Video Hight-tech Systems and Robotics
High-tech systems and robotics are important application domains for artificial intelligence and engineering systems. Industries covering these applications are intensive on technology development, combine methods and tooling from computer science, information technology, systems and control and life and social sciences. Moreover, industries are demanding on autonomous decision making, the certification of robust performance of machines in uncertain environments and the realization of machine specifications that are unprecedented.
This implies a strong focus on control, automated decision making and process optimization. Also, questions on operator support for maintenance of high-tech equipment, the detection and identification of failures, safety and optimized performance, material design, and the discovery of material properties are of key importance to the engineering of high-tech systems and robotics.
What you will learn
In this track you learn how data-based and model-based tools can be properly employed for process optimization, design and for the control of dynamical systems. Like in many technical applications, uncertainty in either the process, its operation or its environment plays a key role that needs to be understood and considered in decision making processes.
You will learn how to learn from process behavior, how to reduce uncertainty. You will learn how AI techniques and data inferred from experiments can lead to relevant knowledge of processes and how to subsequently use this knowledge for performance enhancement and optimization of processes.
You will learn methods and techniques that lead to verification and performance certification in safety critical situations; modeling and complexity management in cyber-physical systems; human interfacing; techniques for failure prediction, maintenance scheduling, service, support, and calibration. Furthermore, you learn that data-human-machine integration is especially relevant in the high-tech systems sector to enhance and complement human decision making in processes.