Interactions between emergency first responders (EFRs) and Generative Voice Agents (GVAs) are shaping the future of communication in crisis management operations and training. Key issues are the associated security, privacy and ethical concerns of centralized, proprietary, remote GVAs especially in critical tasks. Remote GVAs also impact response times and require high power consumption infrastructure. These characteristics hinder the usability of GVAs since earlier voice assistants. However, open-source, local GVAs provide secure and efficient alternatives, but no standardized process exists to build GVAs in line with EFR’s requirements. This study proposes a unified evaluation framework, EFR-GVA EvalKit, with metrics of regulatory compliance, technical specifications and performance tests inline with EFRs’ applications requirements that prioritize transparency, data sovereignty and usability. We then used the EFR-GVA EvalKit framework to assess and compare the design and development of local GVAs on consumer grade devices with a frontier remote conversational agent in a triage training 3D scenario. A user study (N=19) with EFRs showed the capacity of local GVAs to meet EFRs’ expectations. Compared to existing approaches, our contribution is more comprehensive and engineered for reuse. EFR–GVA EvalKit is introduced in this paper as a new, compliance-gated evaluation method and the triage scenario is its first instantiation and validation, demonstrating how the framework can be replicated across devices and tasks.

We compare four human–robot interaction configurations for semi-autonomous Unmanned Ground Vehicles (UGV) support in a simulated search-and-rescue task, organised along two orthogonal dimensions: Immersion (screen vs head-mounted display) and Viewpoint (exocentric/top-down vs egocentric/first-person). Thirty-six professional first responders and CBRN specialists completed the task using a 2D screen, a 3D screen, VR, or XR. 2D yielded the highest perceived explainability and self-rated performance; XR showed the lowest mean workload and a trend toward lower perceived difficulty (non-significant); VR increased negative effects (e.g., discomfort). Transparency significantly predicted trust, but with a counterintuitive negative coefficient, suggesting that uncalibrated disclosures can undermine perceived reliability. We report effect sizes and methodological details, discuss design implications for calibrating immersion and viewpoint to balance situational awareness, comfort, and trust in safety-critical operations.

In mobile technologies for health and well-being (mHealth), push notifications are a widely used tool to implement persuasive strategies. However, little research has been carried out to investigate the impact of notifications in such technologies and users' attitudes towards them. In this study, we address this gap by exploring the role of notifications and their customisation in the context of mobile applications that promote social, mental, or physical well-being. Based on observational data collected from 152 participants, we investigate users' attitudes and preferences towards notifications and explore how they differ along demographic dimensions. In addition, we then verified these results with behavioural measures and attitude ratings through a user study (N = 31), which saw participants interacting with a prototype of a mHealth application. Our findings show that customisation of notifications is a desired feature that can be used to improve the persuasive aspect of mHealth applications. Implications derived from our study can provide guidance for researchers and practitioners alike when designing app notifications to create better motivating, meaningful, and persuasive experiences.

The impact of COVID-19 has highlighted the importance of sports and physical activity for maintaining people’s mental well-being. In this domain, promising use cases for social robots have been identified. However, current research lacks a systematic approach for implementing, analyzing and understanding the contribution of robotic embodiment and proximity for persuasive and motivation technologies. In this work, we investigate how social robots could be used, in real-world training scenarios, to support trainers in conducting exercises while positively motivating trainees. Two use cases were designed to meet the needs of health and competitive oriented trainees. Qualitative and quantitative results from a field study show positive effects of the robot on trainees in terms of acceptance and intrinsic motivation. In addition, our findings highlight directions for further improvement of the design of social robots in sports and physical scenarios.