Adaptive Multimodal User Interfaces
Personal Homepage: http://www.mpi-inf.mpg.de/~oantti/
Group Homepage: http://hci.mpi-inf.mpg.de/
Designing easy-to-use user interfaces is a challenging problem-solving task. The number of possible designs in any meaningful design problem is too large to explore manually. For example, there are 1026 possible virtual keyboard designs – more than stars in the known universe (1024)! Ideally, the analysis of well-studied parts of a design could be automatized, allowing the designer to focus on the truly novel aspects of the problem. This goal can be achieved by models of human-computer interaction that make predictions on optimal designs.
We develop models of human-computer interaction that capture well-studied aspects of interaction and use them for optimizing interface designs. The basis of our work is quantitative behavioral modeling of interaction combined with computational methods for searching the optimal design. Whereas previous work in user interface design has been largely based on trial and error, this approach allows aggressive exploration of user interfaces. The outcomes are demonstrated as novel user interfaces targeted to both classic interactive tasks, such as text entry and menu selection, as well as novel multimodal and mixed reality interfaces.
Antti Oulasvirta joined Aalto University as an Associate Professor in spring 2014.
Mentor in Saarbrücken: Professor Hans-Peter Seidel