Introduction: This article describes an enhanced telepresence robot named ROBIN, part of a telecare system derived from the GIRAFFPLUS project for supporting and monitoring older adults at home. ROBIN is integrated in a sensor-rich environment that aims to continuously monitor physical and psychological wellbeing of older persons living alone. The caregivers (formal/informal) can communicate through it with their assisted persons. Long-term trials in real houses highlighted several user requirements that inspired improvements on the robotic platform. The enhanced telepresence robot was assessed by users to test its suitability to support social interaction and provide motivational feedback on health-related aspects. Methods: Twenty-five users (n = 25) assessed the new multimodal interaction capabilities and new communication services. A psychophysiological approach was adopted to investigate aspects like engagement, usability, and affective impact, as well as the possible role of individual differences on the quality of human-robot interaction. Results: ROBIN was overall judged usable, the interaction with/through it resulted pleasant and the required workload was limited, thus supporting the idea of using it as a central component for remote assistance and social participation. Open-minded users tended to have a more positive interaction with it. Conclusions: This work describes an enabling technology for remote assistance and social communication. It highlights the importance of being compliant with users' needs to develop solutions easy to use and able to foster their social connections. The role of personality appeared to be relevant for the interaction, underscoring a clear role of the service personalization.

The development of a Social Intelligence System based on artificial intelligence is one of the cutting edge technologies in Assistive Robotics. Such systems need to create an empathic interaction with the users; therefore, it os required to include an Emotion Recognition (ER) framework which has to run, in near real-time, together with several other intelligent services. Most of the low-cost commercial robots, however, although more accessible by users and healthcare facilities, have to balance costs and effectiveness, resulting in under-performing hardware in terms of memory and processing unit. This aspect makes the design of the systems challenging, requiring a trade-off between the accuracy and the complexity of the adopted models. This paper proposes a compact and robust service for Assistive Robotics, called Lightweight EMotion recognitiON (LEMON), which uses image processing, Computer Vision and Deep Learning (DL) algorithms to recognize facial expressions. Specifically, the proposed DL model is based on Residual Convolutional Neural Networks with the combination of Dilated and Standard Convolution Layers. The first remarkable result is the few numbers (i.e., 1.6 Million) of parameters characterizing our model. In addition, Dilated Convolutions expand receptive fields exponentially with preserving resolution, less computation and memory cost to recognize the distinction among facial expressions by capturing the displacement of the pixels. Finally, to reduce the dying ReLU problem and improve the stability of the model, we apply an Exponential Linear Unit (ELU) activation function in the initial layers of the model. We have performed training and evaluation (via one- and five-fold cross validation) of the model with five datasets available in the community and one mixed dataset created by taking samples from all of them. With respect to the other approaches, our model achieves comparable results with a significant reduction in terms of the number of parameters.

One of the main challenges of social robots concerns the ability to guarantee robust, contextualized and intelligent behavior capable of supporting continuous and personalized interaction with different users over time. This implies that robot behaviors should consider the specificity of a person (e.g., personality, preferences, assistive needs), the social context as well as the dynamics of the interaction. Ideally, robots should have a “mind" to properly interact in real social environments allowing them to continuously adapt and exhibit engaging behaviors. The authors’ long-term research goal is to create an advanced mind-inspired system capable of supporting multiple assistance scenarios fostering personalization of robot’s behavior. This article introduces the idea of a dual process-inspired cognitive architecture that integrates two reasoning layers working on different time scales and making decisions over different temporal horizons. The general goal is also to support an empathetic relationship with the user through a multi-modal interaction inclusive of verbal and non-verbal expressions based on the emotional-cognitive profile of the person. The architecture is exemplified on a cognitive stimulation domain where some experiments show personalization capabilities of the approach as well as the joint work of the two layers. In particular, a feasibility assessment shows the customization of robot behaviors and the adaptation of robot interactions to the online detected state of a user. Usability sessions were performed in laboratory settings involving 10 healthy participants to assess the user interaction and the robot’s dialogue performance.

This paper describes a novel architecture that aims to create a template for the implementation of an IT platform, supporting the deployment and integration of the different digital twin subsystems that compose a complex urban intelligence system. In more detail, the proposed Smart City IT architecture has the following main purposes: (i) facilitating the deployment of the subsystems in a cloud environment; (ii) effectively storing, integrating, managing, and sharing the huge amount of heterogeneous data acquired and produced by each subsystem, using a data lake; (iii) supporting data exchange and sharing; (iv) managing and executing workflows, to automatically coordinate and run processes; and (v) to provide and visualize the required information. A prototype of the proposed IT solution was implemented leveraging open-source frameworks and technologies, to test its functionalities and performance. The results of the tests performed in real-world settings confirmed that the proposed architecture could efficiently and easily support the deployment and integration of heterogeneous subsystems, allowing them to share and integrate their data and to select, extract, and visualize the information required by a user, as well as promoting the integration with other external systems, and defining and executing workflows to orchestrate the various subsystems involved in complex analyses and processes.

The digital twin (DT) paradigm provides a purpose-built digital representation of a physical system. DTs are often composed by several interconnected models, which need to be specifically tailored to fit the DT purposes. The objective of this work is the development of an urban digital twin (UDT) for the city of Matera, following urban intelligence (UI) paradigm. The latter leverages the multi-disciplinary integration and optimization of the city systems and subsystems to develop purpose-driven DTs and support the decision-making process. The UDT is intended to support governance, stakeholders, and citizens, integrating morphological data for the city representation, reliable simulation tools and data-driven methods for the city state prediction (e.g., traffic, solar irradiation), optimization algorithms for planning and emergency response, sensors for vehicle and pedestrian traffic volumes and environmental monitoring (e.g., pollutant distributions), and a participatory data collection process from the citizens. A Data Lake is used to make available to the UDT modules the data produced by the morphological representation, simulations/data-driven methods, sensors, and the participatory data. The Data Lake provides a standardized approach for the aggregation and extraction of information. Finally, an Urban Sensing Engine supports the decision-making process with artificial intelligence forms of reasoning, to effectively combine the information produced by the UDT components.