Matias Waller

Presentation

A recurring theme in my research is how, with access to large amounts of data, to develop mathematical models that are meaningful representations of the underlying (technical) system. For example, does the data motivate the use of nonlinear models? What type of model can be used for supporting decision-making in a supervisory system? How do you know how statistically similar models will affect control performance when designing closed-loop systems?

Some specific themes are:

• Nonlinear system identification
• Autopilots and autonomous sailing robots
• Identification for control
• Decoupling
• Predictive models for supervision and control.