For an effective deployment in manufacturing, Collaborative Robots should be capable of adapting their behavior to the state of the environment and to keep the user safe and engaged during the interaction. Artificial Intelligence (AI) enables robots to autonomously operate understanding the environment, planning their tasks and acting to achieve some given goals. However, the effective deployment of AI technologies in real industrial environments is not straightforward. There is a need for engineering tools facilitating communication and interaction between AI engineers and Domain experts. This paper proposes a novel software tool, called TENANT (Tool fostEriNg Ai plaNning in roboTics) whose aim is to facilitate the use of AI planning technologies by providing domain experts like e.g., production engineers, with a graphical software framework to synthesize AI planning models abstracting from syntactic features of the underlying planning formalism.

This article is a retrospective overview of work performed in the domain of Active Assisted Living over a span of almost 18 years. The authors have been creating and refining artificial intelligence (AI) and robotics solutions to support older adults in maintaining their independence and improving their quality of life. The goal of this article is to identify strong features and general lessons learned from those experiences and conceive guidelines and new research directions for future deployment, also relying on an analysis of similar research efforts. The work considers key points that have contributed to increase the success of the innovative solutions grounding them on known technology acceptance models. The analysis is presented with a threefold perspective: A Technological vision illustrates the characteristics of the support systems to operate in a real environment with continuity, robustness, and safety; a Socio-Health perspective highlights the role of experts in the socio-assistance domain to provide contextualized and personalized help based on actual people's needs; finally, a Human dimension takes into account the personal aspects that influence the interaction with technology in the long term experience. The article promotes the crucial role of AI and robotics in ensuring intelligent and situated assistive behaviours. Finally, considering that the produced solutions are socio-technical systems, the article suggests a transdisciplinary approach in which different relevant disciplines merge together to have a complete, coordinated, and more informed vision of the problem.

MAESTRO (Sustainable Reference Framework evaluating equipment and services for seniors) is a web-based ICT multi modal platform providing a broad range of services and benefits in the domain of monitoring and self-monitoring sys- tems for well-being and health-related information acquisition. Specifically, MAE- STRO aims at realizing an innovative framework to facilitate the interaction and communication between producers and consumers at different levels, taking into ac- count needs of end-users and features of products. This paper provides an overview of the key concepts and capabilities of MAESTRO focusing on the use of the Inter- national Classification of Functioning, Disability and Health (ICF) to build profiles of end-users and discover and rank products that meet their health-related needs. Additionally, the paper shows the results of a study aimed at evaluating the clas- sification capabilities of MAESTRO and the integrated ICF-based taxonomy with respect to products and services developed within AAL (Active Assisted Living) Projects. The evaluation points out more recurrent health-related needs of end-users of AAL projects focus and underscore some limits and possible enhancements of the integrated ICF-based taxonomy.

The diffusion of Human-Robot Collaborative cells is prevented by some barriers. Classical control approaches seem not yet fully suitable for facing variability conveyed by the presence of human operators beside robots. Heterogeneous knowledge representation capabilities and abstract reasoning are crucial to enhance flexibility of control solutions. This work presents SOHO (Sharework Ontology for Human Robot Collaboration), a novel ontology specifically designed for Human-Robot Collaboration. The paper describes the pursued context-based approach, the novelty of the designed ontology with respect to the state of the art and shows its validity in a realistic Human-Robot Collaboration scenario.

This article describes the work done to create an innovative system to support people with Mild Cognitive Impairment or Mild Dementia. The basic idea of the system is to exploit an extremely simple and familiar technology for older people, namely television (TV). In fact, the TV-AssistDem system exploits the smart-TV technology to provide a series of support services, among which the connection via video conference with healthcare professional or with relatives and friends; monitoring of vital parameters; cognitive stimulation and reminders of important medicines and appointments. The article describes the co-design approach of the prototype pursued during the project which involves a constant and repeated involvement of potential users of the system over time. The refined prototype of TV-AssistDem went under an ecological test in the homes of representative users to assess its robustness and compliance to users needs. The additional objective of the work is to carry out a long-term study that involves the realisation of a clinical trial in two European countries (Spain and Romania) aimed at showing the validity of the proposed solution on the patient's quality of life but also on caregivers and socio-healthcare systems.

The personalized fruition of cultural heritage, especially with the health crisis we are currently experiencing, poses challenges to the learning and educational processes that could benefit from the use of intelligent tools. By emphasizing the interactivity of the learning process, in particular, the recent Technology Enhanced Learning (TEL) methodologies can represent an enabling factor for the construction of the common knowledge. This paper pursues the idea of integrating different heterogeneous artificial intelligence techniques for the personalized administration of stimuli in a dynamic learning environment. With this in mind, this paper describes a system, called WikiTEL and its first instantiation to Cultural Heritage visits in the Matera city.

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.

This paper discusses the issue of efficient resolution of timeline-based planning problems. In particular, taking inspiration from the more classical heuristics for the resolution of STRIPS-like problems, it proposes a new heuristic strategy which, while maintaining the variables lifted, allows more accurate decisions. The concepts presented in this work pave the way for a new type of heuristics which, at present, allow this kind of solvers a significant performance improvement.

Combining task and motion planning efficiently in human-robot collaboration (HRC) entails several challenges because of the uncertainty conveyed by the human behavior. Tasks plan execution should be continuously monitored and updated based on the actual behavior of the human and the robot to maintain productivity and safety. We propose control-based approach based on two layers, i.e., task planning and action planning. Each layer reasons at a different level of abstraction: task planning considers high-level operations without taking into account their motion properties; action planning optimizes the execution of high-level operations based on current human state and geometric reasoning. The result is a hierarchical framework where the bottom layer gives feedback to top layer about the feasibility of each task, and the top layer uses this feedback to (re)optimize the process plan. The method is applied to an industrial case study in which a robot and a human worker cooperate to assemble a mosaic.

This paper provides a quick overview of a Knowledge Engineering system, called ROS-TiPlEx (Timeline-based Planning and Execution with ROS), to provide a shared environment in which experts in robotics and planning can easily interact to, respectively, encode information about low-level robot control and define task planning and execution models. ROS-TiPlEx aims at facilitating the interaction between both kind of experts, thus, enhancing and possibly speeding up the process of an integrated control design. ROS-TiPlEx is the first tool addressing the connection of ROS and timeline-based planning.

During the last decade, industrial collaborative robots have entered assembly cells supporting human workers in repetitive and physical demanding operations. Such human-robot collaboration (HRC) scenarios entail many open issues. The deployment of highly flexible and adaptive plan-based controllers is capable of preserving productivity while enforcing human safety is then a crucial requirement. The deployment of plan-based solutions entails knowledge engineers and roboticists interactions in order to design well-suited models of robotic cells considering both operational and safety requirements. So, the ability of supporting knowledge engineering for integrating high level and low level control (also from non-specialist users) can facilitate deployment of effective and safe solutions in different industrial settings. In this chapter, we will provide an overview of some recent results concerning the development of a task planning and execution technology and its integration with a state of the art Knowledge Engineering environment to deploy safe and effective solutions in realistic manufacturing HRC scenarios. We will briefly present and discuss a HRC use case to demonstrate the effectiveness of such integration discussing its advantages.

Social Robotics is a research field aiming at designing robots able to interact with people in a natural manner. Within the domain of Socially Assistive Robotics the capability of adapting and personalizing behaviors and assistive services of robots, according to the specific assistive context and needs of a person is crucial to improve the efficacy in users support and hence acceptance. The authors rely on some recent results concerning the realization of a cognitive control approach for assistive robots supporting the synthesis of personalized and flexible assistive behaviors. This paper takes into account a general rehabilitation scenario and presents some initial steps toward the integration of perception, knowledge representation and planning capabilities to pursue flexibility, adaptation and personalization of assistive robot behaviors.

Timeline-based Planning and Scheduling (P&S) usually deals with two main sources of uncertainty: some components may depend on an external environment and cannot be planned; there may be tasks whose duration cannot be exactly foreseen in advance. Such uncertainties are formally defined and consequent controllability issues have been addressed, focusing on dynamic controllability. In this work, we present a new software prototype, tiga2exec, for dynamic controllable execution of timeline-based plans leveraging recent results gathered from the integration of P&S and Model Checking techniques. tiga2exec is deployed in a timeline-based planning system to control plan execution guaranteeing dynamic controllability. A preliminary experimental evaluation is also presented.

Socially assistive robotics aims at providing users with continuous support and personalized assistance, through appropriate social interactions. The design of robots capable of supporting people in heterogeneous tasks, raises several challenges among which the most relevant are the need to realise intelligent and continuous behaviours, robustness and flexibility of services and, furthermore, the ability to adapt to different contexts and needs. Artificial intelligence plays a key role in realizing cognitive capabilities like e.g., learning, context reasoning or planning that are highly needed in socially assistive robots. The integration of several of such capabilities is an open problem. This paper proposes a novel "cognitive approach" integrating ontology-based knowledge reasoning, automated planning and execution technologies. The core idea is to endow assistive robots with intelligent features in order to reason at different levels of abstraction, understand specific health-related needs and decide how to act in order to perform personalized assistive tasks. The paper presents such a cognitive approach pointing out the contribution of different knowledge contexts and perspectives, presents detailed functioning traces to show adaptation and personalization features, and finally discusses an experimental assessment proving the feasibility of the approach.

Technology supported assistance is a research area dedicated to support both older adults and, at some level, their caregivers in a variety of situations and contexts. A number of projects doing detailed evaluation both with robots and/or ICT-based intelligent devices have identified as open challenges the need to guarantee both continuity and variability of service according to context interpretation. This paper starts from the willingness to study how both continuity and variability can be pursued by leveraging and integrating results from research areas like artificial intelligence (AI), cognitive systems, psychology and sensor networks. Some of these technological skills are needed for example by an assistive robot and still represent open challenges in AI. This paper presents a medium term research initiative aiming at synthesizing an enhanced (intelligent) control architecture for assistive robots that take advantage from the continuous flow of information provided by a sensor network. The paper presents two main results: (a) starting from the analysis of requirements coming from the real world, it envisages a conceptual cognitive architecture highlighting the functional requirements and the key capabilities characterizing an "ideal" intelligent assistive robot; (b) it presents a prototype of a testbed architecture called KOaLa (Knowledge-based cOntinuous Loop) which integrates sensor data representation, knowledge reasoning and decision making capabilities showing its novelty in a realistic scenario.

Background: Mild cognitive impairment and mild dementia progressively compromise the ability of people to live independently and can have a negative impact on their quality of life. Within the current European Active and Assisted Living programme (AAL), project TV-AssistDem has been developed to deliver a TV-based platform service to support patients with mild cognitive impairment or mild dementia and provide relief to their caregivers. The application is intended to be used daily at home, mainly by the participants themselves, with the help of their informal caregivers. The aim of this study is to evaluate the effectiveness of TV-AssistDem to improve quality of life in people with mild cognitive impairment or mild dementia. Methods: This is a 12-month European multicentre randomized controlled trial which will be performed in two countries: Spain and Romania. Two hundred and forty older adults will be recruited using identical inclusion/exclusion criteria. The primary outcome will be the change from baseline of TV-AssistDem on patient quality of life at 12 months. The secondary outcomes will be the changes from baseline of: 1) informal caregiver quality of life, 2) informal caregiver burden, 3) patient treatment adherence, 4) patient treatment compliance, 5) patient functional status, and 6) healthcare cost-effectiveness at 12 months. Patients in the intervention group will have access to an interactive platform which offers remote assistive services through a device connected to the television. The core services of the platform are: 1) Calendar and reminders, 2) Health monitoring and data transmission to a health server and 3) Videoconference; service-oriented applications are: 4) Cognitive stimulation; 5) Reminiscences; and 6) Patient and caregiver healthcare education. The analysis will be made following an intention-to-treat procedure. Linear and Generalized Mixed Model analysis will be performed. Discussion: We hypothesize that the regular use of TV-AssistDem will result in an improvement in patient quality of life. The uniqueness of this home TV-based intervention lies on its widespread accessibility and its integrative approach to quality of life in people with mild cognitive impairment or mild dementia and their informal caregivers. However, several anticipated challenges will need to be faced: poor engagement and connectivity problems. Trial registration: ClinicalTrials.gov Identifier NCT03653234, Date of registration: 31 August 2018.

This paper presents a newborn collaboration between heterogeneous AI competences. In particular, it describes current work on the integration of machine learning techniques for the automatic generation of contents for an Intelligent Tutoring System grounded on automated planning techniques. The joint use of these two approaches allows on the one hand to facilitate the task of instructional designers in defining and preparing courses, and on the other hand to dynamically support the use of content according to different users context.

The increasing dynamism of contemporary society poses some challenges also to current learning processes that could benefit from new methods based upon intelligent technologies. The use of technology, in this context, can be an enabling factor. The Intelligent Tutoring Systems (ITS), for example, are systems that, despite some limitations (for example, lack of dynamic adaptability and reduced innovation compared to classical learning environments), are able to support the acquisition of knowledge by their users through the use of modern Information and Communication Technologies. The experience of the authors in the field of education, coming from the development of crisis management training systems, has been renewed and enriched over the years, arriving to a new generation of ITSs. This latter one is able to support the dynamic adaptation of the lessons and to bring the educational processes out of the classrooms, overcoming the original limitations of the ITSs and pursuing the idea of a continuous learning both in time and in space.

Modern automation systems are asked to provide a step change toward flexibility and reconfigurability to cope with increasing demand for fast changing and highly fragmented production--which is more and more characterising the manufacturing sector. This reflects in the transition from traditional hierarchical and centralised control architecture to adaptive distributed control systems, being the latter capable of exploiting also knowledge-based strategies toward collaborating behaviours. The chapter intends to investigate such topics, by outlining major challenges and proposing a possible approach toward their solution, founded on autonomous, self-declaring, knowledge-based and heterarchically collaborating control modules. The benefits of the proposed approach are discussed and demonstrated in the field of re-manufacturing of electronic components, with specific reference to a pilot plant for the integrated End-Of-Life management of mechatronic products.

This paper presents a novel comprehensive framework called ROS-TiPlEx (Timeline-based Planning and Execution with ROS) to provide a shared environment in which experts in robotics and planning can easily interact to, respectively, encode information about low-level robot control and define task planning and execution models. ROS-TiPlEx aims at facilitating the interaction between both kind of experts, thus, enhancing and possibly speeding up the process of an integrated control design. ROS-TiPlEx is the first tool addressing the connection of ROS and timeline-based planning.