The aim of the course is to provide students with a general overview of the cognitive robot development in order to achieve autonomous behaviour while solving the given task in real-world situations. Students will learn how to develop and implement machine learning based on computational intelligence AI techniques in order to achieve autonomous behaviour of the robot. In experimental process students will assess performance and accuracy of the developed model. The final outcome is to provide them with basics in cognitive capabilities of autonomous robots so as to enable them further research in this field.

Expected learning outcomes are as follows: • Selection of methods based on the application of artificial neural networks and other computational intelligence AI techniques in designing and building intelligence of cognitive robots; • Implementation of developed algorithms in order to enable autonomous behaviour of mobile robots in laboratory model of manufacturing environment; • Advanced programming in MATLAB® environment; • Experimental verification of autonomous robot behaviour with analysis of experimental results and comparison with other existing methods; • Building ability to analyze related work in the field of cognitive robotics; • Team work.

Cognitive robotics – development of autonomous robot behaviour and its implementation in advanced technologies of the 21st century. Autonomous robots - machine learning from experience; learning from human teachers (Learning from Demonstrations-LfD); developing the ability to deal effectively with the real environment. Common elements and functions of autonomous robot: • Machine vision • Proximity sensing • Anticipation and planning • Programmable motion (mobility) • Teachability • Ability to learn from mistakes • Long-term knowledge acquisition • Ability to explore on its own, etc. Empirical robot control. Implementation of machine learning and computational intelligence techniques in autonomous robotic systems with the primary goal to make the robot act and react appropriately in real-world situations (e.g. autonomous mobile robots can thus be observed interacting with their manufacturing environment based on long-term knowledge acquisition).

Sensors: lasers, sonars and camera (stereo vision). Sensor models. Estimation of mobile robot pose – localization. Simultaneous localization and mapping (SLAM). Robot motion planning and future actions. Hybrid mobile robot control algorithm based on firefly method and homography visual servoing. Mobile robot learning of complex skills and autonomous behaviour based on examples provided by teacher: Learning from Demonstrations (LfD).

MSc degree of technically oriented faculty.

1. Z. Miljković, M.M. Petrović, INTELLIGENT MANUFACTURING SYSTEMS – with excerpts from robotics and artificial intelligence, Textbook, XXVIII+409 p., University of Belgrade - Faculty of Mechanical Engineering, 2021 (I edition), 18.1 /In Serbian/ 2. Z. Miljković, D. Aleksendrić, ARTIFICIAL NEURAL NETWORKS – solved examples with theoretical background (2nd ed.), Textbook, University of Belgrade - Faculty of Mechanical Engineering, 2018, 18.1 /In Serbian/ 3. Z. Miljković, SYSTEMS OF ARTIFICIAL NEURAL NETWORKS IN PRODUCTION TECHNOLOGIES, Monograph book within the Series Intelligent Manufacturing Systems, Vol. 8, University of Belgrade - Faculty of Mechanical Engineering, 2003, 18.1 /In Serbian/ 4. Laboratory mobile robots (PAL-TIAGo - Mobile Manipulator Robot with stereo vision system; K-Team's Khepera II mobile robot with gripper and camera; LEGO Mindstorms NXT & LEGO Mindstorms EV3 Sets of reconfigurable mobile robots equipped with sensors and micro-controllers; RAICO (Robot with Artificial Intelligence based Cognition) & DOMINO (Deep learning based Omnidirectional Mobile robot with INtelligent cOntrol) - prototypes of own development mobile robots), Laboratory CeNT, University of Belgrade - Faculty of Mechanical Engineering. 5. Laboratory model of designed manufacturing system, Laboratory CeNT, University of Belgrade - Faculty of Mechanical Engineering. 6. Software packages (BPnet, ART Simulator, Python 3.14.0rc2 and 3.13.7, MATLAB®), Laboratory CeNT, University of Belgrade - Faculty of Mechanical Engineering.

Total assigned hours: 65

New material: 30
Elaboration and examples (recapitulation): 20

Auditory exercises: 0
Laboratory exercises: 0
Calculation tasks: 0
Seminar paper: 0
Project: 0
Consultations: 0
Discussion/workshop: 0
Research study work: 0

Review and grading of calculation tasks: 0
Review and grading of lab reports: 0
Review and grading of seminar papers: 10
Review and grading of the project: 0
Test: 0
Test: 0
Final exam: 5

Activity during lectures: 20
Test/test: 0
Laboratory practice: 0
Calculation tasks: 0
Seminar paper: 40
Project: 0
Final exam: 40
Requirement for taking the exam (required number of points): 40

R. Siegwart, I.R. Nourbakhsh, D. Scaramuzza, (2011) INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS, 2nd Edition, 472 pp. (ISBN 9780262015356), The MIT Press, Cambridge, MA 02142.; E. Alpaydin, (2010) INTRODUCTION TO MACHINE LEARNING, 2nd Edition, 400 pp. (ISBN 9780262012119), The MIT Press, Cambridge, England.; Yang,X.S., (2010) ENGINEERING OPTIMIZATION: AN INTRODUCTION WITH METAHEURISTIC APPLICATIONS, 376 pp. (ISBN 978-0-470-58246-6), Wiley.; Dudek,G., Jenkin,M., (2024) COMPUTATIONAL PRINCIPLES OF MOBILE ROBOTICS, 3rd Edition, 450 pp. (9781108736381), Cambridge University Press.; Nolfi, S., Floreano, D., (2000) EVOLUTIONARY ROBOTICS: THE BIOLOGY, INTELLIGENCE, AND TECHNOLOGY OF SELF-ORGANIZING MACHINES, 320 pp. (ISBN 9780262140706), The MIT Press.