Riccardo De Benedictis

Modeling users of crisis training environments by integrating psychological and physiological data

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.

Timeline Planning in the J-TRE Environment

Timeline-based representations constitute a quite natural way to reason on time and resource constraints while planning. Additionally timeline-based planners have been demonstrated as successful in modeling and solving problems in several real world domains. In spite of these successes, any aspect related to search control remains a “black art” for few experts of the particular approach mostly because these architectures are huge application developments environments. For example, the exploration of alternative search techniques is quite hard. This paper proposes a general architecture for timeline-based reasoning that brings together key aspects of such reasoning leaving freedom to specific implementations on both constraint reasoning engines and resolution heuristics. Within such architecture, called J-tre, three different planners are built and compared with respect to a quite challenging reference problem. The experiments shed some light on key differences and pave the way for future works.

Supporting Active and Healthy Ageing by Exploiting a Telepresence Robot and Personalized Delivery of Information

Supporting active and healthy ageing represents an opportunity for improving the quality of life of older citizens while reducing the unsustainable pressure on health systems. The GiraffPlus project aims at improving health quality by offering personalized services for end users on top of a non-invasive state-of-the-art continuous data-gathering infrastructure. Specifically, the system collects elderly daily behaviour and physiological measures from distributed sensors in living environments. In addition, GiraffPlus organizes the gathered information so as to provide customizable visualization and monitoring services to the different users of the system. This paper describes the latest results achieved within the project specifically focusing on the interactive services toward the users.

Integrating Logic and Constraint Reasoning in a Timeline-Based Planner

This paper introduces the ongoing work for a novel domain-independent planning system which takes inspiration from both Constraint Programming (CP) and Logic Programming (LP), flavouring it all with Object Oriented features. We will see a specific customization of our environment to the particular kind of automated planning referred to as timeline-based. By allowing for the interesting ability of solving both planning and scheduling problems in a uniform schema, the resulting system is particularly suitable for complex domains arising from real dynamic scenarios. The paper proposes a resolution algorithm and enhances it with some (static and dynamic) heuristics to help the solving process. The system is tested on different benchmark problems from classical planning domains like the Blocks World to more challenging temporally expressive problems like the Temporal Machine Shop and the Cooking Carbonara problems demonstrating how the new planner, named iLoC, compares with respect to other state-of-the-art planners.

Adaptive Reminders in an Ambient Assisted Living Environment

The GiraffPlus home environment represents a complete AAL system that gathers environmental and physiological measures from distributed sensors for continuous monitoring of an older person. A key point of innovation in the project is the synthesis of reasoning services on the gathered data. Among those services the personalisation of feedback messages to users according to both individual’s needs and continuous data analysis represents an open challenge. This paper paves the way with respect to this challenge by presenting a user-adaptive reminding services endowed with the ability to trigger heterogeneous messages over time. The messages can simply remind to take a medication, can warn that a physiological value is deteriorating, or even offer regular suggestions on “good quality of life behaviour” triggered by some observation on individual users data.

Integrating planning and scheduling in the ISS fluid science laboratory domain

This paper describes a Planning and Scheduling Service (Pss) to support the Increment Planning Process for the International Space Station (ISS) payload management. The Pss is described while targeting the planning of experiments in the Fluid Science Laboratory (FSL), an ISS facility managed by Telespazio User Support and Operation Centre (T-USOC) that has been identified as a representative case study due to its complexity. The timeline-based approach inside the Pss is evaluated against realistic planning benchmark problems.

From Sensor Data to User Services in GiraffPlus

This paper presents an ongoing effort to create added value complete services for end users on top of an AAL continuous data gathering environment. It first presents the general architecture proposed by the GiraffPlus project for long term monitoring of older users at home, then describes the main choices concerning the middleware (universAAL compliant), the long-term data storage, and a user-oriented component, called DVPIS, dedicated to interaction with different users of the AAL environment. The current status of a deployed version of the system is then shortly described.

A Tool for Managing Elderly Volunteering Activities in Small Organizations

This paper describes a pilot application developed by the authors within a project in the area of elders assistance. Specifically, the work addresses the problem of assigning scheduled activities to a set of volunteers by means of an interactive tool that considers both users’ needs/preferences and constraints posed by the organization that manages the volunteers. Particular emphasis is given to the problem of assigning a group of seniors to the “right task” so as to obtain a positive outcome of the services offered by the volunteering association while maximizing the volunteers’ level of satisfaction perceived, in this domain, as a relevant requirement. This paper describes the design of a complete application for supporting this process focusing, in particular, on the back-end functionalities where a formalization as a generic optimization problem and a heuristic, developed to serve the time constants required in the domain, have been integrated. Experimental results, conducted with realistic data, support the particular design of the solution and encourage future work.

Enhancing the Interactive Services of a Telepresence Robot for AAL: Developments and a Psycho-physiological Assessment

This paper describes the work done on a telepresence robot named GIRAFF and part of a telecare AAL system derived from the GIRAFFPLUS project for supporting and monitoring elderly people at home. Specifically, from the long term trials in real houses, a number of user requirements have emerged that inspired changes and improvements on the robotic platform. The implementation of both multimodal communication capabilities and enhanced information services introduced new interesting questions related to human-robot interaction and specifically to usability, valence of interaction, and cognitive load required to interact with and through the robot. An experimental session based on a combination of physiological and psychological methods showed that the enhanced platform is usable, the interaction pleasant and the required workload limited. The analysis of psychophysiological correlates supported the findings from self-report measures and provides further information. It has been possible to discriminate physiological responses between multimodal interaction and the use of new services. Specifically, while usability can be specifically related to the usage of multichannel commands, positive emotions elicited by the interaction with GIRAFF seems to be mostly ascribable to the usage of services provided for the communication with another person.

User-Oriented Services Based on Sensor Data

This paper explores the issue of creating end-to-end services for older adults and their caregivers starting from a continuous gathering of sensor data from their living environment. The described work is part of the GiraffPlus project in which an intelligent AAL environment has been developed. The whole system relies on a state-of-the-art middleware for sensor data gathering and the pursued perspective is the one of designing added value services based on such data. The paper presents the general project concept and its different ingredients then presents two different services: a reasoner for person tracking, and an interaction service that connects the human network involved in a given application environment.