|
Lecturer(s)
|
|
|
|
Course content
|
Content of lectures: Introduction " Agent-based approach to autonomous systems " AI areas with the impact and usability in autonomous systems Environment and its representation " Predicate representation " Object representation " Languages for autonomous systems Agent interaction with the environment " Active sensors " Active effectors " Localization Formulation of goals and planning with UI " Types of objectives and evaluate progress " STRIPS " Navigation and movement " Optimization and Genetic Algorithms Machine Learning " Machine learning types " Case based reasoning " Decision trees " Artificial neural networks in robotics Human - robot interaction " Use UI for HRI Distributed Systems " Multi-agent systems and agent communication " Intelligent Systems and their management and coordination Content of practicals: Seminars content thematically matches the structure of lectures. The main form of teaching are the exploration and implementation of selected techniques from lectures using simulation models and robotic systems.
|
|
Learning activities and teaching methods
|
Monologic (reading, lecture, briefing), Demonstration, Laboratory
- Preparation for classes
- 48 hours per semester
- Preparation for exam
- 26 hours per semester
- Semestral paper
- 26 hours per semester
- Class attendance
- 56 hours per semester
|
|
Learning outcomes
|
The course focuses on topics to be included in the field of artificial intelligence and their use in robotics and autonomous and embedded systems. The aim of the course is to introduce the selected methods from those fields, emphasis will be put on the classic agent concept of autonomous systems. The topics related to human-robot interaction and to problems of coordination of autonomous systems will also be included. During the seminars the students will learn to implement selected methods both in simulation models and in real robotic systems. After completing the course the student obtains a sufficient understanding of AI techniques applicable in autonomous systems and robots and will also have personal experience with their implementation.
Upon completion of the course the student will have knowledge of interrelated areas of autonomous systems and artificial intelligence and advanced data processing of various data types. Student will be able to to practically use this knowledge and implement it both in the simulation environment and in real robot systems and robots.
|
|
Prerequisites
|
To complete the course, it is advisable to have basic knowledge of computer networks and programming.
|
|
Assessment methods and criteria
|
Written examination, Analysis of student's work activities (technical works), Seminar work
During the semester, students work on projects arising from the subject matter. The exam is evaluated on the basis of semester, semestral work and theoretical test. Terms of endings: Compleeting exercise projects (about 5 tasks) - 5 x 10 p. (min. 25 p.) Semestral work - 40 b. (min. 20 b.) Test - 30 p. (min. 15 p.)
|
|
Recommended literature
|
-
HUHNS, Michael N. Distributed artificial intelligence. Elsevier, 2012.
-
Informační zdroje na síti Internet. Vzhledem k častým obměnám budou konkrétní místa upřesněna při zahájení výuky předmětu..
-
KAELBLING, Leslie Pack; ROSENSCHEIN, Stanley J. Action and planning in embedded agents. Robotics and autonomous systems, 1990.
-
MURPHY, Robin. Introduction to AI robotics. MIT press, 2000.
-
RUSSELL, Stuart; NORVIG, Peter; Artificial intelligence - A modern approach. Prentice-Hall, Egnlewood Cliffs, 1995, 25.
-
Bratko, I. Prolog Programming for Artificial Inteligence.. Addison - Wesley, 1986.
-
Mařík, V., Štěpánková, O., Lažanský, J. a kol. Umělá inteligence I.. Academia, 1993.
|