Wenge Xu, Foroogh Hajiseyedjavadi, Kurtis Weir
et al.
External Human-Machine Interfaces (eHMIs) have been proposed to facilitate communication between Automated Vehicles (AVs) and pedestrians. However, no attention was given to Deaf and Hard-of-Hearing (DHH) people. We conducted a formative study through focus groups with 6 DHH people and 6 key stakeholders (including researchers, assistive technologists, and automotive interface designers) to compare proposed eHMIs and extract key design requirements. Subsequently, we investigated the effects of visual and auditory eHMI in a virtual reality user study with 32 participants (16 DHH). Results from our scenario suggesting that (1) DHH participants spent more time looking at the AV; (2) both visual and auditory eHMIs enhanced trust, usefulness, and perceived safety; and (3) only visual eHMIs reduced the time to step into the road, time looking at the AV, gaze time, and percentage looking at active visual eHMI components. Lastly, we provided five practical implications for making eHMI inclusive of DHH people.
Cultural heritage treasures are precious communal assets that show the past human legacy. It depicts present and future way of life as well as cultural values of a society, and enhances solidarity and social integration of communities. This study is designed to investigate the practices and challenges of cultural heritage conservations in North Shoa Zone, Central Ethiopia. The research employed a mixed research approach and cross-sectional descriptive and explanatory research design. The researchers applied multiple data gathering instruments including questionnaire survey, interview, focus group discussion and observation. Concerning sampling techniques, systematic random sampling technique was applied to select samples from local communities, and purposive sampling was designed to choose interviewees from government authorities, and culture and tourism office experts of North Shoa Zone and respective districts. The actual and valid sample size of the study is 236. The findings of the study revealed that the cultural heritage properties in North Shoa are not safeguarded from being damaged and found in a poor status of conservation. The major conclusion sketched from the study is that the principal factors affecting heritage conservation are lack of proper management, monitoring and evaluation, lack of funds and stakeholder involvement, urbanization, settlement programs and agricultural practice, poor government concern and professional commitment, poor attitude towards cultural heritage and low level of community concern, vandalism and illicit trafficking, low promotions of cultural heritage, and natural catastrophes such as invasive intervention, climate change (humidity and frost, excessive rainfall and flood, heat from the sun). The study implied that the sustainability of cultural heritage in the study area are endanger unless conservation practice is supported by conservation guidelines, heritage site management plans and research outputs, stakeholders’ integration, and community involvement. Most importantly, the study recommends the integration of heritage conservation and sustainable development, and the promotion of conservation is a way of achieving economic and social sustainability.
Healthcare access and equity are human rights. Worldwide conflicts, violence, and persecution have increased the number of people from refugee or refugee-like backgrounds. Because urban areas are already densely populated, governments have aimed to increase refugee resettlement in rural and/or regional areas. Because of the complex healthcare needs of refugees, this creates challenges for healthcare service providers. Identifying barriers to accessing healthcare in rural areas is therefore important to better inform policy settings and programmes that will provide culturally appropriate patient-centred care to the refugee community. This review scoped 22 papers written in English between 2018 and July 2023 from five countries (Australia, New Zealand, Germany, Bangladesh, and Lebanon) in order to provide an overview of the barriers and possible solutions to facilitate refugees’ access to healthcare. The reviewed literature summarised the perceptions of at least 3,561 different refugees and 259 rural health service providers and/or administrators and identified major challenges. These include communication (illiteracy in the resettlement country language and lack of a suitable interpreter), lack of cultural awareness of health services, discrimination, and access difficulties (transportation, availability of health specialist services, cost). As a consequence, it was identified that improving access to affordable housing, employment through credential recognition, competence-level education for children, facilitating language training, and adapting health information would increase resettlement and encourage access to healthcare. Refugees face significant barriers to accessing and engaging with healthcare services. This impacts their integration into rural communities and increases the prevalence of psychosocial issues like feelings of loneliness, low self-esteem, a lack of autonomy, and a lack of empowerment over informed decision-making, especially for women, jobless men, and the elderly. These findings support the need for additional support for refugees and healthcare providers to improve language proficiency and cultural competency. Policymakers need to improve the availability and accessibility of employment, housing accessibility, and service mobility. Additionally, more research is needed to assess the efficacy of emerging innovative programmes that aim to close the gap by delivering culturally appropriate patient-centred care to refugee communities in rural areas.
Abdul Aziz Jaziri, Awang Tri Satria, Rahmi Nurdiani
et al.
Community empowerment plays an important role in strengthening local economic resilience, particularly in coastal areas where fisheries are the main livelihood. In Konang Village, Lamongan, abundant aquaculture production, especially milkfish and tilapia, often faces declining prices during peak harvest seasons, leading to economic vulnerability. To address this issue, a Community Partnership Program (PKM) was implemented with the objective of enhancing the capacity of the Pertiwi Sukses Bersama community group through fish cracker processing technology. The program applied a participatory and collaborative approach, consisting of five stages: socialization, training and capacity building, technology application, mentoring and evaluation, and sustainability planning. Training modules included fish cracker production, food safety and legality (Business Identification Number/NIB, PIRT, and halal certification), as well as digital marketing using e-commerce platforms. The results showed significant improvement in participants’ knowledge and skills, reflected in post-test scores that increased from 44 to 82 on average. The group successfully acquired an NIB, initiated the process of halal and PIRT certification, and practiced digital marketing strategies. In addition, the community product was branded as “Kerupuk Ikan Bengawan” to strengthen identity and competitiveness. These achievements demonstrate that structured empowerment programs can foster sustainable fisheries-based enterprises, support the blue economy, and contribute to rural economic resilience.
Yi Li, Francesco Chiossi, Helena Anna Frijns
et al.
As autonomous agents, from self-driving cars to virtual assistants, become increasingly present in everyday life, safe and effective collaboration depends on human understanding of agents' intentions. Current intent communication approaches are often rigid, agent-specific, and narrowly scoped, limiting their adaptability across tasks, environments, and user preferences. A key gap remains: existing models of what to communicate are rarely linked to systematic choices of how and when to communicate, preventing the development of generalizable, multi-modal strategies. In this paper, we introduce a multidimensional design space for intent communication structured along three dimensions: Transparency (what is communicated), Abstraction (when), and Modality (how). We apply this design space to three distinct human-agent collaboration scenarios: (a) bystander interaction, (b) cooperative tasks, and (c) shared control, demonstrating its capacity to generate adaptable, scalable, and cross-domain communication strategies. By bridging the gap between intent content and communication implementation, our design space provides a foundation for designing safer, more intuitive, and more transferable agent-human interactions.
Parag Khanna, Andreas Naoum, Elmira Yadollahi
et al.
This work presents REFLEX: Robotic Explanations to FaiLures and Human EXpressions, a comprehensive multimodal dataset capturing human reactions to robot failures and subsequent explanations in collaborative settings. It aims to facilitate research into human-robot interaction dynamics, addressing the need to study reactions to both initial failures and explanations, as well as the evolution of these reactions in long-term interactions. By providing rich, annotated data on human responses to different types of failures, explanation levels, and explanation varying strategies, the dataset contributes to the development of more robust, adaptive, and satisfying robotic systems capable of maintaining positive relationships with human collaborators, even during challenges like repeated failures.
Human-AI collaborative tools attract attentions from the data storytelling community to lower the expertise barrier and streamline the workflow. The recent advance in large-scale generative AI techniques, e.g., large language models (LLMs) and text-to-image models, has the potential to enhance data storytelling with their power in visual and narration generation. After two years since these techniques were publicly available, it is important to reflect our progress of applying them and have an outlook for future opportunities. To achieve the goal, we compare the collaboration patterns of the latest tools with those of earlier ones using a dedicated framework for understanding human-AI collaboration in data storytelling. Through comparison, we identify consistently widely studied patterns, e.g., human-creator + AI-assistant, and newly explored or emerging ones, e.g., AI-creator + human-reviewer. The benefits of these AI techniques and implications to human-AI collaboration are also revealed. We further propose future directions to hopefully ignite innovations.
M. Marconcini, Annekatrin Metz- Marconcini, T. Esch
et al.
To improve the understanding of current trends in global urbanisation, we have launched the World Settlement Footprint (WSF) suite, a collection of novel datasets aimed at providing accurate, reliable and frequent information on the location and extent of human settlements, as well as on their morphology and built-up density. In this paper, we present three of its products (i.e., the WSF-Evolution, WSF2019 and WSF3D), which are expected to become an asset for national statistical offices, local authorities, academia, civil society, private sector, geospatial information community, as well as international organisations involved in the implementation of the Sustainable Development Goal 11 of the United Nations and the New Urban Agenda.
Tiago Rodrigues de Almeida, Tim Schreiter, Andrey Rudenko
et al.
Accurate human activity and trajectory prediction are crucial for ensuring safe and reliable human-robot interactions in dynamic environments, such as industrial settings, with mobile robots. Datasets with fine-grained action labels for moving people in industrial environments with mobile robots are scarce, as most existing datasets focus on social navigation in public spaces. This paper introduces the THÖR-MAGNI Act dataset, a substantial extension of the THÖR-MAGNI dataset, which captures participant movements alongside robots in diverse semantic and spatial contexts. THÖR-MAGNI Act provides 8.3 hours of manually labeled participant actions derived from egocentric videos recorded via eye-tracking glasses. These actions, aligned with the provided THÖR-MAGNI motion cues, follow a long-tailed distribution with diversified acceleration, velocity, and navigation distance profiles. We demonstrate the utility of THÖR-MAGNI Act for two tasks: action-conditioned trajectory prediction and joint action and trajectory prediction. We propose two efficient transformer-based models that outperform the baselines to address these tasks. These results underscore the potential of THÖR-MAGNI Act to develop predictive models for enhanced human-robot interaction in complex environments.
AI is not only a neutral tool in team settings; it influence the social and cognitive fabric of collaboration. Across two randomized experiments, we demonstrate that AI exposure produces causal spillover into human-human interaction -- affecting shared language, collective attention, shared mental models, and social cohesion. These spillover effects occur robustly across settings, modalities, tasks, and AI qualities, suggesting that mere exposure to AI drives the influence. AI functions as an implicit ``social forcefield,'' influencing not only how people speak, but also how they think, what they attend to, and how they relate to each other. We argue for shifting the design paradigm from optimizing ``AI as a tool'' to understanding AI as a socially influential actor whose effects extend beyond the human-AI interface.
Land use/land cover (LULC) dynamics and the resulting changes in ecosystems, as well as the services they provide, are a consequence of human activities and environmental drivers, such as invasive alien plant species. This study assessed the changes in LULC and ecosystem service values (ESVs) in the Afar National Regional State, Ethiopia, which experiences a rapid invasion by the alien tree Prosopis juliflora (Swartz DC). Landsat satellite data of 1986, 2000 and 2017 were used in Random Forest algorithm to assess LULC changes in the last 31 years, to calculate net changes for different LULC types and the associated changes in ESVs. Kappa accuracies of 88% and higher were obtained for the three LULC classifications. Post-classification change analyses for the period between 1986 and 2017 revealed a positive net change for Prosopis invaded areas, cropland, salt flats, settlements and waterbodies. The rate of Prosopis invasion was estimated at 31,127 ha per year. Negative net changes were found for grassland, bareland, bush-shrub-woodland, and natural forests. According to the local community representatives, the four most important drivers of LULC dynamics were climate change, frequent droughts, invasive species and weak traditional law. Based on two different ESVs estimations, the ecosystem changes caused by LULC changes resulted in an average loss of ESVs in the study area of about US$ 602 million (range US$ 112 to 1091 million) over the last 31 years. With an increase in area by 965,000 ha, Prosopis-invaded land was the highest net change during the study period, followed by grassland (-599,000 ha), bareland (-329,000 ha) and bush-shrub-woodland (-327,000 ha). Our study provides evidence that LULC changes in the Afar Region have led to a significant loss in ESVs, with serious consequences for the livelihoods of the rural people.
Rafael Ricardo Rentería Ramos, Alicia María Vitale Alfonso
Se presenta un modelo basado en agentes para estudiar el comportamiento migratorio del departamento de Risaralda, Colombia. Para su construcción se consideraron tres elementos fundamentales en la dinámica poblacional: la toma de decisión de migrar, con el desarrollo de un modelo bayesiano; el componente de atracción, a través de un modelo gravitacional; y la aplicación del enfoque minimalista usando modelos basados en agentes en estudios de la migración por decisión. Los resultados evidencian que la dinámica migratoria del departamento tiene rutas con alta concentración de capital social, que condicionan el arribo y la expulsión poblacional, modificando su estructura.
Human settlements. Communities, Demography. Population. Vital events
In the recent shift towards human-centric AI, the need for machines to accurately use natural language has become increasingly important. While a common approach to achieve this is to train large language models, this method presents a form of learning misalignment where the model may not capture the underlying structure and reasoning humans employ in using natural language, potentially leading to unexpected or unreliable behavior. Emergent communication (Emecom) is a field of research that has seen a growing number of publications in recent years, aiming to develop artificial agents capable of using natural language in a way that goes beyond simple discriminative tasks and can effectively communicate and learn new concepts. In this review, we present Emecom under two aspects. Firstly, we delineate all the common proprieties we find across the literature and how they relate to human interactions. Secondly, we identify two subcategories and highlight their characteristics and open challenges. We encourage researchers to work together by demonstrating that different methods can be viewed as diverse solutions to a common problem and emphasize the importance of including diverse perspectives and expertise in the field. We believe a deeper understanding of human communication is crucial to developing machines that can accurately use natural language in human-machine interactions.
For social robots like Astro which interact with and adapt to the daily movements of users within the home, realistic simulation of human activity is needed for feature development and testing. This paper presents a framework for simulating daily human activity patterns in home environments at scale, supporting manual configurability of different personas or activity patterns, variation of activity timings, and testing on multiple home layouts. We introduce a method for specifying day-to-day variation in schedules and present a bidirectional constraint propagation algorithm for generating schedules from templates. We validate the expressive power of our framework through a use case scenario analysis and demonstrate that our method can be used to generate data closely resembling human behavior from three public datasets and a self-collected dataset. Our contribution supports systematic testing of social robot behaviors at scale, enables procedural generation of synthetic datasets of human movement in different households, and can help minimize bias in training data, leading to more robust and effective robots for home environments.
Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb
et al.
Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets ("slices") of data. This behavior can have significant societal consequences for the safety or bias of the model in deployment, but identifying these underperforming slices can be difficult in practice, especially in domains where practitioners lack access to group annotations to define coherent subsets of their data. Motivated by these challenges, ML researchers have developed new slice discovery algorithms that aim to group together coherent and high-error subsets of data. However, there has been little evaluation focused on whether these tools help humans form correct hypotheses about where (for which groups) their model underperforms. We conduct a controlled user study (N = 15) where we show 40 slices output by two state-of-the-art slice discovery algorithms to users, and ask them to form hypotheses about an object detection model. Our results provide positive evidence that these tools provide some benefit over a naive baseline, and also shed light on challenges faced by users during the hypothesis formation step. We conclude by discussing design opportunities for ML and HCI researchers. Our findings point to the importance of centering users when creating and evaluating new tools for slice discovery.
21st Century war is increasing in speed, with conventional forces combined with massed use of autonomous systems and human-machine integration. However, a significant challenge is how humans can ensure moral and legal responsibility for systems operating outside of normal temporal parameters. This chapter considers whether humans can stand outside of real time and authorise actions for autonomous systems by the prior establishment of a contract, for actions to occur in a future context particularly in faster than real time or in very slow operations where human consciousness and concentration could not remain well informed. The medical legal precdent found in 'advance care directives' suggests how the time-consuming, deliberative process required for accountability and responsibility of weapons systems may be achievable outside real time captured in an 'advance control driective' (ACD). The chapter proposes 'autonomy command' scaffolded and legitimised through the construction of ACD ahead of the deployment of autonomous systems.