Learning from Demonstration (LfD) allows novice users to teach robots through demonstrations without coding; however, such demonstrations are often suboptimal and can limit robot performance. To better support novices, we investigate the design of a feedback system that enables effective human-robot communication during demonstrations. We first conducted a focus group study (N = 9) to identify effective ways of visualizing key robot information, including joint limits, self-collisions, and manipulability. Guided by these insights, we designed an AR-based real-time feedback system and evaluated it in a between-subjects user study (N = 36) on a 7-DoF collaborative robot. Participants performed two tasks—insertion and pouring—with the second task enabling assessment of participants’ learning across tasks. Results show that real-time feedback reduced demonstration time, increased task completion rate, lowered perceived mental workload, and improved adherence to robot kinematic constraints. These findings demonstrate the effectiveness of the real-time feedback system for intuitive and effective robot teaching.

Speculative and systemic design are both used by HCI researchers to engage in complex sociotechnical change. However, they are rarely integrated in ways that make their complementary strengths explicit. This paper introduces Systemic Futures Dialogue, a design approach that interleaves speculative and systemic design methods across micro-macro and present-future dimensions. We report on an 18-month case study with the Architecture, Engineering, and Construction (AEC) industry, that applied a mixture of methods used in both design disciplines. These included semi-structured interviews, systems mapping, future-based scenarios, speculative probes, and participatory reflection. The resulting design approach generates grounded futures by connecting macro-level system dynamics with micro-level speculative critique, identifying tensions between present-day solutions and desired futures. The final Systemic Futures Dialogue contributes methodological guidance for conducting critical, participatory design work within a sociotechnical system.

In human–robot collaboration, repeated failures are inevitable and can undermine trust and perceptions of robot intelligence. While some failures severely disrupt tasks and others are relatively benign, their cumulative impact on trust is not clearly understood. We investigated whether users perceive repeated failures of the same type differently from varied failures, and how robot awareness of its own failures affects these perceptions. In a collaborative physical task with 54 participants, we manipulated failure sequence (homogeneous vs. heterogeneous) and awareness (none, partial, full). Results show that trust and perceived intelligence were influenced by both current and prior failures, with homogeneous sequences leading to smaller reductions in these evaluations compared to heterogeneous ones. Robots displaying awareness, whether partial or full, were consistently rated higher than unaware robots, particularly for grasping and planning failures. Our findings provide a deeper understanding of how failure type, sequence, and robot awareness shape users’ perceptions of collaborative robots.

Tangible interactions involve multiple sensory cues, enabling the accurate perception of object properties, such as size. Research has shown, however, that if we decouple these cues (for example, by altering the visual cue), then the resulting discrepancies present new opportunities for interactions. Perception over time though, not only relies on momentary sensory cues, but also on a priori beliefs about the object, implying a continuing update cycle. This cycle is poorly understood and its impact on interaction remains unknown. We study (N=80) visuo-haptic perception of size over time and (a) reveal how perception drifts, (b) examine the effects of visual priming and dead-reckoning, and (c) present a model of visuo-haptic perception as a cyclical, self-adjusting system. Our work has a direct impact on illusory perception in VR, but also sheds light on how our visual and haptic systems cooperate and diverge.

Learning from Demonstration allows robots to acquire skills from human demonstrations, making them more accessible to a wider range of users. Among different approaches, kinesthetic teaching allows humans to manipulate the robot joints directly, making it effective method for demonstrating constrained tasks. However, robots with kinematic redundancy enable multiple joint configurations to achieve a desired task, which could influence human teaching performance. One one hand, it could make it easier, allowing more freedom to demonstrate the task, but on the other, it also increases the number of joints that needs to be manipulated, potentially affecting cognitive and physical load of the demonstrator. Therefore, it is crucial to investigate how the number of degrees of redundancy (DoR) impact human performance during kinesthetic demonstrations, and then how these demonstrations influence robot performance. We simulated high and low DoR by locking one of the robot joint on a 7-DoF Panda robotic arm. We conducted a within-subject user study (N = 24) with two conditions: unconstrained condition (high DoR) and constrained condition (low DoR). We used a motion capture system to capture participants physical interaction with the robot when demonstrating two tasks: button pressing and cuboid block insertion. The results show that the robot’s DoR significantly affects mental workload, demonstration time, number of failed attempts, and physical interaction with the robot. Likewise, joint constraints significantly influence robot performance, measured by task completion using the learned model. These findings highlight the importance of considering robot DoR during demonstrating constrained tasks, allowing novice users to provide effective demonstrations.

Figure 1: Exemplified experimental setting for air pollution: participants were given a GUI to manipulate the different levels of particulate matter by moving a slider.The respective information was conveyed through the physical humanlike agent placed next to them.

Leveraging the integration of visual and proprioceptive cues, research has uncovered various perception thresholds in VR that can be exploited to support haptic feedback for grasping.While previous studies have explored individual dimensions, such as size, the combined effect of multiple geometric properties on perceptual illusions remains poorly understood.We present a two-alternative forced choice study investigating the perceptual interplay between object size and taper angle.We introduce an illusion space model, providing detailed insights into how physical and virtual object configurations affect human perception.Our insights reveal how, for example, as virtual sizes increase, users perceive that taper angles increase, and as virtual angles decrease, users overestimate sizes.We provide a mathematical model of the illusion space, and an associated tool, which can be used as a guide for the design of future VR haptic devices and for proxy object selections.

Can you move it to

Recent advances in multi-agentic systems (e.g., AutoGen, OpenAI Agents) allow users to interact with a group of specialised AI agents rather than a single general-purpose agent. Despite the promise of this new paradigm, the HCI community has yet to fully examine the opportunities, risks, and user-centred challenges it introduces. We contribute to research on multi-agentic systems by exploring their architectures and key features through a human-centred lens. While literature and use cases are still emerging, we build on existing tools and frameworks available to developers to identify a set of overarching challenges, e.g., orchestration and conflict resolution, that can guide future research in HCI. We illustrate these challenges through examples, present potential design considerations, and provide research opportunities to spark interdisciplinary conversation. Our work lays the groundwork for future exploration and offers a research agenda focused on user-centred design in multi-agentic systems.

For a robot to perform personalised human support in a home, it is essential to uniquely identify the people it is working for. Each individual has their own attributes, knowledge of the environment, and experiences which the robot should learn and keep in its memory. One of the current challenges is for a robot to identify and re-identify an individual while dealing with visual occlusion, changes in appearance, and identity switching. This paper presents a novel approach to address these challenges in robot vision by extending current state-of-the-art solutions to enhance person memorisation by taking multiple viewpoints to extract features for matching and maintaining this information in a world model of the robot.

Shared control systems aim to combine human and robot abilities to improve task performance. However, achieving optimal performance requires that the robot's level of assistance adjusts the operator's cognitive workload in response to the task difficulty. Understanding and dynamically adjusting this balance is crucial to maximizing efficiency and user satisfaction. In this paper, we propose a novel benchmarking method for shared control systems based on Fitts' Law to formally parameterize the difficulty level of a target-reaching task. With this we systematically quantify and model the effect of task difficulty (i.e. size and distance of target) and robot autonomy on task performance and operators' cognitive load and trust levels. Our empirical results (N=24) not only show that both task difficulty and robot autonomy influence task performance, but also that the performance can be modelled using these parameters, which may allow for the generalization of this relationship across more diverse setups. We also found that the users' perceived cognitive load and trust were influenced by these factors. Given the challenges in directly measuring cognitive load in real-time, our adapted Fitts' model presents a potential alternative approach to estimate cognitive load through determining the difficulty level of the task, with the assumption that greater task difficulty results in higher cognitive load levels. We hope that these insights and our proposed framework inspire future works to further investigate the generalizability of the method, ultimately enabling the benchmarking and systematic assessment of shared control quality and user impact, which will aid in the development of more effective and adaptable systems.

Office Assistant Robots (OARs) offer a promising solution to proactively provide in-situ support to enhance employee well-being and productivity in office spaces. We introduce OfficeMate, a social OAR designed to assist with practical tasks, foster social interaction, and promote health and well-being. Through a pilot evaluation with seven participants in an office environment, we found that users see potential in OARs for reducing stress and promoting healthy habits and value the robot's ability to provide companionship and physical activity reminders in the office space. However, concerns regarding privacy, communication, and the robot's interaction timing were also raised. The feedback highlights the need to carefully consider the robot's appearance and behaviour to ensure it enhances user experience and aligns with office social norms. We believe these insights will better inform the development of adaptive, intelligent OAR systems for future office space integration.

Robots are prone to making errors, which can negatively impact their credibility as teammates during collaborative tasks with human users. Detecting and recovering from these failures is crucial for maintaining effective level of trust from users. However, robots may fail without being aware of it. One way to detect such failures could be by analysing humans' non-verbal behaviours and reactions to failures. This study investigates how human gaze dynamics can signal a robot's failure and examines how different types of failures affect people's perception of robot. We conducted a user study with 27 participants collaborating with a robotic mobile manipulator to solve tangram puzzles. The robot was programmed to experience two types of failures -executional and decisional- occurring either at the beginning or end of the task, with or without acknowledgement of the failure. Our findings reveal that the type and timing of the robot's failure significantly affect participants' gaze behaviour and perception of the robot. Specifically, executional failures led to more gaze shifts and increased focus on the robot, while decisional failures resulted in lower entropy in gaze transitions among areas of interest, particularly when the failure occurred at the end of the task. These results highlight that gaze can serve as a reliable indicator of robot failures and their types, and could also be used to predict the appropriate recovery actions.

Detecting robot failures during collaborative tasks is crucial for maintaining trust in human-robot interactions. This study investigates user gaze behaviour as an indicator of robot failures, utilising machine learning models to distinguish between non-failure and two types of failures: executional and decisional. Eye-tracking data were collected from 26 participants collaborating with a robot on Tangram puzzle-solving tasks. Gaze metrics, such as average gaze shift rates and the probability of gazing at specific areas of interest, were used to train machine learning classifiers, including Random Forest, AdaBoost, XGBoost, SVM, and CatBoost. The results show that Random Forest achieved 90 % accuracy for detecting executional failures and 80 % for decisional failures using the first 5 seconds of failure data. Real-time failure detection was evaluated by segmenting gaze data into intervals of 3, 5, and 10 seconds. These findings highlight the potential of gaze dynamics for real-time error detection in human-robot collaboration.

Human-robot interaction (HRI) is an interdisciplinary field that utilises both quantitative and qualitative methods. While ROSBags, a file format within the Robot Operating System (ROS), offer an efficient means of collecting temporally synched multimodal data in empirical studies with real robots, there is a lack of tools specifically designed to integrate qualitative coding and analysis functions with ROSBags. To address this gap, we developed ROSAnnotator, a web-based application that incorporates a multimodal Large Language Model (LLM) to support both manual and automated annotation of ROSBag data. ROSAnnotator currently facilitates video, audio, and transcription annotations and provides an open interface for custom ROS messages and tools. By using ROSAnnotator, researchers can streamline the qualitative analysis process, create a more cohesive analysis pipeline, and quickly access statistical summaries of annotations, thereby enhancing the overall efficiency of HRI data analysis. https://github.com/CHRI-Lab/ROSAnnotator

Teleoperating a robot arm involves the human operator positioning the robot's end-effector or programming each joint. Whereas humans can control their own arms easily by integrating visual and proprioceptive feedback, it is challenging to control an external robot arm in the same way, due to its inconsistent orientation and appearance. We explore teleoperating a robot arm through motion-capture (MoCap) of the human operator's arm with the assistance of augmented reality (AR) visualisations. We investigate how AR helps teleoperation by visualising a virtual reference of the human arm alongside the robot arm to help users understand the movement mapping. We found that the AR overlay of a humanoid arm on the robot in the same orientation helped users learn the control. We discuss findings and future work on MoCap-based robot teleoperation.

Inspired by the observation that humans naturally adjust finger configurations based on object size and weight, we present ThumbShift, a novel haptic controller that physically moves and rotates the user's thumb to render subtle shifts in finger collaboration and affect whole-hand grasp perception. Unlike prior work focused on grasp type or global haptic feedback, our approach uniquely targets finger collaboration variation through localised, real-time finger repositioning during grasp - enabling Dynamic Digit Positioning (DDP) to modulate haptic and perceptual experience. Results of our user studies show that while size perception changes only slightly, by about 5%, in a two-alternative forced choice (2AFC) task, perceived weight shifts significantly—by approximately 19%—in magnitude estimation tasks. We also report on the influence of mass centre position which extends the weight perception changing ability to about 56%, and how finger force distribution works in altering users' perception. These findings demonstrate that dynamic thumb movement can reconfigure force distribution across the hand and substantially alter haptic experience. By highlighting the underexplored role of digit motion in object perception, our work opens new directions for perception-aware haptic devices in VR, AR, and physical interaction design.

Robots are embodied agents that act under several sources of uncertainty. When assisting humans in a collaborative task, robots need to communicate their uncertainty to help inform decisions. In this study, we examine the use of visualising a robot’s uncertainty in a high-stakes assisted decision-making task. In particular, we explore how different modalities of uncertainty visualisations (graphical display vs. the robot’s embodied behaviour) and confidence levels (low, high, 100%) conveyed by a robot affect the human decision-making and perception during a collaborative task. Our results show that these visualisations significantly impact how participants arrive to their decision as well as how they perceive the robot’s transparency across the different confidence levels. We highlight potential trade-offs and offer implications for robot-assisted decision-making. Our work contributes empirical insights on how humans make use of uncertainty visualisations conveyed by a robot in a critical robot-assisted decision-making scenario.

Learning from Demonstration (LfD) empowers novice users to teach robots daily life tasks without writing sophisticated code, thereby promoting the democratization of robotics. However, novice users often provide sub-optimal demonstrations, which can potentially impact the robot’s ability to efficiently learn and execute the tasks. Prior research has assessed the quality of demonstrations by evaluating the robot’s task performance; however, the approach remains insufficient to qualify individual demonstrations, leaving the reason for classifying demonstrations as high- or low-quality unknown. Therefore, this simulation-based study aims to quantify the quality of individual demonstration at each step by incorporating motion-related quality features such as manipulability and joint-space jerk. To assess the efficacy of these features, we initially evaluated the given demonstrations—taking into account each quality feature—to rank them from high- to low-quality. Subsequently, we investigated the impact of demonstration’s quality on task performance and the quality of task execution. In this pursuit, we trained a series of LfD models for distinct manipulation tasks: cube lifting and pick-and-place of soda can. Our results illustrate a strong correlation between ranked demonstrations and the quality of task execution. Interestingly, we observed that the quality features have a significant impact on task performance, particularly when the provided demonstrations exhibit diversity in terms of quality. Overall, this analysis enables quantifying the quality of individual demonstrations based on motion-related quality features, thus improving learning from demonstration.

Complex 3D shapes’ surfaces can be characterised using three shape descriptors: zeroth-order for rendering width; first-order to convey slope; and second-order for curvature. These shapes can be symmetric or asymmetric. To date, controllers in VR have been unable to render these properties in 3D. We present Stuet - a handheld VR controller that can render complex asymmetrical 3D objects for two-finger grasping and shape exploration. Stuet leverages dual 3 degrees of freedom (3-DOF) Stewart Platforms. This enables the contact plates for the fingers to be controlled individually, rendering object widths up to 75 mm and individual plate angles up to 30° in any tilt direction with respect to the vertical plane. We present the design and implementation of Stuet. We explain and benchmark its mechanical capabilities, present the inverse kinematics model required for its use, and report on a feasibility demonstration. Our results reveal that dual Stewart platforms offer new capabilities for asymmetric, advanced haptic interactions in VR.

There are current methodological and epistemological gaps and struggles between Human-Drone Interaction research and the field of design. We highlight five HDI design considerations and suggest a non-exhaustive list of design methods to approach them. We present an appeal to a more diverse and inclusive study of drones where current research can be balanced with a deeply qualitative and critical understanding of these flying robots through embracing design knowledge.

Teaching robots can be challenging, particularly for novice human users who struggle to understand the robot’s learning process. Current research in interactive robot learning lacks effective methods for assessing a user’s interpretation of the robot’s learning state, which makes it difficult to compare different teaching approaches. To address these issues, we propose and demonstrate a method for assessing the user’s interpretation of the robot’s learning state in an interactive learning scenario with a robotic manipulator. Additionally, we draw on existing literature to categorise types of interface interventions that can enhance the human-robot teaching process for novice users – both pragmatically and hedonically. In a user study (N=30), we implement two of these interventions and show how they improve robot performance, teaching efficiency and interpretability. These findings provide preliminary insights into the design of effective human-robot teaching interfaces and can be used to assist the development of future teaching approaches.

Embodied agents, in the form of virtual agents or social robots, are rapidly becoming more widespread. In human-human interactions, humans use nonverbal behaviours to convey their attitudes, feelings, and intentions. Therefore, this capability is also required for embodied agents in order to enhance the quality and effectiveness of their interactions with humans. In this paper, we propose a novel framework that can generate sequences of joint angles from the speech text and speech audio utterances. Based on a conditional Generative Adversarial Network (GAN), our proposed neural network model learns the relationships between the co-speech gestures and both semantic and acoustic features from the speech input. In order to train our neural network model, we employ a public dataset containing co-speech gestures with corresponding speech audio utterances, which were captured from a single male native English speaker. The results from both objective and subjective evaluations demonstrate the efficacy of our gesture-generation framework for Robots and Embodied Agents.

In interactive agent learning, the human may teach in a collaborative or adversarial manner. Past research has been focusing on collaborative teaching styles as these are common in human education settings, while overlooking adversarial ones despite promising results in recent research. Moreover, agent performance has been the main focal point while neglecting the perspective of the human teacher, who is crucial to the instructional process. In this work, we examine the impact of competitive and collaborative teaching styles on agent learning and human perception. We conducted a study (N=40) for participants to demonstrate a task in different interaction modes for teaching a computer agent: collaboratively, competitively, or without interacting with the agent. Most participants reported that they preferred competing against the computer agent to the other two modes. Despite smaller numbers of demonstrations given from the user, the agent performance from the interactive modes (collaborative and competitive) was comparable to the non-interactive mode (solo). The agent was perceived as being more competent in the competitive mode than the collaborative mode despite the marginally worse in-task performance. These preliminary findings suggest that competitive types of interaction, when agents or robots learn from humans, lead to better human perception of the agent’s learning when compared to collaborative, and better user engagement when compared to non-interactive learning from demonstrations.

Research in joint action focuses on the psychological, neurological, and physical mechanisms by which humans collabo-rate with other agents, and overlaps with several domains related to human-robot interaction. The development of artificial systems that can support or emulate the requisite aspects of joint action could lead to improved human-robot team performance as well as improvements in subjective metrics (e.g., trust). This workshop highlights theoretical and technical considerations about human-robot joint action and real-time adaptation, with a particular focus on socio-motor entrainment, showing how the emulation of psychological mechanisms (e.g., emotion, intention signaling, mirroring) can lead to improved performance. We will invite speakers with backgrounds in robotics, neuroscience and psychol-ogy, as well as speakers with a focus in adjacent works, such as in human-robot coordinated dance, alignment, or synchronization. We will call for papers that utilize the theory of joint-action in an interactive human-robot context. We will also call for position papers on the application of the theory of joint action to robotics, with a heavy focus on psychological mechanisms that could potentially be emulated or adapted to a human-robot context. Participants will have the opportunity to brainstorm considerations and techniques that would be applicable to joint action inspired works through breakout sessions with the aim to lead to new and improved collaborations across fields.

Augmented reality (AR) technologies are today more frequently being introduced to Human-Robot Interaction (HRI) to mediate the interaction between human and robot. Indeed, better technical support and improved framework integration allow the design and study of novel scenarios augmenting interaction with AR. While some literature reviews have been published, so far no classifications have been devised for the role of AR in HRI. AR constitutes a vast field of research in HCI, and as it is picking up in HRI, it is timely to articulate the current knowledge and information about the functionalities of AR in HRI. Here we propose a multidimensional taxonomy for AR in HRI that distinguishes the type of perception augmentation, the functional role of AR, and the augmentation artifact type. We place sample publications within the taxonomy to demonstrate its utility. Lastly, we derive from the taxonomy some research gaps in current AR-for-HRI research and provide suggestions for exploration beyond the current state-of-the-art.

With the rising use of Augmented Reality (AR) technologies in Human-Robot Interaction (HRI), it is crucial that HRI research examines the role of AR in HRI to better define AR-HRI systems and identify potential areas for future research. A taxonomy for AR in HRI has recently been proposed for the field. However, it was limited to the definition of the framework, and exemplifying its use was missing. In this paper, we perform a demonstration of how the aforementioned taxonomy of AR in HRI can be used to analyse an existing AR-HRI system and come up with questions for alternative ways AR-HRI could be designed and further extended.

Social robots are increasingly being used as a medi-ator in robot-assisted autism therapy to improve children's social and cognitive skills. Engagement is one of the key measurements used to evaluate the therapeutic interventions' effect on children. While “engagement” is broadly used, it has been challenging to find a consensus about its definition in the community. With this paper, we explore the use of a data-driven approach to investigate the extent to which a model on engagement built on one dataset transfers to another. We utilized two publicly available datasets of engagement recognition, namely PInSoRo and Qamqor datasets, with an attempt to achieve a higher accuracy taking into account the transferred knowledge. The accuracy of 83.18% was obtained on the PInSoRo dataset of child-child interactions with face and body keypoints. We have used the methodology of transfer learning to improve the classification accuracy on the Qamqor dataset. The best result obtained is a 71.89% accuracy on the Qamqor dataset. This suggests that more data with similar keypoints is needed to achieve better accuracy when utilizing transfer learning from one dataset to another dataset.

Humans use gestures as a means of non-verbal communication. Often accompanying speech, these gestures have several purposes but in general, aim to convey an intended message to the receiver. Researchers have tried to develop systems to allow embodied agents to be better communicators when interacting with humans via using gestures. In this article, we present a scoping literature review of the methods and the metrics used to generate and evaluate co-speech gestures. After collecting a set of papers using a term search on the Scopus database, we analysed the content of these papers based on methodology (i.e., model, the dataset used), evaluation measures (i.e., objective and subjective) and limitations. The results indicate that data-driven approaches are used more frequently. In terms of evaluation measures, we found a trend of combining objective and subjective metrics, while no standards exist for either. This literature review provides an overview of the research in the area and, more specifically insights the trends and the challenges to be met in building a system to automatically generate gestures for embodied agents.

Geometry and handwriting rely heavily on the visual representation of basic shapes. It can become challenging for students with visual impairments to perceive these shapes and understand complex spatial constructs. For instance, knowing how to draw is highly dependent on spatial and temporal components, which are often inaccessible to children with visual impairments. Hand-held robots, such as the Cellulo robots, open unique opportunities to teach drawing and writing through haptic feedback. In this paper, we investigate how these tangible robots could support inclusive, collaborative learning activities, particularly for children with visual impairments. We conducted a user study with 20 pupils with and without visual impairments, where they engaged in multiple drawing activities with tangible robots. We contribute novel insights on the design of children-robot interaction, learning shapes and letters, children engagement, and responses in a collaborative scenario that address the challenges of inclusive learning.

Tangible User Interfaces (TUI) have been found to be relevant tools for collaborative learning by providing a shared workspace and enhancing joint visual attention. Researchers have explored the use of TUIs in a variety of curricular activities and found them particularly interesting for spatial exploration. However, very few studies have explored how TUIs could be used as a collaborative medium for people with visual impairments (VIs). In this study, we investigated the effect of tangible interaction (a small tangible robot) in a spatial collaborative task (a treasure hunt) involving two people with VIs. The aim was to evaluate the impact of the design of the TUI on the collaboration and the strategies used to perform the task. The experiment involved six dyads of people with VIs. The results showed that the collaboration was impacted by the interaction design and open interesting perspectives on the design of collaborative games for people with VIs.

This study reviews published scientific literature on the use of swarm robots for education purposes in the last ten years. It focuses on user studies involving robotics swarm in order to identify the potential contributions of the incorporation of swarm robots as an educational tool and insight future research. We consider here the appearance of swarm robots, the curriculum of the experimental task and the interaction modalities between learners and robots. The outcomes of the literature review are discussed in terms of their existing challenges and opportunities for guiding researchers, educators, and practitioners.

Domestic robotic entities are on the rise, out of which, domestic drones are taking place in our society as one of the upcoming interactive technologies that we will see in our daily lives. In this paper, we scope for research literature that addresses the use of domestic drones within our environments to understand the current usage as well as identifying future research directions. After performing a search based collection of relevant papers in the ACM digital library (N=61 papers), we analysed the drone's application areas, their interaction modalities, the target users, and the level of autonomy of the proposed systems. The results show interesting trends in the modalities of interaction (visual projection combined with hand/foot gestures) as well as important research gaps such as child-drone interaction, and the use of drones for healthcare or education, given that currently most use cases for domestic drones are generic in nature.

In the Republic of Kazakhstan, the transition from Cyrillic to Latin alphabet raises challenges to training an entire population in writing the new script. This paper presents a CoWriting Kazakh system, an extension of the existing CoWriter system, aiming to implement an autonomous social robot that would assist children in transition from the old Cyrillic alphabet to a new Latin alphabet. With the aim to investigate which learning strategy yields better learning gains, we conducted an experiment with 67 children, aged 8-11 years old, who interacted with a robot in a CoWriting Kazakh learning scenario. Participants were asked to teach a humanoid NAO robot how to write Kazakh words using one of the scripts, Latin or Cyrillic. We hypothesized that a scenario in which the child is asked to mentally convert the word to Latin would be more effective than having the robot perform conversion itself. Results show that the CoWriter was successfully applied to this new script-switching task. The findings also suggest interesting gender differences in the preferred method of learning with the robot.

Collaborative learning appears in a joint intellectual efforts of individuals to understand an object of knowledge collectively. In their search for understanding the problems, meanings, and solutions, learners employ different multi-modal strategies. In this work, we explore the role of force feedback in learners interaction with tangible hand-held robots. We designed a collaborative learning environment to provide embodied intuitions on linear mathematical functions combined with graphical representations and ran a first study involving 24 participants. Our analysis shows a positive learning gain for our learning activity. Moreover, to explore the link between different types of force feedback and learners' collaboration, we designed a focus group study with 12 participants. Our results suggest that the haptic communication channel affects the collaboration dynamic differently according to the nature of the learning task. We finish by proposing design insights for future exploration of haptic in collaborative learning.

The Robots for Learning workshop series aims at advancing the research topics related to the use of social robots in educational contexts. This year's half-day workshop follows on previous events in Human-Robot Interaction conferences focusing on efforts to design, develop and test new robotics systems that help learners. This 5th edition of the workshop will be dealing in particular on the potential use of robots for adaptive learning. Since the past few years, inclusive education have been a key policy in a number of countries, aiming to provide equal changes and common ground to all. In this workshop, we aim to discuss strategies to design robotics system able to adapt to the learners' abilities, to provide assistance and to demonstrate long-term learning effects.

This paper presents the design of a novel and engaging collaborative learning activity for handwriting where a group of participants simultaneously tutor a Nao robot. This activity was intended to take advantage of both collaborative learning and the learning by teaching paradigm to improve children's meta-cognition (perception of their own skills). Multiple engagement probes were integrated into the activity as a first step towards fostering long term interactions. As a lot of research targets social interactions, the goal here was to determine whether an engagement strategy focused on the task could be as, or more efficient than one focused on social interactions and participants' introspection. To that effect, two engagement strategies were implemented. They differed in content but used the same multi-modal design in order to increase participants' meta-cognitive reflection, once on the task and performances, and once on participants' enjoyment and emotions. Both strategies were compared to a baseline by probing and assessing engagement at the individual and group level, along the behavioural, emotional and cognitive dimensions, in a between subject experiment with 12 groups of children. The experiments showed that the collaborative task pushed the children to adapt their manner of writing to the group, even though the adopted solution was not always correct. Furthermore, there was no significant difference between the strategies in terms of behaviour on task (behavioural engagement), satisfaction (emotional engagement) or performance (cognitive engagement) as the group dynamics had a stronger impact on the outcome of the collaborative teaching task. Therefore, the task and social engagement strategies can be considered as efficient in the context of collaboration.

In recent years, robots have been surfing on a trendy wave as standard devices for teaching programming. The tangibility of robotics platforms allows for collaborative and interactive learning. Moreover, with these robot platforms, we also observe the occurrence of a shift of visual attention from the screen (on which the programming is done) to the physical environments (i.e. the robot). In this paper, we describe an experiment aiming at studying the effect of using augmented reality (AR) representations of sensor data in a robotic learning activity. We designed an AR system able to display in real-time the data of the Infra-Red sensors of the Thymio robot. In order to evaluate the impact of AR on the learner's understanding on how these sensors worked, we designed a pedagogical lesson that can run with or without the AR rendering. Two different age groups of students participated in this between-subject experiment, counting a total of 74 children. The tests were the same for the experimental (AR) and control group (no AR). The exercises differed only through the use of AR. Our results show that AR was worth being used for younger groups dealing with difficult concepts. We discuss our findings and propose future works to establish guidelines for designing AR robotic learning sessions.

In the Republic of Kazakhstan, the transition from Cyrillic towards Latin alphabet raises challenges to teach the whole population in writing the new script. This paper presents a CoWriting Kazakh system that aims to implement an autonomous behavior of a social robot that would assist children in learning a new script. Considering the fact that the current generation of primary school children have to be fluent in both Kazakh scripts, this exploratory study aims to investigate which learning approach provides better effect. Participants were asked to teach a humanoid robot NAO how to write Kazakh words using one of the scripts, Latin vs Cyrillic. We hypothesize that it is more effective when a child mentally converts the word to Latin in comparison to having the robot perform conversion itself. The findings reject this hypothesis, but further research is needed as it is suggested that the way the pre-test was performed might have caused the obtained results.

In this paper, we propose that the data generated by educational robots can be better used by applying learning analytics methods and techniques which can lead to a deeper understanding of the learners' apprehension and behavior as well as refined guidelines for roboticists and improved interventions by the teachers. As a step towards this, we put forward analyzing behavior and task performance at team and/or individual levels by coupling robot data with the data from conventional methods of assessment through quizzes. Classifying learners/teams in the behavioral feature space with respect to the task performance gives insight into the behavior patterns relevant for high performance, which could be backed by feature ranking. As a use case, we present an open-ended learning activity using tangible haptic-enabled Cellulo robots in a classroom-level setting. The pilot study, spanning over approximately an hour, is conducted with 25 children in teams of two that are aged between 11-12. A linear separation is observed between the high and low performing teams where two of the behavioral features, namely number of distinct attempts and the visits to the destination, are found to be important. Although the pilot study in its current form has limitations, e.g. its low sample size, it contributes to highlighting the potential of the use of learning analytics in educational robotics.

In this article, we present a multi-level time scales framework for the analysis of human-robot interaction (HRI). Such a framework allows HRI scientists to model the inter-relation between measures and factors of an experiment. Our final goal with the introduction of this framework is to unify scientific practice in the HRI community for better reproducibility. Our new approach transposes Newell’s framework of human actions to model human-robot interaction. Measures from the interaction are sorted into categories (time scales) corresponding to the temporal constraints proposed by Newell. According to this sorting, a bottom-up or top-down analysis can then be performed to correlate variables which allows a better understanding and explanation of the interaction. The utilization of our method within two experimental use cases is then presented. The first one, a child-robot interaction, involves two robots and one child playing a memory game. The second is based on an analysis of the PInSoRo dataset, involving 30 child-robot pairs in a freeplay interaction. Finally, we introduce clear guidelines to re-use the framework.

In this paper, we present a robotic approach to improve the teaching of handwriting using the tangible, haptic-enabled and classroom-friendly Cellulo robots. Our efforts presented here are in line with the philosophy of the Cellulo platform: we aim to create a ready-to-use tool (i.e. a set of robot-assisted activities) to be used for teaching handwriting, one that is to coexist harmoniously with traditional tools and will contribute new added values to the learning process, complementing existing teaching practices.

Robotics is a multidisciplinary and highly innovative field. Recently, multiple and often minimally connected sub-communities of child-robot interaction have started to emerge, variously focusing on the design issues, engineering, and applications of robotic platforms and toolkits. Despite increasing public interest in robots, including robots for children, child-robot interaction research remains highly fragmented and lacks regular cross-disciplinary venues for discussion and dissemination. This workshop will bring together researchers with diverse scientific backgrounds. It will serve as a venue in which to reflect on the current circumstances in which child-robot research is conducted, articulate emerging and "near future" challenges, and discuss actions and tools with which to meet those challenges and consolidate the field.

This paper describes research aimed at supporting children's reading practices using a robot designed to interact with children as their reading companion. We use a learning by teaching scenario in which the robot has a similar or lower reading level compared to children, and needs help and extra practice to develop its reading skills. The interaction is structured with robot reading to the child and sometimes making mistakes as the robot is considered to be in the learning phase. Child corrects the robot by giving it instant feedbacks. To understand what kind of behavior can be more constructive to the interaction especially in helping the child, we evaluated the effect of a deictic gesture, namely pointing on the child's ability to find reading mistakes made by the robot. We designed three types of mistakes corresponding to different levels of reading mastery. We tested our system in a within-subject experiment with 16 children. We split children into a high and low reading proficiency even-though they were all beginners. For the high reading proficiency group, we observed that pointing gestures were beneficial for recognizing some types of mistakes that the robot made. For the earlier stage group of readers pointing were helping to find mistakes that were raised upon a mismatch between text and illustrations. However, surprisingly, for this same group of children, the deictic gestures were disturbing in recognizing mismatches between text and meaning.

Rehabilitation aims to ameliorate deficits in motor control via intensive practice with the affected limb. Current strategies, such as one-on-one therapy done in rehabilitation centers, have limitations such as treatment frequency and intensity, cost and requirement of mobility. Thus, a promising strategy is home-based therapy that includes task specific exercises. However, traditional rehabilitation tasks may frustrate the patient due to their repetitive nature and may result in lack of motivation and poor rehabilitation. In this article, we propose the design and verification of an effective upper extremity rehabilitation game with a tangible robotic platform named Cellulo as a novel solution to these issues. We first describe the process of determining the design rationales to tune speed, accuracy and challenge. Then we detail our iterative participatory design process and test sessions conducted with the help of stroke, brachial plexus and cerebral palsy patients (18 in total) and 7 therapists in 4 different therapy centers. We present the initial quantitative results, which support several aspects of our design rationales and conclude with our future study plans.

The Cellulo robots are small tangible robots that are designed to represent virtual interactive point-like objects that reside on a plane within carefully designed learning activities. In the context of these activities, our robots not only display autonomous motion and act as tangible interfaces, but are also usable as haptic devices in order to exploit, for instance, kinesthetic learning. In this article, we present the design and analysis of the haptic interaction module of the Cellulo robots. We first detail our hardware and controller design that is low-cost and versatile. Then, we describe the task-based experimental procedure to evaluate the robot's haptic abilities. We show that our robot is usable in most of the tested tasks and extract perceptive and manipulative guidelines for the design of haptic elements to be integrated in future learning activities. We conclude with limitations of the system and future work.

This article presents a learning activity and its user study involving the Cellulo platform, a novel versatile robotic tool designed for education. In order to show the potential of Cellulo in the classroom as part of standard curricular activities, we designed a learning activity called Windfield that aims to teach the atmospheric formation mechanism of wind to early middle school children. The activity involves a didactic sequence, introducing the Cellulo robots as hot air balloons and enabling children to feel the wind force through haptic feedback. We present a user study, designed in the form of a real hour-long lesson, conducted with 24 children in 8 groups who had no prior knowledge in the subject. Collaborative metrics within groups and individual performances about the learning of key concepts were measured with only the hardware and software integrated in the platform in a completely automated manner. The results show that almost all participants showed learning of symmetric aspects of wind formation while about half showed learning of asymmetric vectorial aspects that are more complex.

In this article, we present Cellulo, a novel robotic platform that investigates the intersection of three ideas for robotics in education: designing the robots to be versatile and generic tools; blending robots into the classroom by designing them to be pervasive objects and by creating tight interactions with (already pervasive) paper; and finally considering the practical constraints of real classrooms at every stage of the design. Our platform results from these considerations and builds on a unique combination of technologies: groups of handheld haptic-enabled robots, tablets and activity sheets printed on regular paper. The robots feature holonomic motion, haptic feedback capability and high accuracy localization through a microdot pattern overlaid on top of the activity sheets, while remaining affordable (robots cost about EUR 125 at the prototype stage) and classroom-friendly. We present the platform and report on our first interaction studies, involving about 230 children.

In this paper, we explored the effect of a robot's subconscious gestures made during moments when idle (also called adaptor gestures) on anthropomorphic perceptions of five year old children. We developed and sorted a set of adaptor motions based on their intensity. We designed an experiment involving 20 children, in which they played a memory game with two robots. During moments of idleness, the first robot showed adaptor movements, while the second robot moved its head following basic face tracking. Results showed that the children perceived the robot displaying adaptor movements to be more human and friendly. Moreover, these traits were found to be proportional to the intensity of the adaptor movements. For the range of intensities tested, it was also found that adaptor movements were not disruptive towards the task. These findings corroborate the fact that adaptor movements improve the affective aspect of child-robot interactions (CRI) and do not interfere with the child's performances in the task, making them suitable for CRI in educational contexts.

We present an omnidirectional ball wheel drive design that utilizes a permanent magnet as the drive roller to generate the contact force. Particularly interesting for novel human-mobile robot interaction scenarios where the users are expected to physically interact with many palm-sized robots, our design combines simplicity, low cost and compactness. We first detail our design and explain its key parameters. Then, we present our implementation and compare it with an omniwheel drive built with identical conditions and similar cost. Finally, we elaborate on the main advantages and drawbacks of our design.

In this paper, we present an experiment in the context of a child-robot interaction where we study the influence of the child-robot spatial arrangement on the child's focus of attention and the perception of the robot's performance. In the “Co-Writer learning by teaching” activity, the child teaches a Nao robot how to handwrite. Usually only face-to-face spatial arrangements are tested in educational child robot interactions, but we explored two spatial conditions from Kendon's F-formation, the side-by-side and the face-to-face formations in a within subject experiment. We estimated the gaze behavior of the child and their consistency in grading the robot with regard to the robot's progress in writing. Even-though the demonstrations provided by children were not different between the two conditions (i.e. the robot's learning didn't differ), the results showed that in the side-by-side condition children tended to be more indulgent with the robot's mistakes and to give it better feedback. These results highlight the influence of experimental choices in child-robot interaction.

New technologies and especially robotics is going towards more natural user interfaces. Works have been done in different modality of interaction such as sight (visual computing), and audio (speech and audio recognition) but some other modalities are still less researched. The touch modality is one of the less studied in HRI but could be valuable for naturalistic interaction. However touch signals can vary in semantics. It is therefore necessary to be able to recognize touch gestures in order to make human-robot interaction even more natural. We propose a method to recognize touch gestures. This method was developed on the CoST corpus and then directly applied on the HAART dataset as a participation of the Social Touch Challenge at ICMI 2015. Our touch gesture recognition process is detailed in this article to make it reproducible by other research teams. Besides features set description, we manually filtered the training corpus to produce 2 datasets. For the challenge, we submitted 6 different systems. A Support Vector Machine and a Random Forest classifiers for the HAART dataset. For the CoST dataset, the same classifiers are tested in two conditions: using all or filtered training datasets. As reported by organizers, our systems have the best correct rate in this year's challenge (70.91% on HAART, 61.34% on CoST). Our performances are slightly better that other participants but stay under previous reported state-of-the-art results.

Sociability of companion robots is one of the challenges that the field of human-robot interaction faces. Inspired from research in psychology and sociology dealing with inter-personal relationships, we aim to render robots capable of a behaviour compatible to be among humans. In the context of a companion robot for children, we propose different parenting styles (namely authoritative and permissive) and evaluate their effectiveness and acceptability by parents. We implemented behaviours of different styles played out by two robots, Nao and Reeti, with body and facial channels respectively for communication. 94 parents watched videos of the robots and replied to a questionnaire about the authoritativeness, effectiveness and acceptability of the robots. The results showed that robots can be perceived as dominant and authoritative; however their effectiveness as an authoritative figure is limited to young children and is correlated to the style played when giving an order. When given a choice between authoritative and permissive styles, the parents ended up not always choosing a parenting style similar to their own. This work contributes in formalising context dependent personalisation to parent expectation of a companion robot for children using the concept of styles.