Logo ČVUT
ČESKÉ VYSOKÉ UČENÍ TECHNICKÉ V PRAZE
STUDIJNÍ PLÁNY
2022/2023

Artificial Intelligence in Robotics

Přihlášení do KOSu pro zápis předmětu Zobrazit rozvrh
Kód Zakončení Kredity Rozsah Jazyk výuky
BE4M36UIR Z,ZK 6 2P+2C anglicky
Předmět nesmí být zapsán současně s:
Umělá inteligence v robotice (B4M36UIR)
Předmět je náhradou za:
Umělá inteligence v robotice (B4M36UIR)
Přednášející:
Jan Faigl (gar.), Stefan Edelkamp, Tomáš Kroupa
Cvičící:
Jan Faigl (gar.), Stefan Edelkamp, Tomáš Kroupa, Jiří Kubík, David Milec, Miloš Prágr, Jakub Sláma, David Valouch
Předmět zajišťuje:
katedra počítačů
Anotace:

The course aims to acquaint students with the use of planning approaches and decision-making techniques of artificial intelligence for solving problems arising in autonomous robotic systems. Students in the course are employing knowledge of planning algorithms, game theory, and solving optimization problems in selected application scenarios of mobile robotics. Students first learn architectures of autonomous systems based on reactive and behavioral models of autonomous systems. The considered application scenarios and robotic problems include path planning, persistent environmental monitoring, robotic exploration of unknown environments, online real-time decision-making, deconfliction in autonomous systems, and solutions of antagonistic conflicts. In laboratory exercises, students practice their problem formulations of robotic challenges and practical solutions in a realistic robotic simulator or consumer mobile robots.

Požadavky:
Osnova přednášek:

1. Course information, introduction to robotics

2. Robotic paradigms and control architectures

3. Path planning - grid and graph-based path planning methods

4. Robotic information gathering - Mobile robot exploration

5. Multi-goal path planning

6. Data collection planning

7. Curvature-constrained data collection planning

8. Randomized sampling-based motion planning methods

9. Visibility based pursuit-evasion games

10. Patrolling games

11. Temporal task-motion planning

12. Multi-robot planning

13. Reserve (invited lecture of a guest host)

14. Reserve (invited lecture of a guest host)

Osnova cvičení:

During laboratory exercises, students practice robotic challenges and practical solutions in a realistic robotic simulator or mobile robots.

- Computational models of autonomous systems;

- Path planning, randomized search techniques, multi-goal path planning, and informative path planning;

- Robotic exploration, online decision-making, persistent environmental monitoring, decision-making with limited resources;

- Methods of game theory and safety games in mobile robotics tasks, solving antagonistic conflict;

- Reactive and behavioral models in tasks of collective robotics;

- Coordination and cooperation in autonomous systems;

1. Introduction to CoppeliaSim and open-loop robot locomotion control

2. Exteroceptive sensing and reactive-based obstacle avoidance

3. Mapping

4. Grid and graph-based path planning

5. Incremental path planning

6. Mobile robot exploration

7. Semestral project assignment

8. Data collection path planning with remote sensing (TSPN)

9. Curvature-constrained data collection path planning (DTSPN)

10. Randomized sampling-based algorithms

11. Curvature-constrained local planning with RRT-based algorithms

12. Pursuit evasion - greedy policy and value iteration policy

13. Area patrolling

14. Semestral project discussion

Cíle studia:

The goal of the course is to developed practical experience with the deployment of planning and optimization methods in robotics states. The hands-off experience supports the practical understanding limitations of physical systems. After completing the course, the students should understand that problems with real robots need to make sufficient simplifications yielding satisfactory solutions but still be computationally feasible.

Studijní materiály:

• Course materials - https://cw.fel.cvut.cz/wiki/courses/uir/start

• 1st chapter: Robin R. Murphy: Introduction to AI Robotics, MIT Press, Cambridge, MA, 2001

• Steven M. LaValle: Planning Algorithms, Cambridge University Press, 2006 (http://planning.cs.uiuc.edu )

• Maja J. Mataric: The Robotics Primer, 2007, MIT Press.

• Kevin M. Lynch, Frank C. Park: Modern Robotics: Mechanics, Planning, and Control, Cambridge University Press, 2017.

Poznámka:
Další informace:
https://cw.fel.cvut.cz/wiki/courses/uir/
Rozvrh na zimní semestr 2022/2023:
06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Po
místnost KN:E-107

11:00–12:30
(přednášková par. 1)
Karlovo nám.
Zengerova posluchárna K1
místnost KN:E-307
Prágr M.
14:30–16:00
(přednášková par. 1
paralelka 102)

Karlovo nám.
HW-lab K307
místnost KN:E-307
Prágr M.
16:15–17:45
(přednášková par. 1
paralelka 103)

Karlovo nám.
HW-lab K307
Út
St
Čt

Rozvrh na letní semestr 2022/2023:
Rozvrh není připraven
Předmět je součástí následujících studijních plánů:
Platnost dat k 6. 2. 2023
Aktualizace výše uvedených informací naleznete na adrese https://bilakniha.cvut.cz/cs/predmet4870106.html