Researchers have explored the design of ambient information systems across a wide range of physical and screen-based media. This work has yielded rich examples of design approache...
We propose a novel approach to optimize Partially Observable Markov Decisions Processes (POMDPs) defined on continuous spaces. To date, most algorithms for model-based POMDPs are ...
Josep M. Porta, Nikos A. Vlassis, Matthijs T. J. S...
In this note, we propose a method to perform segmentation on the tensor manifold, that is, the space of positive definite matrices of given dimension. In this work, we explicitly ...
Yogesh Rathi, Allen Tannenbaum, Oleg V. Michailovi...
Designing distributed controllers for self-reconfiguring modular robots has been consistently challenging. We have developed a reinforcement learning approach which can be used bo...
The purpose of our research is to support cognitive, motor, and emotional development of severely disabled children in the school context. We designed and implemented a set of nov...