Development of intelligent systems

During the course the following topics will be presented:
Technologies and tools for the development of intelligent systems: an introduction
Typical applications of intelligent technologies
Technological platforms and development methodologies
Tools for machine perception, machine learning and reasoning, with the emphasis on the techniques for integration of these tools
Approaches to the integration of machine perception, learning, and planning into an artificial real-time agent system
Specific properties of robotic systems
Basics of mobile robotics
Case studies of the development of complex intelligent systems
The lectures will familiarize the students with key technologies and tools. The students will use these on practical problems within the scope of laboratory classes and projects. They will combine the knowledge and skills obtained in Artificial Intelligence and Machine Perception classes from the same course module. The emphasis of this course will be on the development of practical and functional implementations in both in simulation environments and especially in real-time systems operating on robot platforms. The implementations will be developed in open-source frameworks and tools for development of intelligent systems.

Dokumentacija prostodostopnega Robotskega operacijskega sistema ROSDocumentation of the open source Robot Operating System ROSwww.ros.org.
Dokumentacija prostodostopne knjižnice za delo s slikovnimi in 3D podatki PCLDocumentation of the open source Point Cloud Library PCLhttp://pointclouds.org.
S. Thrun, W. Burgard, D. Fox, Probabilistic Robotics (Intelligent Robotics and Autonomous Agents series), The MIT Press, 2005.
Dokumentacija sistema za strojno učenje Orange, prosto dostopna na spletnih straneh/Documentation of the system for machine learning Orange, freely available on the web pages www.ailab.si/orange/doc.

The course aims at teaching the students to develop an intelligent system by integrating techniques from artificial intelligence and machine perception. Students will learn how to design an intelligent system, how to select which tools and methods to use, and how to implement new components and integrate them into a functional robot system.
The students will develop skills in critical and analytical thinking. They will also acquire the ability to search knowledge sources and to search for resources and critically evaluate information. They will acquire the ability to apply the acquired knowledge in independent work for solving technical problems and to independently perform engineering tasks in the field of intelligent robotics. They will be able to solve specific well-defined tasks from this area. Since most of the work will be performed in teams, the students will also acquire the ability of team work.

Knowledge and understanding: Knowledge on methods and tools from machine perception and artificial intelligence and their integration within real-world functional systems.
Application: The application of techniques from machine perception and artificial intelligence, design and implementation of integrated intelligent systems for solving practical problems.
Reflection: Understanding the suitability of theoretical methods for solving practical problems, as well as understanding their requirements and limitations. The ability of analyzing and solving problems by developing intelligent systems.
Transferable skills: Combining the knowledge and skills the students learned during the courses on Artificial Intelligence and Machine perception, multidisciplinary approach, skills for searching and using the literature, application of suitable (primarily open source) software and hardware, identification and solving of complex problems.

Lectures with the appropriate audio-visual equipment in a classroom with suitable hardware and software, including appropriate robot platforms. Individual and group work. Emphasis on hands-on approaches and problem solving including implementation of the developed solutions on robotic systems.

Continuing (homework, midterm exams, project work)
Final (written and oral exam)
grading: 5 (fail), 6-10 (pass) (according to the Statute of UL)

WYATT, Jeremy L., AYDEMIR, Alper, BRENNER, Michael, HANHEIDE, Marc, HAWES, Nick, JENSFELT, Patric, KRISTAN, Matej, KRUIJFF, Geert-Jan M., LISON, Pierre, PRONOBIS, Andrzej, SJÖÖ, Kristoffer, VREČKO, Alen, ZENDER, Hendrik, ZILLICH, Michael, SKOČAJ, Danijel. Self-understanding and self-extension : a systems and representational approach. IEEE transactions on autonomous mental development, ISSN 1943-0604. [Print ed.], Dec. 2010, vol. 2, no. 4, str. 282-303, ilustr. [COBISS-SI-ID 8305492]
SKOČAJ, Danijel, LEONARDIS, Aleš, BISCHOF, Horst. Weighted and robust learning of subspace representations. Pattern recognition, ISSN 0031-3203. [Print ed.], May 2007, vol. 40, no. 5, str. [1556]-1569, ilustr. [COBISS-SI-ID 5898836]