Flexible Automation and Artificial Intelligence

Industrial automation, Robotics, Machine vision, Distributed control systems, Data science, Estimation and learning

Completing the course, the students shall have acquired knowledge of industrial automation technologies with the focus on flexibility. Specific topics of focus will include machine vision, artificial intelligence and distributed control systems. The students will acquire hands-on experience of implementing computational models for flexible, modular automation systems.

Knowledge

• Familiarity with the pool of traditional industrial automation technologies
• Familiarity with the basics of industrial robotics
• Knowledge on the principles of industrial vision systems
• Knowledge on the novel distributed control systems
• Knowledge on flexible automation techniques
• Knowledge on the mathematical foundation of estimation and machine learning
• Knowledge on the data science techniques in the context of distributed automated systems

Skills

• Prototyping of computational solutions in Python
• Experience with creation of computer vision algorithms using OpenCV and Scikit-image
• Manipulation of geometric primitives in matrix form using NumPy
• Data science skills: data preparation, training of machine learning models using Pandas, Scikit-learn

General competence

• Can contribute to the implementation of technical solutions as part of Industry 4.0 transformations
• Can apply the acquired knowledge and skills in forthcoming assignments and projects
• Can contribute to new thinking and innovation in the area of ​​manufacturing automation
• Can contribute to the realization of novel automation solutions based on flexible architectures and intelligent algorithms

The course is based on seminars that combine lecturing with tutoring in the given topics. The seminars will be organized on-campus, with the access being provided for the remote students via a web-conferencing system. The homework assignments are based on programming tasks using Jupyter notebooks and/or Python scripts, which will be discussed in-class during the tutoring sessions. In case of less than 4 students, the course will be based on self-study.