Rīgas Tehniskā universitāte 28.09.2021 07:08

RTU Course "Large Range Robotic Adaptive Virtual Reality and Artificial Intelligence Technology" 27101 null General data Code EEI788 Course title Large Range Robotic Motion Simulator Adaptive Virtual Reality and Artificial Intelligence Technology Course status in the programme Compulsory/Courses of Limited Choice Responsible instructor Mihails Gorobecs Academic staff Andrejs Potapovs Volume of the course: parts and credits points 1 part, 5.0 Credit Points, 7.5 ECTS credits Language of instruction LV, EN Annotation The study course is devoted to study the virtual reality of a large range robotic motion simulator and to mastering and programming of artificial intelligence techniques such as neural networks and evolutionary algorithms to develop adaptive abilities of a virtual environment to adapt to the needs of a robotic simulator operator - learning, training and health control. The study course uses a BEC Rides Large Range Robotic Motion Simulator based on a 6 DoF KUKA industrial manipulator with operator or passenger gondola. Goals and objectives of the course in terms of The aim of the study course is to master the principles, methods and artificial intelligence competences and skills algorithms of virtual reality and its adaptation mechanisms using the industrial BEC KUKA Robot 6 DoF Large Range Simulator with the operator or passenger in the robot gondola. The tasks of the course are: 1) to develop Unity 3D virtual reality environment development skills; 2) to improve programming skills in C # language; 3) to teach to create neural networks; 4) to acquaint with the neural networks and implement evolutionary algorithms for adaptation of robot virtual environment according to the task and operator's actions. Structure and tasks of independent studies Homeworks, practical tasks. Individual study work assignment for each student. Recommended literature Obligāta/Obligatory: 1. BEC Rides Robot manual. 2. Thomas Braunl. Embedded Robotics, Mobile Robot Design and Applications with Embedded Systems, Second Edition. Springer, 2006. 458 p. 3. Jones T. AI Application Programming. Charles River Media, Hingham, Massachusetts, 2003. 4. Luger G. F. Artificial Intelligence. Structures and Strategies for Complex Problem Solving, Williams, 2003. 5. Ruano A. E. Intelligent Control Systems using Computational Intelligence Techniques. The Institution of Electrical Engineers, 2005. 454 p. Papildu/Additional: 6. Russel S. J., Norvig P. Artificial Intelligence. A Modern Approach, 2nd edition - Prentice Hall, 2006, 1408 p. 7. Haykin S. Neural Networks. A Comprehensive Foundation. Prentice-Hall, 1999, 897 p. 8. Bill Drury. The Control Techniques Drives and Controls Handbook, Second Edition. The Institution of Electrical Engineers, 2009. 724 p. 9. Rutkowski L. Flexible Neuro-Fuzzy Systems: Structures, Learning and Performance Evaluation. Springer, 2004, 279 p. Course prerequisites Programming, Adaptive systems, Advanced Mathematics, Mathematical analysis.

Course contents Content Full- and part-time Part time extramural intramural studies studies Contact Indep. Contact Indep. Hours work Hours work Basic principles of using robotic motion simulator. 6 9 3 12 Research and development of dynamic models of different physical systems in Unity 3D. 8 12 3 12 Implementation of dynamic models of different physical systems in industrial robotics motion 6 9 4 16 simulator. Basic principles of Neural Networks for virtual reality. 6 9 3 12 Basic principles of Evolutionary Algorithms for virtual reality. 6 9 3 12 Practical and laboratory works: Artificial Intelligence programming in C#: Neural Networks for 10 15 5 20 adaptive virtual reality. Practical and laboratory works: Artificial Intelligence programming in C#: Evolutionary Algorithms 10 15 5 20 for adaptive virtual reality. Practical and laboratory works: Software component research and development with feedback 8 12 4 16 implementing adaptive virtual reality interface for robotic motion simulator. Practical and laboratory works: Development of examples of robotic motion simulator application 10 15 5 20 with virtual reality simulation. Practical and laboratory works: Development of examples of robotic motion simulator application 10 15 5 20 with virtual reality adaptation. Total: 80 120 40 160 Learning outcomes and assessment Learning outcomes Assessment methods Understands the principles of robot simulator virtual environment development, adaptive, neural Theoretical exam questions, tests. networks and evolutionary algorithms and their programming solutions in C # language. Is able to develop a virtual environment for a robot simulator in Unity 3D software. Practical and laboratory works. Course work. Is familiar with the programming of artificial intelligence algorithms for virtual reality. Practical task of exam. Practical and laboratory works. Is able to implement adaptive control for a robotic motion simulator for various tasks. Course work.

Evaluation criteria of study results Criterion % Answers to theoretical exam questions 15 Fulfilment of practical task of exam 20 Fulfilment of tests 15 Fulfilment of practical and laboratory tasks 20 Fulfilment of course work 30 Total: 100

Study subject structure Part CP Hours per Week Tests Lectures Practical Lab. Test Exam Work 1. 5.0 2.0 1.5 1.5 *