visibility Graphs; Voronoi Diagrams; Search, Dijkstra, A* and D* Algorithms; Potential Field Method; Obstacle Avoidance; Navigation Architectures; World Exploration Methods; High-Level Planning.


7. Human-Robot Interaction (HRI): 
   Basics of Human-Computer Interaction; Perception for HRI; Decision-Making for HRI; Action for HRI; Human-Robot Intelligent Cooperation.


8. Robot Learning: 
   Introduction and Challenges in Robot Learning; Dimensionality Reduction; Supervised Robot Learning; Evolutionary Robot Learning; Reinforcement Learning for Robotics; Optimization and Metaheuristics for Robotics; Self-Supervised, Imitation Learning, Deep Learning for Robotics; Multi-Robot Learning.


9. Cooperative Robotics and Human-Robot Teams: 
   Cooperation between Robots for Teamwork; Joint Intentions, TAEMS, Role-Based, Social Rules; Multi-Robot Formations; Multi-Robot Communication and Mutual Modeling; Locker-Room, Strategical Coordination, Setplays; Swarm Robotics; Human-Robot Teams.


10. Robotics in the Future: 
    Artificial Intelligence and Robotics in the Future; Visions, Science Fiction and Reality; Advanced Projects in Robotics in Portugal, EU, Japan and USA; Asimov Laws and their Future; Robot Ethics, Robot Rights and Robotic Governance; Industrial, Personal, Ubiquos and Cloud Robots; Robotics Future Trends and Applications; The Singularity?

Mandatory literature

Howie Choset, Kevin M. Lynch, Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia E. Kavraki, Sebastian Thrun ; Principles of Robot Motion : Theory, Algorithms, and Implementations , Bradford Book, MIT Press, Cambridge, Massachussets, London England, 2005. ISBN: 0-262-03327-5
Robin R. Murphy; An Introduction to AI Robotics , Bradford Book, MIT Press, Cambridge, Massachussets, London England, 2000. ISBN: 0-262-13383-0
Russell, Stuart; Artificial intelligence. ISBN: 0-13-360124-2

Complementary Bibliography

Sebastian Thrun, Wolfram Burgard, Dieter Fox ; Probabilistic Robotics, MIT Press, Cambridge, Massachussets, London England, 2005. ISBN: 0-262-20162-3
Siciliano, Bruno; Khatib, Oussama (Eds.); Springer Handbook of Robotics, Springer, 2008. ISBN: 978-3-540-38219-5
Jason M. O'Kane; A Gentle Introduction do ROS, Independently published, 2013. ISBN: 978-14-92143-23-9 (Free - https://www.cse.sc.edu/~jokane/agitr/)

Teaching methods and learning activities

• Exposition with interaction in classes


• Examples are taken from projects coordinated/developed by the lecturers. 


• Use of simulators for mobile robots navigation and humanoid robots


• Assignments on cooperative robotics


• Exploration of mobile robotic platforms


• Challenge students to higher level learning


• The evaluation includes the ability to search for information, do scientific work, do technical work and disseminate the work done. Higher order thinking skills are encouraged


• Detailed feedback is given to students about the quality of their research work and learning process

Software

Simuladores Soccer-Server (2D e 3D)
Linguagem de Programação: C++
Simulador Ciber-Rato
Simulador RoboCup Rescue
ROS

keywords

Technological sciences > Engineering > Control engineering > Robótica Robotics
Technological sciences > Engineering > Simulation engineering
Technological sciences > Engineering > Computer engineering
Technological sciences > Engineering > Knowledge engineering
Technological sciences > Technology > Knowledge technology > Agent technology

Evaluation Type

Distributed evaluation without final exam

Assessment Components

Designation	Weight (%)
Trabalho escrito	30,00
Trabalho laboratorial	70,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Elaboração de projeto	40,00
Estudo autónomo	30,00
Frequência das aulas	42,00
Trabalho de investigação	20,00
Trabalho laboratorial	30,00
Total:	162,00

Eligibility for exams

• Presence in more than 75% of the classes


• Delivery of all Assignments

Calculation formula of final grade

• 10% Distributed Assessment - HomeWorks, kahoots and in-class work


• 20% Assignment 1 - Reactive Robot and article


• 20% Assignment 2 - Quiz


• 10% Assignment 3 - Evaluation of the quality of the proposal (contract) of the final course project


• 40% Assignment 4 - Evaluation of the final course project




• Includes: Code; Functionalities; Demonstration; "Conference" article; video; presentation + Q&A

Obs 1: In very special (justified) cases, in-class assignments concentrated in time can be substituted by equivalent work

Obs 2: The "Final Course Project" encompasses Assignments 3 and 4

Examinations or Special Assignments

See Final Course Project notes

Internship work/project

Examples of Final Course Projects include DuckieTown robot, Ciber Mouse simulation agent (such as collaborative or mapping), autonomous driving, robotic soccer, humanoid robots or other scientific research project agreed (in written contract) by students and teacher.
Optionally, the work can be done with real robots

Special assessment (TE, DA, ...)

• Attendance not required


• 20% Assignment 1


• 20% Assignment 2


• 60% Assignment 4

Classification improvement

• Individual improvement of the previously work that must have been previously presented in the final course presentation.


• The grade of the "Distributed Assessment" can not be improved

Observations

Attention: Classes and materials are in English language