Search

Socially assistive robots should provide users with personalized assistance within a wide range of scenarios such as hospitals, home or social settings and private houses. Different people may have different needs both at the cognitive/physical support level and in relation to the preferences of interaction. Consequently the typology of tasks and the way the assistance is delivered can change according to the person with whom the robot is interacting. The authors’ long-term research goal is the realization of an advanced cognitive system able to support multiple assistive scenarios with adaptations over time. We here show how the integration of model-based and model-free AI technologies can contextualize robot assistive behaviors and dynamically decide what to do (assistive plan) and how to do it (assistive plan execution), according to the different features and needs of assisted persons. Although the approach is general, the paper specifically focuses on the synthesis of personalized therapies for (cognitive) stimulation of users.

In Ambient Assisted Living scenarios, elderly people are supported by pervasive and smart environments in their daily mobility and activities, with which they interact by means of a variety of devices and services deployed in the house. These devices, in addition to their particular function, can provide useful context information about the user behavior. In this paper we propose an indoor localization technique that exploits the presence of commercially available devices in the GiraffPlus AAL environment. GiraffPlus is a EU funded project, running in several test sites across Europe, that combines social interaction and long-term monitoring to help people live independently. In this context, the proposed localization algorithm is able to provide the position information in terms of last room visited by the user improving considerably the reaction of a user's caregiver in emergency situations. This paper also aims at providing a performance characterization of the commercially available devices used in the GiraffPlus AAL environments. We prove that, in order to guarantee an high level of reliability, this kind of device show a considerable transmission delay that makes the localization process non-trivial.

This paper describes aspects of RAXEM2, an intelligent software system developed to support human mission planners in the daily task to plan uplink commands for the MARS EXPRESS mission at the European Space Agency. A first system called RAXEM has been in operational use at the ESA-ESOC mission control center since Summer 2007. During 2008 authors have been working to a new version of the tool to both incorporate new functionalities and capture the entire life-cycle of the plan uplink problem. RAXEM2 has been released for daily use on March 2009 replacing previous work practice. The new tool combines a flexible AI-based automated algorithm, a user-friendly interaction front-end, and several functionalities for information management, overall guaranteeing continuity of work practice. The paper touches upon various aspects of the new system and comments on how a key factor for success has been the integration of such different modules in a unique comprehensive support environment.