Socially assistive robotics (SAR) is getting a lot of attention for its potential in assisting elderly users. However, for robotic assistive applications to be effective, they need to satisfy the particular needs of each user and be well perceived. For this purpose, a personalization based on user’s characteristics such as personality and cognitive profile, and their dynamic changes is a crucial factor. Moreover, most of the existing solutions rely on the availability of specific technological infrastructures, generally requiring high economic investment, and that cannot be easily placed in different environments. Personalization and adaptation of assistive robotics applications to different user’s characteristics and needs, and even to different technological environments, are still not fully addressed in real environments. In the present work, the results of the UPA4SAR project are presented. The project aimed at providing a social robotic system to deliver assistive tasks for home care of patients with mild cognitive impairment in a personalized and adaptive way. We introduce the general architecture of the system and the developed robotic behaviors. Personalization and dynamic adaptation of assistive tasks are realized using a service-oriented approach by taking into account both user’s characteristics and environmental dynamic conditions. Field experimentation of the project was carried out with 7 patients, using the robotic system autonomously running in their homes for a total of 118 days. Results showed a reliable functioning of the proposed robotic system, a generally positive reaction, and a good acceptability rate from patients.

We performed a study to evaluate if the acceptance of a social humanoid robot used for monitoring the activities of elderly users with cognitive deficits increased after interacting with the robot. In addition, we evaluated if the robot’s acceptance is improved when the interaction with the robot occurred in different modalities modulated according to each user’s cognitive and personality profile. A group of 7 participants underwent assessment tools for cognitive and personality traits and for the level of acceptability of the robot. They interacted with the robot at their private home for a minimum of two weeks. The interaction with the robot occurred under two different modalities: standard modality where the robot performed tasks by approaching the subject at a fixed pre-defined frequency of interactions, and at fixed pre-defined times; modulated modality where the robot performed tasks by approaching the subject at different frequencies set according to some personality traits and cognitive profile of the user. The results showed no change in the acceptability level of the robot after direct interaction. Still, personality traits such as Neuroticism and Openness influenced the acceptability of the robot in the elderly only before an interaction. At the same time, these personality traits did not seem to influence the acceptability of the new technology after a direct interaction. Different is the case of cognitive profiles and demographic characteristics. Finally, the score on the pleasantness scale was higher when the interaction with the robot was set in modulated modality rather than standard modality. In conclusion, the identification of the personality traits and the cognitive status in the elderly with cognitive deficits seems to be useful to modulate the type and frequency of interaction of the robot with the user to increase the acceptability of the instrument and pleasures in every daily life.

The increasing popularity of cruise tourism has led to the need for effective planning and management strategies to enhance the city tour experience for cruise passengers. This paper presents a deep reinforcement learning (DRL)-based planner specifically designed to optimize city tours for cruise passengers. By leveraging the power of DRL, the proposed planner aims to maximize the number of visited attractions while considering constraints such as time availability, attraction capacities, and travel distances. The planner offers an intelligent and personalized approach to city tour planning, enhancing the overall satisfaction of cruise passengers and minimizing the negative impacts on the city’s infrastructure. An experimental evaluation was conducted considering Naples’s fourteen most attractive points of interest. Results show that, with 30 state variables and more than $19\ast {10}^{12}$ possible states to be explored, the DRL-based planner converges to an optimal solution after only 20,000 learning steps.

Internet is evolving from a network of computers and information into a network of services allowing applications to be built by selecting services and composing them in a loosely coupled manner. These Service Based Applications (SBA) are composed of a number of possibly independent services that are provided by many actors under different conditions (like price, time to deliver, and so on). Service provision conditions may change in time depending on provider policies or other environmental changes, so it is necessary to organize compositions of services on demand in response to dynamic requirements and circumstances. In this paper we propose to use a chemical computational model to address this problem by decoupling the process of finding services composing an SBA requested by a user, from their actual enactment. An SBA request is described in terms of an abstract workflow where only service functionalities of the single components and their execution order (i.e. the application control flow) are specified, along with parameters representing the conditions under which the user expects the application to be delivered. The proposed approach allows to model the process of instantiating the required functionalities with actual service implementations as an evolving and always running middleware mechanism that can take into account the current state of the context when the composition is required. Furthermore, the evolutionary nature of the chemical system provides a form of adaptation since once compositions of services are computed with the available services, new compositions can be computed as soon as new services become available or the conditions of existing ones change.