Human-AI collaboration has evolved into a complex, multidimensional paradigm shaped by research in various domains. Key areas such as human-in-the-loop systems, Interactive Machine Learning (IML), Hybrid Intelligence, and Human-Agent Interaction have significantly contributed to this development. However, these fields often lack cohesion, underscoring the need for a cohesive perspective to advance. This work addresses this gap by integrating insights from diverse aspects of collaboration to present a holistic approach to fostering effective and adaptive interactions between humans and artificial agents. It emphasizes empowering end-users with greater control and involvement in decision-making processes, thereby enhancing both the levels of interactivity and adaptability within intelligent systems. Moving beyond a focus on AI training techniques, this paper presents a broader perspective on incorporating human input into AI decision-making and learning processes, highlighting the importance of flexibility in systems and user engagement. The manuscript proposes a framework encompassing five levels of human integration and examines their relationship with core collaboration aspects, including the system purpose, participant expertise, and system proactivity. By synthesizing current knowledge on human-AI collaboration and outlining essential design principles, this work aims to advance the field and foster interdisciplinary collaboration among researchers, practitioners, and designers.

This work addresses the task allocation problem in spatial crowdsensing with altruistic participation, tackling challenges like declining engagement and user fatigue from task overload. Unlike typical models relying on financial incentives, this context requires alternative strategies to sustain participation. This paper presents a new solution, the Volunteer Task Allocation Engine (VTAE), to address these challenges. This solution is not based on economic incentives, and it has two primary goals. The first one is to improve user experience by limiting the workload and creating a user-centric task allocation solution. The second goal is to create an equal distribution of tasks over the spatial locations to make the solution robust against the possible decrease in participation. Two approaches are used to test the performance of this solution against different conditions: computer simulations and a real-world experiment with real users, which include a qualitative evaluation. The simulations tested system performance in controlled environments, while the real-world experiment assessed the effectiveness and usability of the VTAE with real users. This research highlights the importance of user-centered design in citizen science applications with altruistic participation. The findings demonstrate that the VTAE algorithm ensures equitable task distribution across geographical areas while actively involving users in the decision-making process.

Air pollution is a major environmental and public health challenge, especially in urban areas where fine-grained air quality data are essential to effective interventions. Traditional monitoring networks, while accurate, often lack spatial resolution and public engagement. This study presents a novel wearable wireless sensor node (WSN) that was developed within the Horizon Europe SOCIO-BEE project to support air quality monitoring through citizen science (CS). The low-cost, body-mounted WSN measures NO₂, O₃, and PM_2.5. Three pilot campaigns were conducted in Ancona (Italy), Maroussi (Greece), and Zaragoza (Spain), and involved diverse user groups—seniors, commuters, and students, respectively. PM_2.5 sensor data were validated through two approaches: direct comparison with reference stations and spatial clustering analysis using K-means. The results show strong correlation with official PM_2.5 data (R² = 0.75), with an average absolute error of 0.54 µg/m³ and a statistical confidence interval of ±3.3 µg/m³. In Maroussi and Zaragoza, where no reference stations were available, the clustering approach yielded low intra-cluster coefficients of variation (CV = 0.50 ± 0.40 in Maroussi, CV = 0.28 ± 0.30 in Zaragoza), indicating that the measurements had high internal consistency and spatial homogeneity. Beyond technical validation, user engagement and perceptions were evaluated through pre-/post-campaign surveys. Across all pilots, over 70% of participants reported satisfaction with the system’s usability and inclusiveness. The findings demonstrate that wearable low-cost sensors, when supported by a structured engagement and data validation framework, can provide reliable, actionable air quality data, empowering citizens and informing evidence-based environmental policy.

The involvement of citizens and all stakeholders is crucial in tackling environmental and social matters. This, addressing equity and diversity issues, although challenging, is a necessary condition for achieving positive outcomes and ensuring that no one is left behind. To help ease this challenge, this work presents a systematic approach to ensure inclusive participation and leverage non-technical and technical elements to maximise stakeholder engagement in scientific activities to successfully address sustainability concerns. For that, it builds on the interim results of the H2020 SOCIO-BEE project, a Citizen science (CS) proposal to reduce air pollution through inclusive community engagement and social innovation. As part of an interdisciplinary CS project, an abductive systematic combining methodology was employed, which allowed for dialogue and collaboration between theory and practice throughout the whole process, during which separate groups of experts and potential end-users were involved. The article presents (i) the stakeholder engagement strategy codified in the SOCIO-BEE toolkit as a robust, actionable and inclusive foundation of engagement to CS activities; and (ii) the digital platform UX that allows setting up campaigns for measurements and assignment to citizens, incorporating the requirements for flexibility, accessibility, limited digital literacy, inclusion and legal and ethical considerations. Their combination and mutual interaction aim to leverage the pros of CS and technology whilst reducing their cons to ensure the four pillars of applicability, scalability, actionability, and inclusion. This is supported by the presented hybrid model which combines physical and virtual spaces and individual and collective action.

Despite the fact that nowadays there are many environmental monitoring stations in cities as well as different initiatives that provide open data on their measurements, there are gaps in terms of the availability and accuracy of these data. In many cases this information only gathers georeferenced data at static positions and in a number not significant enough to describe the diverse and dynamic environmental situations that can be found in an urban environment. The SOCIO-BEE initiative described in this article is not only a technological solution to obtain dynamic data from a larger geographical area, but its main objective is to involve citizens in this data collection, its exploitation and the taking of measures to help mitigate the environmental impact, all in a context of co-creation and citizen participation.