In this article we present an integrated system the domestic care of elderly people which is being developed within the RoboCare project. The system is composed of a network of sensors placed in the environment to reconstruct a global situation and a set of robotic and software agents for controlling the environment. Within this framework, the two main components that we describe in this article are: (1) a people and robot localization and tracking system that exploits stereo vision in order to monitor the positions of robots and persons; (2) a supervision framework that is in charge of collecting information about the distributed sensors and monitoring the activities of the assisted person. This article shows how, starting from these two ingredients, we are developing a system prototype for an "intelligent" environment, which acts as a global monitor surveying an assisted elderly person and reacts to the stimuli coming from the environment in order to control its evolution.

This article describes aspects of a fully implemented artificial intelligence (AI) system that integrates multiple intelligent components to actively assist an elderly person at home. Specifically, we describe how constraint-based scheduling technology is used to actively monitor a pattern of activities executed by the person and how detected temporal constraint violations are used to trigger meaningful and contextualized proactive interactions. This article also presents a psychological evaluation of the system focusing on elderly people's attitudes, in which system acceptability, perceived utility, interaction modality, and emotional response are considered.

No abstract

Abstract. This paper analyzes the problem of evaluating elderly people's perception of assistive robots and domotic environments. Specifically, we focus on aspects related to the modalities in which interaction can occur between an elder user and an assistive robotic agent. Our work benefits from the products of project ROBOCARE, namely, a domestic environment in which sensors, intelligent software components and a domestic robot provide a set of cognitive support services for the elder user. This paper analyzes a number of evaluation criteria in detail, specifically related to the robot's aspect, the way in which it communicates with the user, and the perceived usefulness of its support services. Among these criteria, the paper proposes and reports an evaluation of the Proactive interaction modality (where the system takes the initiative) and On-demand interaction (in which the user explicitly requests a service). Users evaluate the On-demand support services in personal safety scenarios as particularly useful, and less so in scenarios which are not critical. The paper also provides a discussion which can be useful for the design of future assistive agents and robotic companions.

No abstract

This paper presents a heuristic algorithm for solving a job-shop scheduling problem with sequence dependent setup times and min/max separation constraints among the activities (SDST-JSSP/max). The algorithm relies on a core constraintbased search procedure, which generates consistent orderings of activities that require the same resource by incrementally imposing precedence constraints on a temporally feasible solution. Key to the effectiveness of the search procedure is a conflict sampling method biased toward selection of most critical conflicts and coupled with a non-deterministic choice heuristic to guide the base conflict resolution process. This constraint-based search is then embedded within a larger iterative-sampling search framework to broaden search space coverage and promote solution optimization. The efficacy of the overall heuristic algorithm is demonstrated empirically both on a set of previously studied job-shop scheduling benchmark problems with sequence dependent setup times and by introducing a new benchmark with setups and generalized precedence constraints.

No abstract

No abstract