Search

Most robotic systems are usually used and evaluated in laboratory setting for a limited period of time. The limitation of lab evaluation is that it does not take into account the different challenges imposed by the fielding of robotic solutions into real contexts. Our current work evaluates a robotic telepresence platform to be used with elderly people. This paper describes our effort toward a comprehensive, ecological and longitudinal evaluation of such robots. Specifically, the paper highlights open points related to the transition from laboratory to real world settings. It first discusses some results from a short term evaluation performed in Italy, obtained by interviewing 44 healthcare workers as possible clients (people connecting to the robot) and 10 older adults as possible end users (people receiving visits through the robot). It then describes a complete evaluation plan designed for a long term assessment also dwelling on the initial application of such methodology to test sites, finally it introduces some technical features that could enable a more robust real world deployment. © Springer-Verlag Berlin Heidelberg 2013.

Training for crisis decision makers poses a number of challenges that range from the necessity to foster creative decision making to the need of creating engaging and realistic scenarios in support of experiential learning. This article describes our effort to build an end-to-end intelligent system, called the PANDORA-BOX, that supports a trainer in populating a 4-5 hours training session with exercises for a class of decision makers to teach them how to achieve joint decisions under stress. The paper gives a comprehensive view of the current system and in particular focuses on how AI planning technology has been customized to serve this purpose. Aspects considered are: (a) the timeline-based representation that acts as the core component for creating training sessions and unifying different concepts of the PANDORA domain; (b) the combination of planning and execution functionalities to maintain and dynamically adapt a "lesson plan" on the basis of both trainees-trainer interactions and individual behavioral features and performance; (c) the importance of keeping the trainer in the loop preserving his/her responsibility in creating content for the class but endowing him/her with a set of new functionalities.

This paper describes aspects of a training environment for crisis decision makers who, notoriously, operate in highly stressful and unpredictable situations. Training such decision makers is the goal of Pandora-Box, a system which is able to teach a class of trainees representing different authorities that coordinate their interventions in critical situations. This paper dwells on the selection and modeling of the relevant human features that are shown to have an influence in decision making under crisis. The chosen features are used to create a trainee model on the basis of which the system adjusts the training exercises with the ultimate goal of maximizing the effectiveness of training. Trainees models are built by merging physiological and psychological data, and are represented by means of a timeline-based approach, a representation derived from planning technology. The infrastructure built for the trainee modeling constitutes the basis to assess the influence of specific variables (e.g., personality traits, self efficacy, stress and anxiety) on the performance of crisis managers during the training. © 2011 Springer-Verlag.

This paper describes outcome from a project aimed at creating an instance of integrated environment endowed with heterogeneous software and robotic agents to actively assist an elderly person at home. Specifically, a proactive environment for continuous daily activity monitoring has been created in which an autonomous robot acts as the main interactor with the person. This paper describes how the synergy of different technologies guarantees an overall intelligent behavior capable of personalized and contextualized interaction with the assisted person.

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.

This paper describes a software tool that synthesizes commands for data downlink from the on-board memory of the Mars Express spacecraft to the ground station. Some features of the tool are depicted, showing how AI techniques for planning, scheduling, domain modeling and intelligent interaction have been put into context in a challenging application environment. The system is the result of a two steps effort: a first study which produced a demonstration prototype able to capture the main aspects of the problem, and a second effort that has developed a fielded application completely integrated in operations environment. The tool is in daily use by the mission planning team of Mars Express at the European Space Agency since February 2005.

This paper explores the interaction between human and artificial problem solvers when interacting with an Intelligent Scheduling System. An experimental study is presented aimed at investigating the users’ attitude towards two alternative strategies for solving scheduling problems: automated and interactive. According to an automated strategy the responsibility of solving the problem is delegated to the artificial solver, while according to an interactive strategy human and automated solvers cooperate to achieve a problem solution. Previous observations of end-users’ reactions to problem solving systems have shown that users are often skeptical toward artificial solver performance and prefer to keep the control of the problem solving process. The current study aims at understanding the role played by both the users’ expertise and the difficulty of the problem in choosing one of the two strategies. Results show that user expertise and task difficulty interact in influencing this choice. A second aspect explored in the paper concerns the context in which the end-users rely on explanations to understand the solving process. Explanations are in fact expected to play an important role when artificial systems are used for cooperative and interactive problem solving. Results support the hypothesis that explanation services are more often called into play in case of problem solving failures.

This paper describes an innovative application of AI technology in the area of space mission planning. A system called Mexar has been developed to synthesize spacecraft operational commands for the memory dumping problem of the ESA mission called Mars Express. The approach implemented in Mexar is centered on constraint satisfaction techniques enhanced with flexible user interaction modalities. This paper describes the effort in developing a complete application that models and solves a problem, and also offers functionalities to help users in interacting with different aspects of the problem. The paper surveys the design principles underlying the whole project and shows how different components contribute to the delivered system.

This work introduces a combinatorial optimization problem called MARS EXPRESS Memory Dumping Problem (MEX-MDP), which arises in the European Space Agency program MARS EXPRESS. It concerns the generation of high quality schedules for the spacecraft memory downlink problem. MEX-MDP is an NP-hard combinatorial problem characterized by several kinds of constraints, such as on-board memory capacity, limited communication windows over the downlink channel, deadlines and ready times on the observation activities. The contribution of this paper is twofold: on one hand it provides a CSP model of a real problem, and on the other it presents a set of metaheuristic strategies based on local and randomized search which are built around the constraint-based model of the problem. The algorithms are evaluated on a benchmark set distilled from ESA documentation and the results are compared against a lower bound of the objective function. This work describes results obtained in the framework of a research study conducted for the European Space Agency (ESA-ESOC) under contract No.14709/00/D/IM.