Artificial Intelligence in Robotics
BASIC DATA
course listing
A - main register
course code
ITI8800
course title in Estonian
Tehisintellekt robootikas
course title in English
Artificial Intelligence in Robotics
course volume CP
-
ECTS credits
6.00
to be declared
yes
fully online course
not
assessment form
Examination
teaching semester
autumn
language of instruction
Estonian
English
Study programmes that contain the course
code of the study programme version
course compulsory
IAIM26/26
yes
Structural units teaching the course
IT - Department of Software Science
Course description link
Timetable link
View the timetable
Version:
VERSION SPECIFIC DATA
course aims in Estonian
Aine eesmärk on:
- tekitada seoseid abstraktse tehisintellekti teooria ja selle praktilise rakenduse vahel robotsüsteemides, mis peavad tajuma, arutlema ja tegutsema määramatuse tingimustes;
- kujundada terviklikku, süsteemset vaadet, juhendades üliõpilasi lõimima erinevaid informaatika valdkondi (nt taju, planeerimine, juhtimine ja masinõpe) üheks terviklikuks süsteemiks;
- varustada üliõpilasi praktiliste oskustega robootikatarkvara projekteerimiseks, rakendamiseks ja valideerimiseks;
- arendada kriitilist mõtlemist kaasaegsete autonoomsete süsteemide võimekuste ja piirangute suhtes ning tutvustada olulisi eetilisi raamistikke ja ühiskondlikke kontekste, mis nende rakendamist suunavad;
- valmistada üliõpilasi ette edasijõudnutele mõeldud teadus- ja arendustöö rollideks või edasisteks õpinguteks, pakkudes nii sügavat teoreetilist alust kui ka projektipõhist õpikogemust.
course aims in English
The principal aim of this course is to:
- bridge the gap between abstract artificial intelligence theory and its practical, embodied application in physical robotic systems that must perceive, reason, and act under uncertainty;
- foster a holistic, system-level perspective by guiding students to integrate disparate computer science domains (e.g., perception, planning, control, and machine learning) into a single, complex intelligent system;
- equip students with a portfolio of practical skills for designing, implementing, and validating robotic software using industry-standard tools like the Robot Operating System (ROS 2), and high-fidelity simulators;
- cultivate critical thinking on the capabilities and limitations of modern autonomous systems, while introducing the crucial ethical frameworks and societal contexts that govern their deployment;
- prepare students for advanced roles in research and development or further studies by providing both a deep theoretical foundation and challenging, project-based learning experiences.
learning outcomes in the course in Est.
Õppeaine läbinud üliõpilane:
- lahendab keerukaid autonoomsete robotite ülesandeid (nt lokaliseerimine, kaardistamine, planeerimine), rakendades sobivaid tõenäosuslikke, mudelipõhiseid või masinõppe meetodeid;
- analüüsib kriitiliselt erinevate tehisintellekti algoritmide (nt Kalmani filtrid vs. osakeste filtrid; A* vs. RRT) kompromisse, et valida konkreetse robootikaülesande jaoks sobiv meetod;
- kombineerib erinevaid komponente (nt taju, SLAM, planeerimine) terviklikuks süsteemiks, kasutades standardset vahevara (ROS 2), ning valideerib selle jõudlust simulatsioonis;
- hindab intelligentsete robootikasüsteemide rakendamist ühiskondliku mõju, kehtivate eetiliste raamistikute ja tekkivate regulatsioonide kontekstis;
- põhjendab algoritmilisi ja süsteemidisaini valikuid, koostades tehnilise aruande ja luues hästi dokumenteeritud lähtekoodi;
- selgitab keeruka, integreeritud süsteemi toimimist kaaslastele ja juhendajatele selge tehnilise ettekandega.
learning outcomes in the course in Eng.
After completing the course, the student:
- solves complex robotic autonomy problems (e.g., localization, mapping, planning) by applying appropriate probabilistic, model-based, or machine learning methods;
- analyzes critically the trade-offs of different AI algorithms (e.g., Kalman Filters vs. Particle Filters; A* vs. RRTs) to select the appropriate method for a specific robotics problem;
- combines multiple functional components (e.g., perception, SLAM, planning) into a complete system using standard middleware (ROS 2) and validates its performance in simulation;
- evaluates the deployment of intelligent robotic systems in the context of societal impact, established ethical frameworks, and emerging regulations;
- argues for algorithmic and system design choices by composing a formal technical report and creating well-documented code;
- explains the functionality of a complex, integrated system to peers and instructors via a clear technical demonstration presentation.
brief description of the course in Estonian
Aine pakub põhjalikku ülevaadet tehisintellekti põhitehnikatest, mis võimaldavad kaasaegsetel robootikasüsteemidel tajuda, mõelda ja tegutseda intelligentselt. Õppeaine seob abstraktsed AI algoritmid nende füüsiliste rakendustega, keskendudes autonoomsete süsteemide peamistele valdkondadele: tõenäosuslik olekuhindamine, taju, planeerimine, juhtimine ja masinõpe. Üliõpilased omandavad nii teoreetilise arusaamise kui ka praktilised oskused autonoomsete süsteemide integreerimiseks. Lisaks käsitletakse kursuses olulisi eetilisi raamistikuid, mis reguleerivad intelligentsete robotite kasutuselevõttu ühiskonnas (nt EL-i tehisintellekti määrus).
brief description of the course in English
The course provides a comprehensive exploration of the essential artificial intelligence techniques that enable modern robotic systems to perceive, reason, and act intelligently. It bridges the gap between abstract AI algorithms and their embodied application, focusing on the core pillars of autonomous systems: probabilistic state estimation, perception, planning, control, and machine learning. Students will gain both theoretical understanding and the practical skills to integrate autonomous systems. The course also examines the critical ethical frameworks governing the deployment of intelligent robots in society (e.g., EU AI Act).
type of assessment in Estonian
Ülesanded, vaheeksam, projekt
type of assessment in English
Lab assignments, midterm exam, capstone project
independent study in Estonian
-
independent study in English
-
study literature
Thrun, S., Burgard, W. & Fox, D. (2005). Probabilistic Robotics. MIT Press.
Lynch, K. & Park, F. (2017). Modern Robotics: Mechanics, Planning, and Control. Cambridge University Press.
study forms and load
daytime study: weekly hours
4.0
session-based study work load (in a semester):
lectures
0.0
lectures
-
practices
4.0
practices
-
exercises
0.0
exercises
-
lecturer in charge
Gert Kanter, vanemlektor (IT - tarkvarateaduse instituut)
LECTURER SYLLABUS INFO
semester of studies
teaching lecturer / unit
language of instruction
Extended syllabus
Course-teacher pairs of the corresponding version are missing!
Course description in Estonian
Course description in English