As Pakistan’s population ages and traditional care structures evolve, there is increasing interest in technological solutions for supporting older adults at home. This study investigates the potential of social assistive robots (SARs) in Pakistani homes, focusing on cultural values, inter-generational living, and limited access to such technologies. In a 3-day mixed-methods home study, 14 older adults interacted with a SAR communicating in Urdu. Through observations, interviews, and questionnaires, we evaluated the robot’s acceptability, engagement, and cultural compatibility. The results highlighted the need for culturally sensitive design, emphasising the role of robots as companions rather than replacements for human care, and the importance of robot’s ability to communicate in Urdu. We discuss how SARs could be designed to reflect the characteristics of Pakistani households, including faith, family values, everyday routines, and environmental factors. Our design considerations can benefit research on deploying SARs to support older adults in Pakistan and similar cultures.

Understanding and modelling how humans develop and maintain trust in robots is crucial for ensuring appropriate trust calibration during Human-Robot Interaction (HRI). This paper presents a mathematical model that simulates a three-layered framework of trust, encompassing dispositional, situational and learned trust. This framework aims to estimate human trust in robots during real-time interactions. Our trust model was tested and validated in an experimental setting where participants engaged in a collaborative trust game with a robot over four interactive sessions. Results from mixed-model analysis revealed that both the Trust Perception Score (TPS) and interaction session significantly predicted the Trust Modeled Score (TMS), explaining a substantial portion of the variance in TMS. Statistical analysis demonstrated significant differences in trust across sessions, with mean trust scores showing a clear increase from the first to the final session. Additionally, we observed strong correlations between situational and learned trust layers, demonstrating the model’s ability to capture dynamic trust evolution. These findings underscore the potential of this model in developing adaptive robotic behaviours that can respond to changes in human trust levels, ultimately advancing the design of robotic systems capable of real-time trust calibration.

As robots are increasingly becoming part of daily life worldwide, it is important to ensure that they are inclusive and culturally sensitive to accommodate users from different backgrounds. In particular, many countries in the Global South (GS) have yet to explore the integration and benefits of robots, especially for underrepresented language groups such as Urdu. We present an exploratory mixed-methods study that investigates how robots' language affects the social interaction, acceptability and overall perception of robots within Pakistani Urdu-speaking individuals. The findings highlight the importance of language and cultural adaptation, and how these factors influence the acceptance of robots, emphasising the need for more inclusive and religion sensitive technologies designed for the GS users.

This study explores optimising human-robot trust using reinforcement learning (RL) in simulated environments. Establishing trust in human-robot interaction (HRI) is crucial for effective collaboration, but misaligned trust levels can re-strict successful task completion. Current RL approaches mainly prioritise performance metrics without directly addressing trust management. To bridge this gap, we integrated a validated mathematical trust model into an RL framework and conducted experiments in two simulated environments: Frozen Lake and Battleship. The results showed that the RL model facilitated trust by dynamically adjusting it based on task outcomes, enhancing task performance and reducing the risks of insufficient or extreme trust. Our findings highlight the potential of RL to enhance human-robot collaboration (HRC) and trust calibration in different experimental HRI settings.

Existing research has shown that vocal and non-vocal human cues correlate with human trust and distrust behaviours, suggesting their potential to measure human trust in robots in real-time. However, there is a lack of research in Human-Robot Interaction that integrates vocal and non-vocal cues into a comprehensive model to measure trust. This paper aims to estimate human trust in robots by examining vocal and non-vocal cues differences between trust and distrust states across multiple sessions of collaborative game-based HRI with 40 participants. Our analysis revealed that vocal and non-vocal human cues can indeed predict trust in HRI, with certain facial expressions, facial movements, and pitch being significant factors. Random Forest classifier achieved the highest accuracy (84 %) in classifying trust states, with key features such as facial expressions (fear, angry), facial blendshapes (cheekSquintRight, jawRight), and vocal characteristics (Duration, Harmonicity std) being the most predictive of trust. These findings demonstrate the importance of combining vocal and non-vocal cues for accurate trust measurement and highlight the potential for real-time trust assessment in robotic systems.

Social robots such as companion or pet robots are increasingly being used for older adults’ mental well-being. Pet robot touch interactions could have positive effects on well-being similar to those observed in natural interactions with real animals. Designing pet robot interactions for an elderly family member with young adults could create gratitude and memory, thereby improving attitudes towards social robots. To this end, we conducted a preliminary user identification study with five young adults to determine their elderly family members’ preferences for sound/voice responses to touch inputs, using JoyForAll pet robots as technology probes. We report users’ likability of the preferred positive touch interactions, themes that emerged from the think-aloud design for touch interactions, and agreement rates of the robots’ sound/voice responses.

Existing work on detecting deception has mainly relied on collecting datasets evolving from contrived user interactions. We argue that naturally occurring deception behaviours can inform more reliable datasets and improve detection rates. Therefore, in this paper, we discuss the findings of two experiments which enabled participants to freely and naturally engage in deceptive and truthful behaviours in a game environment. We collected physiological and oculomotor behaviour (PB, & OB) data including electrodermal activity, blood volume pulse, heart rate, skin temperature, blinking rate, and blinking duration during the deceptive and truthful states. We investigate the changes in both PB and OB across repeated interactions and explore the potential of incremental transfer learning in detecting deception. We found significant differences in electrodermal activity, and skin temperature between deception and non-deception groups in both studies. The incremental transfer learning method with a logistic regression classifier detected deception with 80% accuracy, outperforming previous research. These results highlight the importance of collecting data from multiple sources and promote the use of incremental transfer learning to accurately detect deception in real time.

Existing work has shown that physiological behaviours (PBs) can effectively measure trust. However, there is a limited exploration of using multiple PBs concurrently to calibrate human trust in robots during real-time HRI. Additionally, most datasets are based on one-off interactions or a single context. This project addresses this gap by examining differences in PBs between trust and distrust states and investigating how these PBs change over repeated interactions in different contexts. We conducted two experiments to collect data on electrodermal activity (EDA), blood volume pulse (BVP), heart rate (HR), skin temperature (SKT), blinking rate (BR), and blinking duration (BD) from participants across multiple HRI sessions. The results showed significant differences in HR and SKT between trust and distrust states in Study 1, and significant differences in HR in Study 2. Furthermore, the Decision Tree classifier achieved the highest accuracy of 79% in classifying trust when using the incremental transfer learning algorithm for collective datasets. These results highlight the potential of using PBs for real-time trust measurement in HRI and suggest further exploration of incremental transfer learning methods to enhance trust prediction across different interaction contexts.

In human–robot interaction studies, trust is often defined as a process whereby a trustor makes themselves vulnerable to a trustee. The role of vulnerability however is often overlooked in this process but could play an important role in the gaining and maintenance of trust between users and robots. To better understand how vulnerability affects human–robot trust, we first reviewed the literature to create a conceptual model of vulnerability with four vulnerability categories. We then performed a meta-analysis, first to check the overall contribution of the variables included on trust. The results showed that overall, the variables investigated in our sample of studies have a positive impact on trust. We then conducted two multilevel moderator analysis to assess the effect of vulnerability on trust, including: (1) an intercept model that considers the relationship between our vulnerability categories and (2) a non-intercept model that treats each vulnerability category as an independent predictor. Only model 2 was significant, suggesting that to build trust effectively, research should focus on improving robot performance in situations where the users are unsure how reliable the robot will be. As our vulnerability variable is derived from studies of human–robot interaction and researcher reflections about the different risks involved, we relate our findings to these domains and make suggestions for future research avenues.

Point cloud completion is the task of producing a complete 3D shape given an input of a partial point cloud. It has become a vital process in 3D computer graphics, vision and applications such as autonomous driving, robotics, and augmented reality. These applications often rely on the presence of a complete 3D representation of the environment. Over the past few years, many completion algorithms have been proposed and a substantial amount of research has been carried out. However, there are not many in-depth surveys that summarise the research progress in such a way that allows users to make an informed choice of what algorithms to employ given the type of data they have, the end result they want, the challenges they may face and the possible strategies they could use. In this study, we present a comprehensive survey and classification of articles on point cloud completion untill August 2023 based on the strategies, techniques, inputs, outputs, and network architectures. We will also cover datasets, evaluation methods, and application areas in point cloud completion. Finally, we discuss challenges faced by the research community and future research directions.

Modelling humans’ trust in robots is critical during human-robot interaction (HRI) to avoid under- or over-reliance on robots. Currently, it is challenging to calibrate trust in real-time. Consequently, we see limited work on calibrating humans’ trust in robots in HRI. In this paper we describe a mathematical model that attempts to emulate the three-layered (initial, situational, learned) framework of trust capable of potentially estimating humans’ trust in robots in real-time. We evaluated the trust model in an experimental setup that involved participants playing a trust game on four occasions. We validate the model based on linear regression analysis that showed that the trust perception score (TPS) and interaction session predicted the trust modelled score (TMS) computed by applying the trust model. We also show that TPS and TMS did not change significantly from the second to the fourth session. However, TPS and TMS captured in the last session increased significantly from the first session. The described work is an initial effort to model three layers of humans’ trust in robot in a repeated HRI setup and requires further testing and extension to improve its robustness across settings.

Mental health challenges became more prevalent during the COVID-19 pandemic, especially among older adults. Consequently, we witnessed an uptake of new technologies, including social robots to address these challenges. However, we observed limited inclusion of older adults in the design process to design these technologies to cater user needs during the pandemic. To address this gap, we conducted a co-design workshop with 17 older adults and explored their emotional challenges after the COVID-19 pandemic. They evaluated the current social robot designs available in the literature and elicited the design preferences for a social robot to address their current emotional challenges. Our results based on thematic analysis show that the impact of the pandemic on older adults’ emotional challenges is persisting, and the companionship of a social robot is preferred to enhance their mental well-being. We also show that older adults preferred an animal-like robot design embodied with soft skin possessing a medium size. These findings highlighted older adults’ design choices of a social robot and affirmed their potential to support older adults’ mental well-being.

Abstract Cognitive load has been widely studied to help understand human performance. It is desirable to monitor user cognitive load in applications such as automation, robotics, and aerospace to achieve operational safety and to improve user experience. This can allow efficient workload management and can help to avoid or to reduce human error. However, tracking cognitive load in real time with high accuracy remains a challenge. Hence, we propose a framework to detect cognitive load by non-intrusively measuring physiological data from the eyes and heart. We exemplify and evaluate the framework where participants engage in a task that induces different levels of cognitive load. The framework uses a set of classifiers to accurately predict low, medium and high levels of cognitive load. The classifiers achieve high predictive accuracy. In particular, Random Forest and Naive Bayes performed best with accuracies of 91.66% and 85.83% respectively. Furthermore, we found that, while mean pupil diameter change for both right and left eye were the most prominent features, blinking rate also made a moderately important contribution to this highly accurate prediction of low, medium and high cognitive load. The existing results on accuracy considerably outperform prior approaches and demonstrate the applicability of our framework to detect cognitive load.

Trust is one of the necessary factors for building a successful human-robot interaction (HRI). This paper investigated how human trust in robots differs across HRI scenarios in two cultures. We conducted two studies in two countries: Saudi Arabia (study 1) and the United Kingdom (study 2). Each study presented three HRI scenarios: a dog robot guiding people with sight impairments, a teleoperated robot in healthcare, and a manufacturing robot. Study 1 shows that participants’ trust perception score (TPS) was significantly different across the three scenarios. However, Study 2 results show a slightly significant variation in TPS across the scenarios. We also found that the relevance of trust for a given task is an indicator of a participant’s trust. Furthermore, the findings showed that trust scores or factors affecting users’ trust vary across cultures. The findings identified novel factors that might affect human trust, such as controllability, usability and risk. The findings direct the HRI community to consider a dynamic and evolving design for modelling human-robot trust because factors affecting humans’ trust are evolving and will vary across different settings and cultures.

In this paper, we propose a reinforcement learning (RL) mechanism for social robots to select an action based on users’ learning performance and social engagement. We applied this behavior selection mechanism to extend the emotion and memory model, which allows a robot to create a memory account of the user’s emotional events and adapt its behavior based on the developed memory. We evaluated the model in a vocabulary-learning task at a school during a children’s game involving robot interaction to see if the model results in maintaining engagement and improving vocabulary learning across the four different interaction sessions. Generally, we observed positive findings based on child vocabulary learning and sustaining social engagement during all sessions. Compared to the trends of a previous study, we observed a higher level of social engagement across sessions in terms of the duration of the user gaze toward the robot. For vocabulary retention, we saw similar trends in general but also showing high vocabulary retention across some sessions. The findings indicate the benefits of applying RL techniques that have a reward system based on multi-modal user signals or cues.

We see three different roles (peer, tutee, tutor) for humanoid robots in education. The role of a monitor or an invigilator is understudied. Therefore, in this paper, we describe a method for the social robot to act as an invigilator. We implemented this method on the Nao robot. We conducted a study to compare an active invigilator robot v.s. a passive invigilator robot. The study aimed to understand the participant’s perception of the robot in the role of an invigilator. We found that the robot was highly rated as an invigilator regardless of the condition. Participants were generally satisfied with the use of the robot as an invigilator. Participants rated the active robot invigilator to be more human-like and responsive as compared to the passive one. The findings highlight the applicability of the role of a robot invigilator in education and call for a more careful investigation in the future.

Games have the potential to be used to enable the general public to understand the application and implication of many forms of work. We demonstrate an adaptive game that simulates the activities happening in extreme environments where robots carry out tasks and human operators control robots. Under the emergency, operators can experience high cognitive load (CL), so the game dynamically adjusts its support strategy to the user’s CL. We evaluated the adaptive game to find its effectiveness towards reducing user’s CL in real-time by comparing it with the non-adaptive and randomly adaptive versions of the game. The results showed that the method developed to dynamically adjusts the game-support strategy to the user’s CL was promising. The method reduced the CL significantly when compared to the randomly adaptive version, where the adaptations were randomly enabled or disabled on the game. The findings confirm the applicability of the method used to adapt the game and demonstrate the potential to be used to disseminate the work to the general public.

Public perceptions of Robotics and Artificial Intelligence (RAI) are important in the acceptance, uptake, government regulation and research funding of this technology. Recent research has shown that the public's understanding of RAI can be negative or inaccurate. We believe effective public engagement can help ensure that public opinion is better informed. In this paper, we describe our first iteration of a high throughput in-person public engagement activity. We describe the use of a light touch quiz-format survey instrument to integrate in-the-wild research participation into the engagement, allowing us to probe both the effectiveness of our engagement strategy, and public perceptions of the future roles of robots and humans working in dangerous settings, such as in the off-shore energy sector. We critique our methods and share interesting results into generational differences within the public's view of the future of Robotics and AI in hazardous environments. These findings include that older peoples' views about the future of robots in hazardous environments were not swayed by exposure to our exhibit, while the views of younger people were affected by our exhibit, leading us to consider carefully in future how to more effectively engage with and inform older people.

There are many challenges when it comes to deploying robots remotely including lack of operator situation awareness and decreased trust. Here, we present a conversational agent embodied in a Furhat robot that can help with the deployment of such remote robots by facilitating teaming with varying levels of operator control.

In this paper, we present a Child-Robot Interaction (CRI) study that applies our emotion and memory model on the social robot in the wild in a mathematics learning scenario. The rationale to conduct this study was to explore the effects of our model on children's engagement and learning in a real-life scenario and also to further emphasise the value of our model. We conducted an exploratory long-term CRI study, where the robot used the personalisation mechanism based on our emotion and memory model to understand its effects in terms of improving children's learning and sustaining social engagement on the Mathematics task in a long-term interaction. Our results showed that in a condition, where our model was implemented on the social robot, children showed the higher level of social engagement. Additionally, their learning performance based on calculating area and perimeter of regular and irregular shapes was also better in terms of their test scores.

In this paper, we present our early findings on the utilization of a social robot during the formal interview process. We implemented a mechanism that enabled the robot to ask context-aware questions based on the data based on the resume or linked-in profile of the applicant. Later, we conducted an exploratory between-subject evaluation with 8 adult participants to find the difference in the duration of applicants responses given to the NAO robot and to the human interviewer. Our results didn't find the significant difference in terms of participant responses to human and robotic interviewers.

The HAI conference is the premier discussion venue on the topic of Human Agent Interaction. In this paper we present our findings from the scientometric analysis of full papers from the HAI conference since its inception to date. We extracted various bibliometric measures and qualitatively coded our sample of 107 full papers over the 4 years of the conference. Our results show that the conference has not really grown rapidly and attracts papers from predominantly Asian Pacific regions. User studies were the common research methodology undertaken in HAI papers and humanoid robots are the popular agent of choice. Domains such as Education and Health were surprisingly underrepresented whereas communication was the focus of almost half of the papers. We also report on a mini comparison with the ICSR and IVA conference as a bench-marking strategy, which provides us with some reflections on how the HAI conference can be moved forward. In conclusion, we speculate on our findings and provide some insights to the organizers and steering committee of the HAI conference.

One of the known challenges in Children–Robot Interaction (cHRI) is to sustain children’s engagement during long-term interactions with robots. Researchers have hypothesized that robots that can adapt to children’s affective states and can also learn from the environment can result in sustaining engagement during cHRI. Recently, researchers have conducted a range of studies where robots portray different social capabilities and have shown that it has positively influenced children’s engagement. However, despite an immense body of research on implementation of different adaptive social robots, a pivotal question remains unanswered: Which adaptations portrayed by a robot can result in maintaining long-term social engagement during cHRI? In other words, what are the appropriate and effective adaptations portrayed by a robot that will sustain social engagement for an extended number of interactions? In this article, we report on a study conducted with three groups of children who played a snakes and ladders game with the NAO robot to address the aforementioned question. The NAO performed 1) game-based adaptations, 2) emotion-based adaptations, and 3) memory-based adaptation. Our results showed that emotion-based adaptations were found out to be most effective, followed by memory-based adaptations. Game adaptation didn’t result in sustaining long-term social engagement.

One of the known challenges in Children Robot Interaction (cHRI) is to sustain children's engagement for long-term interactions with robots. Researchers have hypothesised that robots that can adapt to children's affective states, and can also learn from the environment, resulting in sustained engagement during cHRI. In this paper, we report on a study conducted with three groups of children who played a snakes and ladders game with the NAO robot. The NAO performed 1) Game based adaptations, 2) Emotion based adaptations and 3) Memory based adaptation. The purpose of this study was to find which particular condition resulted in maintaining engagement over a certain period of time. Our results show that adaptations performed by the robot, in general, were able to maintain long-term engagement. However, we did not find any significant effect of one adaptation over another on engagement, social presence and perceived support.

In order to establish a long-term relationship between a robot and a child, robots need to learn from the environment, adapt to specific user needs and display behaviours and roles accordingly. Literature shows that certain robot behaviours could negatively impact child's learning and performance. Therefore, the purpose of the present study is to not only understand teacher's opinion on the existing effective social behaviours and roles but also to understand novel behaviours that can positively influence children performance in a language learning setting. In this paper, we present our results based on interviews conducted with 8 language teachers to get their opinion on how a robot can efficiently perform behaviour adaptation to influence learning and achieve long-term engagement. We also present results on future directions extracted from the interviews with teachers.

In this paper, we present our idea about applying an adaptive social mobile agent in a game based scenario to support foreign language vocabulary learning. We hypothesize that through implementing an adaptive agent, we may mitigate the problem of a loss in child engagement or may also prolong the time a child takes to lose interest. We then present details on architecture and implementation of an adaptive social mobile agent.

In this paper we present a survey based approach towards the design of a mobile application meant to function as an electronic version of a child health book for use in Sri Lanka. Through the use of persuasive technology the application aims to inculcate positive behavioural changes in Sri Lankan parents in order to facilitate the well being of their children. We report on a survey conducted with parents living in urban areas in Colombo which led to the formulation of design guidelines for the application. The application was then evaluated with a set of parents. Results from both the survey and application show that parents held great importance to the privacy and security of their child's data. Some aspects of the paper based health book were deemed to be at times unclear; such as the developmental checks. In general parents were positive about the prospects of an electronic health book. We conclude our paper with future directions of the digital health book.

In this paper, we will be introducing, advocating and emphasising the role of an adaptive mobile agent in a game based scenario for supporting foreign language vocabulary learning. We will also be discussing our motivation to design a game for foreign language word learning. We will then be presenting an idea of a possible game design and also discuss the role of an adaptive agent in this game.