Narrow Results

This paper proposes a statistical framework to develop user-adapted spoken dialog systems. The proposed framework integrates two main models. The first model is used to predict the user’s intention during the dialog. The second model uses this prediction and the history of dialog up to the current moment to predict the next system response. This prediction is performed with an ensemble-based classifier trained for each of the tasks considered, so that a better selection of the next system can be attained weighting the outputs of these specialized classifiers. The codification of the information and the definition of data structures to store the data supplied by the user throughout the dialog makes the estimation of the models from the training data and practical domains manageable. We describe our proposal and its application and detailed evaluation in a practical spoken dialog system.

Any physical space can be augmented with digital information, associated to various locations or artefacts contained in it. In this paper, an abstract architecture is presented, supporting interaction with mobile context aware applications in public digitally augmented spaces. We focus on how this architecture supports personalization of interaction and adaptation. The main goal of the architecture is to allow users to benefit of a uniform and personalized experience across different contexts and spaces. Among the concerns are: to support high interoperability and flexibility and to address issues of privacy and user control. The framework has been tested in typical augmented spaces: a library and a museum. The paper concludes with a set of examples of use of the defined framework that cover typical situations for intra-space and across spaces usage.

Humanoid robots that share the same space with humans need to be socially acceptable and effective as they interact with people. In this paper we focus our attention on the definition of a behavior-based robotic architecture that (1) allows the robot to navigate safely in a cluttered and dynamically changing domestic environment and (2) encodes embodied non-verbal interactions: the robot respects the users personal space (PS) by choosing the appropriate distance and direction of approach. The model of the PS is derived from human–robot interaction tests, and it is described in a convenient mathematical form. The robot's target location is dynamically inferred through the solution of a Bayesian filtering problem. The validation of the overall behavioral architecture shows that the robot is able to exhibit appropriate proxemic behavior.