Intuitive teleoperation interfaces are crucial for the safe and effective operation of robotic manipulators in challenging environments. In the nuclear industry, surface contact tasks such as swab sampling require precise path and force tracking, obstacle avoidance, and sustained operator attention, which conventional joystick interfaces struggle to support effectively. This study designs and evaluates a novel touchscreen teleoperation interface that maps continuous finger movements directly to robotic manipulator motions, provides finer velocity control, and integrates control with visualization, enabling more natural, precise, and intuitive surface interaction than conventional controllers. A comparative user study with 20 participants evaluated task performance and workload using the proposed touchscreen, a conventional joystick, and a single-click autonomous mode. Tasks simulated realistic surface manipulation using a Franka Emika Panda arm, remotely controlled from another country. Kinematic, physiological, and behavioral data were recorded to comprehensively assess task performance, cognitive load, and operator trust across each control condition. Participants completed teleoperation tasks more efficiently and accurately with the touchscreen interface, achieving a 53.5

This paper investigates how terrain complexity and user interaction modes (teleoperation versus passive observation) influence human cognitive load and trust during interactions with a reinforcement learning−trained legged robot navigating complex terrains. We quantitatively assess cognitive load and trust dynamics using multimodal physiological measurements, including GSR, facial skin temperature, and blink rate combined with self-reported NASA-TLX scores. Participants either actively teleoperated or passively observed the robot traversing flat surfaces, irregular terrains, and stairs within a high-fidelity IsaacGym simulation. Our findings highlight distinct physiological and subjective responses linked to both terrain difficulty and interaction role. Specifically, teleoperators experienced higher cognitive load but stable trust levels, whereas observers showed heightened stress responses and reduced trust during challenging terrain navigation. By combining reinforcement learning robot locomotion with multimodal physiological sensing, this research advances methods for real-time assessment of trust and workload in human-robot interaction, offering insights for designing more adaptive and user-centered robotic systems.

This paper aims to develop a dynamic trust prediction model for teleoperated robotic systems in human-robot interaction (HRI) scenarios. Our model captures trust fluctuations influenced by task performance, cognitive load, and physiological responses. In our experiments, participants teleoperated a robotic arm under three conditions: without guidance (C1), with verbal guidance (C2), and with a combination of verbal and visual guidance (C3). Trust levels were measured after each condition, and cognitive load was assessed using the NASA TLX and physiological sensors. Our dynamic Bayesian network model demonstrated significant improvements in predictive accuracy, achieving 89

Physical touch, such as handshakes, plays a critical role in human-robot interaction (HRI), influencing perceived naturalness and social presence. This study investigates how arm compliance, hand grip strength, and motion synchrony jointly affect the subjective quality of a human-robot handshake. We implemented a fully actuated, tactile-sensorized humanoid hand mounted on a manipulator arm and designed a compliant, oscillatory handshake controller with adaptive synchronization. Sixteen participants experienced handshakes across a 2x2x2 factorial design, varying arm compliance, grip strength, and synchrony. Objective kinematic analysis revealed significant main and interaction effects across all factors. At the same time, subjective ratings showed clear preferences for a weaker grip and greater arm compliance, with synchrony exerting minimal influence on perceived naturalness. These results highlight a perceptual hierarchy in HRI: foundational haptic properties exert the strongest influence on user experience, while advanced kinematic adjustments have limited impact when basic comfort is lacking. This insight provides concrete guidance for designing robotic handshakes that feel more human-like and pleasant.

Doctoral Networks (DNs) aim to address systemic challenges in doctoral education, such as fostering interdisciplinarity, enabling international and intersectoral collaboration, enhancing employability, and promoting responsible innovation. While cohort-based training helps mitigate student isolation through workshops and summer schools, traditional DNs often struggle to fully realise their collaborative potential, often relying on predefined supervisor relationships or the initiative of individual researchers. In contrast, Marie Skłodowska-Curie Doctoral Networks (MSCA-DNs) prioritise doctoral candidates (DCs), challenging them to balance independent research with contributions to a shared, mission-driven objective. This study examines how structured training, including digital communities and application-focused research sprints, enhances system integration and collaboration within the Robotics and AI for Critical Asset Monitoring (RAICAM) Doctoral Network. DCs located across seven European countries worked in virtual teams, refining systems through structured workflows, weekly meetings, and shared workspaces before training schools. Through continuous online collaboration and targeted sprints, RAICAM facilitated interdisciplinary integration. Two research sprints, conducted in Italy and France, allowed teams to develop and test solutions for real-world challenges with an impact-driven plan that considers a given problem from and end-to-end perspective that requires and foster interdisciplinary collaboration. The results highlight the effectiveness of structured training in enhancing collaboration and adaptability, while identifying key areas for improvement. This study translates lessons from RAICAM into practical guidelines for future doctoral networks, demonstrating how structured training empowers students to drive interdisciplinary research independently.

Social robots have shown significant potential in enhancing learning experiences, and humor has been proven to be beneficial for learning. This study investigates the impact of both the presence and timing of humor on students’ learning outcomes and overall learning experience. A total of 24 participants were randomly assigned to one of the three conditions: (C1) interact with a robot with no humor, (C2) interact with a robot with humor at pre-defined moments during the lesson, and (C3) interact with a robot that triggers humor based on engagement levels. The results revealed that the humor at pre-defined moments condition (C2) led to significantly better learning outcomes and longer interaction times compared to the other two conditions. While the adaptive humor in Condition C3 did not significantly outperform Condition C1, it showed positive effects on participants’ perceived learning effectiveness and engagement. These findings contribute to the understanding of how humor, when strategically timed, can enhance the effectiveness of social robots in educational settings.

Studies indicate that physical rehabilitation exercises recommended by healthcare professionals can enhance physical function, improve quality of life, and promote independence for physically disabled individuals. In response to the lack of immediate expert feedback on performed actions, developing an automated system for monitoring such actions and providing feedback is very much needed. In this work, we focus on skeleton-based exercise assessment, which uses skeleton data to evaluate human motion and provide a score on how well a patient performed a movement. There are several approaches to this issue, with Spatio Temporal Graph Convolutional Networks (GCN) being among the most recent. GCNs model skeleton data as graphs and utilize temporal and spatial convolutions to capture relationships between joints more effectively than previous methods. In this research, we propose a new Transformer based model, PhysioFormer. It is inspired by SkateFormer method for human action recognition, with enhanced structure to fit the task of physical rehabilitation assessment. The model leverages skeletal-temporal self-attention across different groups based on relations between joints. The evaluation is done on the KIMORE, UI-PRMD, and KERAAL datasets, benchmark datasets that provide skeleton data captured by Kinect motion system. Our model is surpassing state-of-the-art methods significantly.

The rise of Generative Artificial Intelligence (GenAI) and Large Language Models (LLMs) is accelerating the integration of social robots into education. These technologies enhance robots' abilities in natural language interaction, adaptive behaviour, and personalised learning support. To advance real-world implementation, it is essential to identify the main challenges and opportunities in this field. We conducted a two-round Delphi study with 16 experts in human-robot interaction and educational technology. In the first round, participants outlined opportunities, challenges, and potential robot roles expected in the short term (1 year) and medium term (5 years). Content analysis revealed 8 opportunities, 10 challenges and 10 roles. In the second round, experts ranked their importance and feasibility across both time horizons. The results show that the most critical opportunities and challenges are also the least feasible to achieve in practice. Conversely, the proposed roles of educational robots demonstrated alignment between importance and feasibility. Experts highlighted three promising roles for robots in the GenAI era: supporting teachers in boosting learner engagement, serving as conversational interfaces for students to access knowledge and assisting teachers in supporting disadvantaged learners. These findings provide a roadmap for prioritising feasible innovations in educational robotics.

Nonverbal communication plays a crucial role in both human-human and human-robot interactions (HRIs), where facial expressions convey emotions, intentions and trust. Enabling humanoid robots to generate human-like facial reactions in response to human speech and facial behaviours remains significant challenges. In this work, we leverage human-human interaction (HHI) datasets to train a humanoid robot, allowing it to learn and imitate facial reactions to both speech and facial expression inputs. Specifically, we extend a sequence-to-sequence (Seq2Seq)-based framework that enables robots to simulate human-like virtual facial expressions that are appropriate for responding to the perceived human user behaviours. Then, we propose a deep neural network-based motor mapping model to translate these expressions into physical robot movements. Experiments demonstrate that our facial reaction-motor mapping framework successfully enables robotic self-reactions to various human behaviours, where our model can best predict 50 frames (two seconds) of facial reactions in response to the input user behaviour of the same duration, aligning with human cognitive and neuromuscular processes. Our code is provided at https://github.com/mrsgzg/Robot_Face_Reaction.

Trust plays a crucial role in user performance during teleoperated human-robot interaction. This study presents a reinforcement learning (RL) model that adapts to dynamic trust levels using physiological data and task performance metrics. Participants completed a complex teleoperation task under three conditions: (C1) limited feedback, (C2) AI-generated verbal guidance, and (C3) AI guidance paired with real-time RViz visualization. Physiological indicators, such as blink rate, galvanic skin response (GSR), and facial temperature along with task performance metrics like success rate and completion time were tracked. Statistical analyses revealed that increased task complexity in C1 reduced trust and increased cognitive load, leading to poorer performance. AI-generated guidance in C2 improved task understanding and performance, supporting Hypothesis H2. In C3, combining AI guidance with RViz visualization further boosted trust and reduced cognitive load, partially confirming Hypothesis H3. The RL model successfully adapted guidance strategies based on real-time user states, and additional testing showed that the agent’s adaptive strategies significantly increased user trust and improved performance. These results underscore the potential of adaptive RL models to enhance trust and efficiency in teleoperated human-robot systems.

Modern over-actuated vehicle systems depend on precise force coordination to achieve optimal yaw moment control, critical for vehicle stability, safety, and handling. While traditional optimization-based control allocation (CA) methods are effective, they become computationally demanding as actuator complexity grows. This work explores imitation learning as a scalable alternative. We present a comparative study between Behavioral Cloning (BC) and Maximum Entropy Inverse Reinforcement Learning (MaxEnt IRL) for neural network-based CA in over-actuated automotive systems. Both approaches are trained using realworld data from a Renault Austral prototype to imitate an optimization-based tire force allocator for yaw control. LSTM architectures are used to capture temporal dependencies. The methods are evaluated across generalization, safety, and computational performance. BC demonstrates low inference latency and strong nominal performance, while IRL achieves similar outcomes, even with reduced training coverage. Under actuator failure, both methods exhibit comparable behavior, consistent with training data characteristics. These findings suggest that imitation learning could be explored as an alternative to traditional optimization-based control allocation in future high-actuation systems, particularly where computational efficiency and scalability become a concern. However, for the present case, optimization based allocation remains the most reliable and well-performing solution. This study serves as a foundational step toward imitating computationally demanding high-level Model Predictive Control (MPC) strategies using neural nets, enabling safe and efficient deployment in real-time automotive environments.

IntroductionDrivers' emotions have been widely investigated in transportation due to their significant effects on driving behaviors and traffic accidents. Appraisal theory posits that emotional reactions are influenced by individuals' attitudes toward current circumstances and events, thereby shaping their driving attitudes and styles. However, In the study of emotional driving, research often focuses on the impact of single factors such as age, gender, and personality, while the interplay between these multiple factors is a challenge. This study aims to explore the impact of age, personality, and driving experience on driving behaviors, and to investigate the interaction effect between these factors, particularly the role of emotional arousal.MethodUsing moderated moderation and mediated moderation analyses, we examined how these individual factors interact and influence driving behaviors, including acceleration, speed stability, and steering performance. Data were collected from a driving simulation experiment involving 40 Chinese participants in various emotional states.ResultsOur findings revealed that higher-age drivers and experienced drivers displayed lower maximum acceleration and better speed stability. Extraversion significantly mediated the relationship between age and driving behaviors, with this relationship being moderated by arousal states. Additionally, Neuroticism moderated the relationship between driving experience and driving behaviors.ConclusionThis study highlights how individual factors influence the trajectory of personality development in relation to driving behaviors. These findings have practical implications for improving traffic safety and driver education programs by incorporating emotional and personality-based interventions. Further long-term and individualized studies are needed to better understand these interactions and develop targeted interventions.

Engagement is a key concept in Human-Robot Interaction (HRI), as high engagement often leads to improved user experience and task performance. However, accurately estimating engagement during interactions is challenging. In this study, we propose a Dynamic Bayesian Network (DBN) to infer user engagement from various modalities, including head rotation, eye movements, facial expressions captured through visual sensors, as well as facial temperature variations measured by a thermal camera. Data was gathered from a human-robot interaction (HRI) experiment, where a robot guided participants and encouraged them to share their thoughts and insights on environmental issues. Our approach successfully combines these diverse features to offer a thorough assessment of user engagement. The network was tested on its capacity to classify participants as either engaged or not engaged, achieving an accuracy of 0.83 and an Area Under the Curve (AUC) of 0.82. These findings underscore the strength of our DBN in detecting user engagement during interactions.

Physical rehabilitation exercises suggested by healthcare professionals can help recovery from various musculoskeletal disorders and prevent re-injury. However, patients' engagement tends to decrease over time without direct supervision, which is why there is a need for an automated monitoring system. In recent years, there has been great progress in quality assessment of physical rehabilitation exercises. Most of them only provide a binary classification if the performance is correct or incorrect, and a few provide a continuous score. This information is not sufficient for patients to improve their performance. In this work, we propose an algorithm for error classification of rehabilitation exercises, thus making the first step toward more detailed feedback to patients. We focus on skeleton-based exercise assessment, which utilizes human pose estimation to evaluate motion. Inspired by recent algorithms for quality assessment during rehabilitation exercises, we propose a Transformer-based model for the described classification. Our model is inspired by the HyperFormer method for human action recognition, and adapted to our problem and dataset. The evaluation is done on the KERAAL dataset, as it is the only medical dataset with clear error labels for the exercises, and our model significantly surpasses state-of-the-art methods. Furthermore, we bridge the gap towards better feedback to the patients by presenting a way to calculate the importance of joints for each exercise.

This study addresses the critical need for refined, reliable, and complete real-world trajectory data in the de-velopment of Advanced Driver Assistance Systems (ADAS), particularly for Adaptive Cruise Control (ACC) functions. We conducted a comprehensive comparison of car-following and deceleration scenarios across ten open-source datasets from multiple countries, encompassing both highway and urban environments. Focusing on key kinematic variables crucial for longitudinal behavior, we employed statistical measures and safety metrics to compare data sets across different driving regulations and road designs. Our findings reveal substantial overlaps in the distributions of logical parameters, despite the varied data sources and cultural contexts. However, we noted significant differences in safety-critical metrics, such as Time Headway and Time To Collision (TTC), highlighting culture-specific driving behaviors. Interestingly, Chinese datasets consistently exhibited the smallest distance head ways across all scenarios, yet maintained high TTC values (around 16s) compared to other datasets, suggesting a unique approach to risk management. To quantify these differences, we calibrated the Intelligent Driver Model using U.S. data and evaluated its transferability, demonstrating remarkable performance degradation when applied to non-U.S. datasets. These results provide crucial insights for developing globally applicable, yet culturally sensitive safety assessment methodologies for next-generation automated vehicles, highlighting the need for adaptive ADAS technologies that can accommodate regional driving norms while maintaining consistent safety standards. The code and extracted Longitudinal Trajectory data used in this study are available: https://github.com/imanetaourarti/Car-Following-analysis.