Robot Interaction Research Articles

Analyzing the Impact of Responding to Joint Attention on the User Perception of the Robot in Human-Robot Interaction

The concept of joint attention holds significant importance in human interaction and is pivotal in establishing rapport, understanding, and effective communication. Within social robotics, enhancing user perception of the robot and promoting a sense of natural interaction with robots becomes a central element. In this sense, emulating human-centric qualities in social robots, such as joint attention, defined as the ability of two or more individuals to focus on a common event simultaneously, can increase their acceptability. This study analyses the impact on user perception of a responsive joint attention system integrated into a social robot within an interactive scenario. The experimental setup involves playing against the robot in the “Odds and Evens” game under two conditions: whether the joint attention system is active or inactive. Additionally, auditory and visual distractors are employed to simulate real-world distractions, aiming to test the system’s ability to capture and follow user attention effectively. To assess the influence of the joint attention system, participants completed the Robotic Social Attributes Scale (RoSAS) after each interaction. The results showed a significant improvement in user perception of the robot’s competence and warmth when the joint attention system was active.

Chemomechanical Self-Oscillatory Microgel Motility in Stratified Chemical Media.

The design of chemomechanical self-oscillators, which execute oscillations in the presence of constant stimuli lacking periodicity, is a step toward the development of autonomous and interactive soft robotic systems. This work presents a simple design of prolonged chemomechanical oscillatory movement in a microgel system capable of buoyant motility within stratified chemical media containing spatially localized sinking and floating stimuli. Three design elements are developed: a stimuli-responsive membranized calcium alginate microgel, a Percoll density gradient for providing stratified antagonistic chemical media, and transduction of microgel particle size actuation into buoyant motility via membrane-mediated displacement of the Percoll media. The presence of citrate or calcium ions in different layers of the Percoll media gives rise to swelling (buoyancy) or contraction (geotaxis), respectively, which in turn mediate the shuttling of the microgels between the layers to produce prolonged or damped chemomechanical oscillatory trajectories. The concentration-dependence of the oscillatory behavior in the stratified media, the density gap between the Percoll layers, and the kinetic asymmetry of microgel swelling and deswelling are studied. The illustrated modular design allows for the development of chemomechanical self-oscillators responsive to light, pH, or temperature, which will find applications in interactive soft robotics, autonomous microbots, and intelligent materials.

Personalization of Robot Behavior Using Approach Based on Model Predictive Control

This paper proposes a novel approach to personalizing robot behavior using Model Predictive Control (MPC). Social humanoid robots, equipped with advanced sensors and human-like capabilities, are increasingly integrated into human environments, necessitating adaptable and intuitive communication interfaces. Our approach enables the design of adaptive interfaces that support fluid, personalized human–robot interactions. In the proposed framework, a user model is applied to predict responses to potential robot actions. Initially, this model represents an average user; however, it is updated as the robot gathers new observations, leading to increasingly personalized decisions. Experiments assessed the performance of five machine-learning algorithms generating user models in a simulated environment, with the Light Gradient Boosting Machine (LGBM) achieving the best results, closely followed by Random Forest (RF). A comparison of the inference time showed that LGBM is more than four times faster than RF. Outlier-removal techniques showed a modest performance improvement over models without outlier removal. Additionally, robot adaptation was tested in the experiments, showing an increase in the average reward over time, although with a relatively high standard deviation. The results suggest that the proposed approach for robot behavior adaptation based on MPC works well, and the recommended algorithm for the user model is LGBM.

Automatic evaluation of planners in dynamic scenes during human–robot interaction

AbstractThe evaluation of planners is essential to guarantee the efficiency and performance of trajectories executed by collaborative robots in human–robot interaction (HRI) contexts. The main objective of this research is to develop a method that allows obtaining an automated assessment of the performance of planners widely used in robotic environments. In addition to analyzing specific metrics such as planning time, path length, smoothness, and clearance, this paper introduces novel contributions, including a unique method for dynamic scene evaluation and a new comprehensive and global performance index, named Total Performance Index (TPIx), which encompasses all the aforementioned metrics. The system proposed is composed of a collaborative robot and an RGB-D sensor to monitor the environment using 3D data to perform safe trajectories during multiple tasks. In this quantitative evaluation, two single-query planners (RRT, KPIECE) and two multiple-query planners (SPARS, PRM) were analyzed. The results obtained demonstrate the feasibility and effectiveness of the proposed method to automatically evaluate the planners used by collaborative robots. Therefore, this study contributes to the advancement of collaborative robotics by introducing updated methods for planner evaluation and aims to facilitate the development of more efficient and adaptive systems in light of recent advancements in robotic technologies.

Enabling Sustainable Diffusion in Supply Chains Through Industry 5.0: An Impact Analysis of Key Enablers for SMEs in Emerging Economies

Industry 5.0 (I5.0) builds upon Industry 4.0 by emphasizing the role of workers in production processes and prioritizing socio-economic-environmental sustainability. It has been shown that I5.0 can enhance sustainability within supply chains (SCs). However, companies in emerging economies, especially small and medium-sized manufacturing enterprises (SMEs), which are crucial to developing economies, face challenges in implementing these concepts. These SMEs are in the early stages of adopting I5.0 to foster sustainability in their SCs and require urgent identification of key I5.0 enablers. Unfortunately, the current literature lacks research on this topic specifically within the context of SMEs in emerging economies. To bridge this gap, this study identifies the enablers of I5.0 that promote sustainability diffusion in SCs, using China’s SME manufacturing sector as a case study. The integrated framework for applying multiple criteria decision-making (MCDM) techniques in this study aims to assist decision-makers in evaluating different options and making optimal choices in a systematic and structured manner when faced with complex situations. The study employs the fuzzy Delphi method (FDM) to identify 15 key I5.0 enablers and categorize them into three clusters. Grey-DEMATEL is subsequently utilized to determine the causal relationships, rank the importance of the enablers, and construct an interrelationship diagram. This study found that ‘availability and functionality of resources’; ‘top management support, active participation, and effective governance’; ‘support from government, regulators, and financial resources’; and ‘introduction of safer and more efficient robotic systems for human–robot interaction and collaboration’ serve as the primary means of resolving issues. Overall, this study helps managers, practitioners, and policymakers interested in I5.0 applications to promote sustainability in the supply chain.

AI-Powered Multimodal Modeling of Personalized Hemodynamics in Aortic Stenosis.

Aortic stenosis (AS) is the most common valvular heart disease in developed countries. High-fidelity preclinical models can improve AS management by enabling therapeutic innovation, early diagnosis, and tailored treatment planning. However, their use is currently limited by complex workflows necessitating lengthy expert-driven manual operations. Here, we propose an AI-powered computational framework for accelerated and democratized patient-specific modeling of AS hemodynamics from computed tomography (CT). First, we demonstrate that the automated meshing algorithms can generate task-ready geometries for both computational and benchtop simulations with higher accuracy and 100 times faster than existing approaches. Then, we showthat the approach can be integrated with fluid-structure interaction and soft robotics models to accurately recapitulate a broad spectrum of clinical hemodynamic measurements of diverse AS patients. The efficiency and reliability of these algorithms make them an ideal complementary tool for personalized high-fidelity modeling of AS biomechanics, hemodynamics, and treatmentplanning.

Deep Neural Networks for Accurate Depth Estimation with Latent Space Features

Depth estimation plays a pivotal role in advancing human–robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation, which relies on a single RGB camera, offers a more affordable solution compared to traditional methods that use stereo cameras or LiDAR. However, despite recent progress, many monocular approaches struggle with accurately defining depth boundaries, leading to less precise reconstructions. In response to these challenges, this study introduces a novel depth estimation framework that leverages latent space features within a deep convolutional neural network to enhance the precision of monocular depth maps. The proposed model features dual encoder–decoder architecture, enabling both color-to-depth and depth-to-depth transformations. This structure allows for refined depth estimation through latent space encoding. To further improve the accuracy of depth boundaries and local features, a new loss function is introduced. This function combines latent loss with gradient loss, helping the model maintain the integrity of depth boundaries. The framework is thoroughly tested using the NYU Depth V2 dataset, where it sets a new benchmark, particularly excelling in complex indoor scenarios. The results clearly show that this approach effectively reduces depth ambiguities and blurring, making it a promising solution for applications in human–robot interaction and 3D scene reconstruction.

Room‐Temperature‐Integrated Flexible Diffusive Oxide Memristors for Artificial Nociceptive Systems

AbstractNovel areas of human–computer interaction and intelligent robotics are rapidly boosted by flexible electronic devices, among which artificial nociceptors for pain perception are considered essential sensory devices. Recently, flexible diffusive memristors with volatile behavior are extensively studied to emulate biological synapses and neurons because of their rich threshold–switching dynamics, which are crucial for nociceptive functions. Herein, flexible diffusive memristors with an Ag/TaO1.8/TaO2.7/TaO1.8/Ag (ATTTA) structure are fabricated at room temperature, demonstrating a high switching ratio of 107, an ultra‐fast turn‐on speed of 40 ns, a long endurance up to 104 sweep cycles, low positive and negative threshold variation rates (6.7%/7.8%) for 50 devices, a good thermal stability at an 85 °C measurement temperature, and a high flexibility under an 8 mm bending radius. These high performances are attributed to the oxygen‐rich TaO2.7 layer, which can prevent the excessive migration of Ag atoms. Moreover, multiple biological nociceptor functions, including threshold firing, no adaptation, and sensitization, are successfully emulated in the flexible ATTTA diffusive memristor. Accordingly, the human–skin nociceptive system is successfully emulated by integrating ATTTA diffusive memristor array with force–sensing resistors (FSRs), which enables stereoscopic injury perception of inhomogeneous stimuli.

Beyond Human Touch: Integrating Soft Robotics with Environmental Interaction for Advanced Applications

Soft robotics is an emerging field dedicated to the design and development of robots with soft structures. Soft robots offer unique capabilities in terms of flexibility, adaptability, and safety of physical interaction, and therefore provide advanced collaboration between humans and robots. The further incorporation of soft actuators, advanced sensing technologies, user-friendly control interfaces, and safety considerations enhance the interaction experience. Applications in healthcare, specifically in rehabilitation and assistive devices, as well as manufacturing, show how soft robotics has revolutionized human–robot collaboration and improved quality of life. Soft robotics can create new opportunities to enhance human well-being and increase efficiency in human–robot interactions. Nevertheless, challenges persist, and future work must focus on overcoming technological barriers while increasing reliability, refining control methodologies, and enhancing user experience and acceptance. This paper reviews soft robotics and outlines its advantages in scenarios involving human–robot interaction.

Lower Limb Joint Angle Prediction Based on Multistream Signaling and Quantile Regression, Temporal Convolution Network–Bidirectional Long Short-Term Memory Network Neural Network

In recent years, the increasing number of patients with spinal cord injuries, strokes, and lower limb disabilities has led to the gradual development of rehabilitation-assisted exoskeleton robots. A critical aspect of these robots is their ability to accurately sense human movement intentions to achieve smooth and natural control. This paper describes research carried out on predicting the motion angles of human lower limb joints. Based on the design of a signal acquisition system for physiological muscle signals and inertial measurement unit (IMU) data, a hybrid neural network prediction model (QRTCN-BiLSTM) and a single neural network prediction model (QRBiLSTM) were constructed using quantile regression, temporal convolution network (TCN) and bidirectional long short-term memory network (BiLSTM), respectively. At the same time, 7-channel surface electromyographic signals (sEMG) and 12-channel IMU data from hip and knee joints were collected and input into the QRBiLSTM and QRTCN-BiLSTM models to unfold the training and analyze the comparison. The results show that the QRTCN-BiLSTM model can more accurately infer human movement intention and provide a more reliable and accurate prediction tool for human–robot interaction research in rehabilitation robotics.

Affordance of Internet of Things for educational resources management for E-learning domain

The Internet of Things (IoT) offers dual dimensions of affordance for educational resources management (ERM), particularly in a Comprehensive open distance e-learning institution in South Africa. The affordance of IoT for educational resources management is not well articulated in a CODEL institution. The study aimed to establish the role of IoT in the administration and management of educational resources. Technology affordance theory is used to establish the role, perceptions, and causality of IoT affordance in ERM. The research opted for the qualitative approach to establish the role and causality of the IoT affordance of ERM. The study found that the CODEL institution is IoT-driven when handling ERM. The main contribution relates to two propositions such as South African higher education institutions, including the CODEL institution, require the articulation and realignment of an IoT-driven business enterprise system for the implementation of OER in tuition; and in an IoT-driven context such as CODEL, where OER are implemented, there is a motive for academics and institutions to develop an Artificial Intelligence or interactive robot for creating and locating OER. It suggests that CODEL should realign its business enterprise system with IoT-driven infrastructure and adopt artificial intelligence practices for OER advancement. Future research should investigate the availability of IoT in all South African higher education institutions.

SincNet-Based Speaker Identification for Robotic Environments with Varying Human–Robot Interaction Distance

As human–robot interaction (HRI) becomes increasingly significant, various studies have focused on speaker recognition. However, few studies have explored this topic in the specific environment of home service robots. Notably, most existing research relies on databases composed of English-language data, while studies utilizing Korean speech data are exceedingly scarce. This gap underscores the need for research on speaker recognition in robotic environments, specifically using Korean data. In response, this paper conducts experiments using a speaker recognition database tailored to the Korean language and set in a robotic context. The database includes noise generated by robot movement as well as common environmental noise, accounting for variable distances between humans and robots, which are partitioned accordingly. The deep learning model employed is SincNet, with experiments conducted under two settings for the SincNet filter parameters: one with learnable parameters and the other with fixed values. After training the model with data collected at varying distances, performance was tested across these distances. Experimental results indicate that SincNet with learnable parameters achieved a peak accuracy of 99%.

Requirements for a Basic Student Course in Robotics and Human–Robot Interaction—A User-Centered Approach

Due to an increasing number of robots in the working world, the interaction between humans and robots will become more and more frequent. Hence, the research field of human–robot collaboration is becoming progressively relevant and should therefore be included in students’ education as early as possible. This paper deals with the requirements of a basic course for university students of interdisciplinary studies like Engineering Psychology or Human Factors. The goal of the course is to provide an adequate training for the students in order to gain a technical basis to design human–robot collaboration in a user-centered way in their future working life. Following a user-centered approach a narrative description and analysis of the context of use with contextual interviews were conducted. Overall, 12 subjects of the identified user groups (1) students studying Engineering Psychology, (2) students with knowledge in robotics and (3) graduates of the Engineering Psychology program participated in the contextual interviews. With these interviews, 47 user and stakeholder needs and 39 user requirements were derived. Based on the results, relevant content of a basic student course was defined, structured and prioritized. The requirements and demands are summarized in a recommendation for action and further steps are presented.

Sensors, Techniques, and Future Trends of Human-Engagement-Enabled Applications: A Review

Human engagement is a vital test research area actively explored in cognitive science and user experience studies. The rise of big data and digital technologies brings new opportunities into this field, especially in autonomous systems and smart applications. This article reviews the latest sensors, current advances of estimation methods, and existing domains of application to guide researchers and practitioners to deploy engagement estimators in various use cases from driver drowsiness detection to human–robot interaction (HRI). Over one hundred references were selected, examined, and contrasted in this review. Specifically, this review focuses on accuracy and practicality of use in different scenarios regarding each sensor modality, as well as current opportunities that greater automatic human engagement estimation could unlock. It is highlighted that multimodal sensor fusion and data-driven methods have shown significant promise in enhancing the accuracy and reliability of engagement estimation. Upon compiling the existing literature, this article addresses future research directions, including the need for developing more efficient algorithms for real-time processing, generalization of data-driven approaches, creating adaptive and responsive systems that better cater to individual needs, and promoting user acceptance.

Guest editorial: The current landscape and research priorities of human–robot interactions in hospitality and tourism

Guest editorial: The current landscape and research priorities of human–robot interactions in hospitality and tourism

BEATRIX: An open source humanoid head platform for robotics teaching and research

This paper introduces BEATRIX, a novel robotic head designed to bridge the gap between theoretical knowledge and practical experience in the field of robotics at universities. The BEATRIX robot comprises a head actuated by a neck-like mechanism with three stepper motors, two cameras and two microphones for acquisition of visual and audio information from the environment. The robot can be connected to any external computer for the design and implementation of algorithms for applications in human–robot interaction. The proposed robotic platform has been used successfully with undergraduate and master students implementing tasks such as face detection and tracking, sound detection and tracking, robot control and graphical user interfaces. This paper includes lists of all the robot components, assembly instructions, and links to all CAD and software files, facilitating replication and further exploration. The robot design and integration of visual and audio sensors enables the development of engaging educational tutorials and robot experiments, enhancing the teaching and learning experience in robotics.

Stiffness-fault-tolerant control strategy for elastic actuators with interaction impedance adaptation

Elastic actuators have the potential to enable safe interaction and energy efficient mobility, making them suitable for physical human–robot interaction. However, their increased complexity makes technical faults and their prevention a relevant research topic, particularly considering faults in elastic and kinematic elements. In this article we investigate a stiffness-fault-tolerant control strategy for elastic actuators, based on impedance control, which compensates for internal faults and adapts to a desired interaction impedance behavior. We analyze the control strategy regarding its stability, and adapt it to the dynamic characteristics of two systems: a mechanically adjustable compliance actuator (MACCEPA) and a series–parallel elastic actuator (+SPEA), highlighting the strategy’s general applicability to multiple actuator designs, considering nonlinear and redundant characteristics. Experimental validation with these systems shows that the control strategy is capable of accurately tracking reference output trajectories and adapting interaction characteristics, under fault and disturbance conditions, showcasing the versatile applicability of the strategy while achieving fault-tolerance.

A Knowledge Transfer-Based Personalized Human–Robot Interaction Control Method for Lower Limb Exoskeletons

A Knowledge Transfer-Based Personalized Human–Robot Interaction Control Method for Lower Limb Exoskeletons

Multimodal Human–Robot Interaction Using Gestures and Speech: A Case Study for Printed Circuit Board Manufacturing

In recent years, technologies for human–robot interaction (HRI) have undergone substantial advancements, facilitating more intuitive, secure, and efficient collaborations between humans and machines. This paper presents a decentralized HRI platform, specifically designed for printed circuit board manufacturing. The proposal incorporates many input devices, including gesture recognition via Leap Motion and Tap Strap, and speech recognition. The gesture recognition system achieved an average accuracy of 95.42% and 97.58% for each device, respectively. The speech control system, called Cellya, exhibited a markedly reduced Word Error Rate of 22.22% and a Character Error Rate of 11.90%. Furthermore, a scalable user management framework, the decentralized multimodal control server, employs biometric security to facilitate the efficient handling of multiple users, regulating permissions and control privileges. The platform’s flexibility and real-time responsiveness are achieved through advanced sensor integration and signal processing techniques, which facilitate intelligent decision-making and enable accurate manipulation of manufacturing cells. The results demonstrate the system’s potential to improve operational efficiency and adaptability in smart manufacturing environments.

Time-Varying Preference Bandits for Robot Behavior Personalization

Robots are increasingly employed in diverse services, from room cleaning to coffee preparation, necessitating an accurate understanding of user preferences. Traditional preference-based learning allows robots to learn these preferences through iterative queries about desired behaviors. However, these methods typically assume static human preferences. In this paper, we challenge this static assumption by considering the dynamic nature of human preferences and introduce the discounted preference bandit method to manage these changes. This algorithm adapts to evolving human preferences and supports seamless human–robot interaction through effective query selection. Our approach outperforms existing methods in time-varying scenarios across three key performance metrics.