Generative artificial intelligence opens new opportunities for accessibility validation. An interesting case is the assessment of alternative text (alt-text) for images. This paper investigates the use of a large language model (LLM) to analyse alt-texts in real e-commerce websites, a domain in which images play an important role and have specific requirements. We present a novel data-driven method and an associated tool that employs tailored prompting strategies to incorporate contextual information when generating and evaluating image descriptions. The approach also supports systematic comparison between human-authored and LLM-generated alt-text. We conducted a user study (N = 16) involving 494 assessments of 157 images, and their corresponding alt-texts extracted from real e-commerce websites. The results show that the proposed solution can provide valid results, supporting its possible integration into existing accessibility validation workflows and authoring tools.

Most countries are ageing rapidly, creating significant challenges in providing adequate care to elderly population. Older adults’ care centers face several difficulties in ensuring support able to address their diverse needs, due to several factors including increasing caregiver shortages, high variability in cognitive and health conditions of elderly, and challenges in delivering personalized interventions to them. Additionally, maintaining elderly engagement during cognitive training is often problematic due to the repetitive and impersonal nature of involved tasks. To address these limitations, we carried out a study investigating the use of a humanoid robot to deliver interactive, personalised serious games based on older adults' personal memories, to enhance relevance and engagement for them. The approach has been evaluated in a trial conducted in a center for older adults, involving users with varying cognitive abilities. Results indicated that such personalised games were well received by them, with a positive impact on their experience.

The use of humanoid robots in older adult training has recently started to be considered. We investigated a solution that offers serious games personalised to each individual, to stimulate more interest and participation in cognitive training. In particular, we have studied how to consider personal memories in customising humanoid robot games for Mild Cognitive Impaired (MCI) older adults. For this goal, a prototype platform for collecting and exploiting personal memories in associated games is presented. The memories are exploited by six games designed and implemented in a Pepper robot considering current practices. We report on a mixed-method study consisting of a two-phase trial that involved 15 MCI older adults. The participants first furnished some memories from their past, and then used two game versions regularly for twelve weeks, one personalised and one with general content. We collected both quantitative (through questionnaires and interaction log analysis) and qualitative feedback. The results provide useful information about the robot games’ impact on users and, more generally, for understanding how to introduce robot games based on personal memories in cognitive training programmes.

The "Robots for Humans" (RfH) workshop bridges the Human-Computer Interaction (HCI) and Human-Robot Interaction (HRI) communities. The workshop encourages methodological exchange and explores theoretical, technical and design solutions in robotics. Join us to explore the intricate bond between humans and robots for thoughtful HRI advancements.

Cognitive developmental disorders are common in children and can affect various abilities. Attention Deficit/Hyperactivity Disorder (ADHD) is the most prevalent childhood psychiatric condition. This work presents PlayToPickUp, a serious game that aims to stimulate children in relevant cognitive domains (attention and error monitoring). A multidisciplinary team of experts and caregivers from two different centers that support therapeutic activities with such children participated from the games’s inception to the design and the evaluation of the game. Depending on the characteristics and abilities of the player, therapists can customize the game to provide training that best fits the skills and the needs of the child while maintaining the player’s motivation. After its development, the game was used over 2 months “in the wild” by children recruited by the two centers. In one case the children played with it within the regular activities offered by the training center. In the other one, the parents of the children were instructed by caregivers to have the children play the game at home. In the paper, we describe the experience gathered from such two studies run in parallel, discussing the aspects that worked better, those that represented difficulties, and the lesson learnt for future studies.

In the last few years, several end-user tools have been designed to help people who are not professional developers in programming their smart environments. However, such tools are often based on structured visual editors providing abstract representations of the available connected sensors and objects, which can be problematic for end users, and do not particularly encourage their participation. This work aims to make the end-user experience of creating everyday automations involving various types of connected sensors and objects more engaging by replacing extensive, static, structured and comprehensive abstract visual tools with more narrowed, relevant, context-sensitive, dynamic, augmented reality-based representations. We present a solution for this purpose that mobile users can exploit through their smartphone. End users can use the smartphone camera to frame the relevant sensor or object through the developed prototype, then get the current automations associated with it, edit their definition, create new ones as well as monitor the automations involving the whole current environment. We also report a first user test of the developed prototype deployed in a home equipped with connected sensors and objects, which yielded positive feedback.

Oral health care can be a challenging experience for children with autism, for their parents and for dentists. Recently, some technology-enhanced systems have been proposed to help people with autism to cope with distressing situations originated by unknown social-life contexts, such as dental care settings with intense sound-visual stimulations. Results were positive in mitigating anxiety at the dental clinic but seem to fail in supporting proper oral hygiene at home. Thanks to the increasing spread of household Intelligent Personal Assistants (IPA) and Vocal Conversational Agents (VCAs), we envisage new opportunities considering the Voice-enabled IPAs not only as support on daily activities but also to enrich and simplify access to healthcare procedures from home. This work attempts to extend the use of technology-enhanced systems for dental care by exploiting the potential of the Vocal User Interface, Amazon Alexa, as an instructional agent with children on the spectrum. To this purpose, we developed a personalized Alexa Skill with two different functionalities: (i) support the child during the routine transition toward the target activity: move to the bathroom to brush their teeth; (ii) act as a persuader and a timer to guide the child during the procedure observing the proper brushing time. We conducted a three-week preliminary study with three children of different autistic profiles. The goal was to collect opportunities and issues deriving from the device introduction in the home context and test the device usage to favour dental care. Results and feedback were encouraging and gave insights to improve this approach.

This work aims to explore the potentialities of an end-user personalisation platform in industrial settings. In such a context, stakeholders with different roles and competencies collaborate to manage and control an environment where legacy machines coexist and interact with newer ones. Our goal is to provide a rule-based tool that allows end-users to build personalised solutions to respond quickly to the dynamic needs of factories. We report on a case study in the paper factory domain, in which the industrial aspects identified with expert stakeholders through interviews have been simulated and addressed through an extension of a personalisation platform. A first user test of the resulting environment has been carried out with a representative set of users, and has provided useful and encouraging feedback in terms of the potentialities of the proposed approach in industrial contexts.

In this paper, we present the design and the implementation of a cooking game for older adults interacting through a humanoid robot. We discuss the motivations and the requirements that have driven such design and indicate how it has been implemented. The main goal is to stimulate the cognitive resources of older adults in order to limit their decline. For this purpose, we have exploited the multimodal possibilities of the humanoid robot and have identified two robot personalities, which are suitable to improve users' engagement, and thus their potential participation in cognitive training programmes.

Automatic support for web accessibility validation needs to evolve for several reasons. The increasingly recognised importance of accessibility implies that various stakeholders, with different expertise, look at it from different viewpoints and have different requirements regarding the types of outputs they expect. The technologies used to support Web application access are evolving along with the associated accessibility guidelines. We present a novel tool that aims to provide flexible and open support for addressing such issues. We describe the design of its main features, including support for recent guidelines and tailored results presentations, and report on first technical and empirical validations that have provided positive feedback.

In the coming years humanoid robots will be increasingly used in a variety of contexts, thereby presenting many opportunities to exploit their capabilities in terms of what they can sense and do. One main challenge is to design technologies that enable those who are not programming experts to personalize robot behaviour. We propose an end user development solution based on trigger-action personalization rules. We describe how it supports editing such rules and its underlying software architecture, and report on a user test that involved end user developers. The test results show that users were able to perform the robot personalization tasks with limited effort, and found the trigger-action environment usable and suitable for the proposed tasks. Overall, we show the potential for using trigger-action programming to make robot behaviour personalization possible even to people who are not professional software developers.

Remote monitoring services should be strongly personalised to the specific needs, preferences, abilities and motivations of elderly, a population segment whose characteristics can largely vary and even dynamically evolve over time for the same individual, depending on changing needs and usage contexts. We present a demo showing how a platform supporting End User Development (EUD) of context-dependent applications has been customized for remotely assisting elderly people at home. The user-editable personalisation features are specified by using trigger-action rules. The platform has been integrated with various sensors and appliances, and an application for remotely monitoring older adults at home. The resulting environment supports the possibility of creating trigger-action rules that can actually be executed when relevant sensors indicate that specific events or conditions occurred.

With today's technology, elderly can be supported in living independently in their own homes for a prolonged period of time. Monitoring and analyzing their behavior in order to find possible unusual situation helps to provide the elderly with health warnings at the proper time. Current studies are focusing on the elderly daily activity and the detection of anomalous behaviors aiming to provide the older people with remote support. To this aim, we propose a real-time solution which models the user daily routine using a task model specification and detects relevant contextual events occurred in their life through a context manager. In addition, by a systematic validation through a system that automatically generates wrong sequences of tasks, we show that our algorithm is able to find behavioral deviations from the expected behavior at different times by considering the extended classification of the possible deviations with good accuracy.

Our life is characterized by the presence of a multitude of interactive devices and smart objects exploited for disparate goals in different contexts of use. Thus, it is impossible for application developers to predict at design time the devices and objects users will exploit, how they will be arranged, and in which situations and for which objectives they will be used. For such reasons, it is important to make end users able to easily and autonomously personalize the behaviour of their Internet of Things applications, so that they can better comply with their specific expectations. In this paper, we present a method and a set of tools that allow end users without programming experience to customize the context-dependent behaviour of their Web applications through the specification of trigger-action rules. The environment is able to support end-user specification of more flexible behaviour than what can be done with existing commercial tools, and it also includes an underlying infrastructure able to detect the possible contextual changes in order to achieve the desired behaviour. The resulting set of tools is able to support the dynamic creation and execution of personalized application versions more suitable for users’ needs in specific contexts of use. Thus, it represents a contribution to obtaining low threshold/high ceiling environments. We also report on an example application in the home automation domain, and a user study that has provided useful positive feedback.

Current authoring environments provide the possibility of developing user interfaces with limited adaptation capacities. The most widely adopted tools follow the responsive design approach and allow developers to obtain user interfaces that can adapt mainly to the screen size and orientation. We present a solution able to support development of user interfaces able to adapt to the various types of contextual events (that can be related to users, devices, environments, and social relationships), with the added possibility of distributing the user interface elements across multiple devices. The context-dependent behavior is modelled through trigger / action rules, and can even be applied to Web applications that were not originally designed to be context-aware. This paper describes the design and main features of the novel authoring environment and reports on a first user study.