Search

The current research examined the link between the informativeness of tourist-chatbot interaction, destination image, and visit intention in two studies. In the first study, 111 participants were asked to interact with ChatGPT about a destination (i.e. Batumi) for 5–10 min. The conceptual model was analyzed using the Structural Equation Modelling framework. Findings suggested that the informativeness of tourist-chatbot interaction would increase destination image and visit intention. Destination image was also directly and positively related to visit intention. Specifically, destination image mediated the link between the informativeness of tourist-chat bot interaction and visit intention. A second study (N = 184) was conducted, in which the entire procedure was the same as the first study, to test the replicability of the current findings. Consequently, all results remained consistent with the first study. This is the first study to show the mediating role of destination image in the link between human-machine interaction and visit intention in tourism research. Thus, the findings would expand the current understanding regarding the role of human-machine interaction on attitude and behaviour. [ABSTRACT FROM AUTHOR]

The design of modern production systems is requiring more and more integration of human-in-the-loop principles introduction of new working paradigms, where humans and machines cooperate and interact with each other. Such practices are reinforcing the need for human-centric smart manufacturing (HSM). Today, human-cyber-physical systems (HCPSs) allow to intrinsically meet the industrial complexity and bring insights in the development and implementation of HSM. In this context, the growing interest of academics and practitioners on the three key concepts of "sustainability, human-centric, and resiliency" related to the Industry 5.0 (I5.0) framework is justified. The aim of this study is to present a methodological approach for the design of adaptive human-cyber-physical systems to meet the I5.0 objectives. Starting from the analysis of the as-is user and process-related conditions, this innovative closed-loop framework guarantees a step-by-step tuning logic according to specified objectives. A use case concerning a quality control procedure for the Oil&Gas sector is proposed, where a preliminary HCPS prototype has been developed and tested. The solution provides a contextual support throughout all the value chain to the diverse activities carried out by design engineers up to end-users by offering a valuable operator's user experience (UX). The main results suggested that the conceived strategy overcomes traditional limitations of the technical drawings by integrating model-based engineering with human-centred design (HCD) principles. The systematic introduction of HCPS allows to redesign the human–machine interaction according to new paradigms of collaboration between the humans and the smart factory. [ABSTRACT FROM AUTHOR]

AFBI E-skin with good biocompatibility integrating antifouling, antibacterial, and breathability functions is developed for self-powered motion monitoring and ultra-long-range human-machine interaction. E-skin shows "dynamic-static" synergistic antibacterial strategy by combination of triboelectric effect and PANI charge action. The ultra-long-range human-machine interaction control system, enables synchronized hand gestures between human hand and robotic hand in any internet-covered area worldwide theoretically. [Display omitted] • AFBI E-skin enables stable signal output for motion monitoring, even when splashed with water. • AFBI E-skin integrates antifouling, antibacterial, biocompatibility and breathability. • AFBI E-skin shows a synergistic effect of "dynamic-static" antibacterial activity. • Ultra-long-range human-machine interaction control system developed using AFBI E-skin. Electronic skin (e-skin) inspired by the sensory function of the skin demonstrates broad application prospects in health, medicine, and human–machine interaction. Herein, we developed a self-powered all-fiber bio-inspired e-skin (AFBI E-skin) that integrated functions of antifouling, antibacterial, biocompatibility and breathability. AFBI E-skin was composed of three layers of electrospun nanofibrous films. The superhydrophobic outer layer Poly(vinylidene fluoride)-silica nanofibrous films (PVDF-SiO 2 NFs) possessed antifouling properties against common liquids in daily life and resisted bacterial adhesion. The polyaniline nanofibrous films (PANI NFs) were used as the electrode layer, and it had strong "static" antibacterial capability. Meanwhile, the inner layer Polylactic acid nanofibrous films (PLA NFs) served as a biocompatible substrate. Based on the triboelectric nanogenerator principle, AFBI E-skin not only enabled self-powered sensing but also utilized the generated electrical stimulation for "dynamic" antibacterial. The "dynamic-static" synergistic antibacterial strategy greatly enhanced the antibacterial effect. AFBI E-skin could be used for self-powered motion monitoring to obtain a stable signal output even when water was splashed on its surface. Finally, based on AFBI E-skin, we constructed an ultra-long-range human-machine interaction control system, enabling synchronized hand gestures between human hand and robotic hand in any internet-covered area worldwide theoretically. AFBI E-skin exhibited vast application potential in fields like smart wearable electronics and intelligent robotics. [ABSTRACT FROM AUTHOR]

Featured Application: This work can be applied to the display calibration and characterization of augmented reality glasses with a retinal scan architecture. Augmented reality display performance depends strongly on features of the human visual system. This is especially true for retinal scan glasses, which use laser beam scanning and transparent holographic optical combiners. Human-centered approaches allow us to go beyond conventional optical metrology and evaluate display performance as it is perceived in actual augmented reality use cases. Here, we first present a theoretical formula for the retinal scan luminance and ambient contrast ratio calculated from optical powers, wavelengths, field of view, and human pupil diameter. As a promising insight, we found that the pupil diameter dependence is beneficial in assimilating the virtual image luminance to the ambient luminance. Second, we designed and performed a psychophysical experiment to assess perceived resolution in augmented reality settings using a fully functional retinal scan glasses prototype. We present the results of the trials and illustrate how this approach can be used in the further development of augmented reality smart glasses. [ABSTRACT FROM AUTHOR]

Surgical robots are designed to provide enhanced precision and dexterity compared to manual surgical procedures, which mainly rely on multimodal sensing technologies for the surgeon to seamlessly operate the robotic arms and instruments. Compared with single-mode sensors, optical and mechanical bi-modal sensors provide improved precision, enhanced safety, and robustness of human-machine interaction systems. Here, the template-guided and pneumatic printing technologies are combined to construct perovskite and graphene parallel structures with both optical and mechanical sensing capabilities. The printed uniformly crystallized perovskite microstructure exhibits fast and sensitive photoelectric response characteristics, enabling shadow recognition functionality. The combination of graphene and elastic rubber endows the great printability to prepare parallel structures near the perovskite arrays for force sensing capabilities. Thus, the printed perovskite and graphene structures possess non-contact optical sensing capabilities to detect hand position by recognizing shadows between the hand and the sensor, as well as contact mechanical sensing capabilities to detect touch force applied by the hand. It provides a synergistic platform for real-time and multidimensional feedback to improve human-machine interaction. [ABSTRACT FROM AUTHOR]

The control of swarms has emerged as a paradigmatic example of human-autonomy teaming. This review focuses on understanding human coordination behaviours, while controlling evasive autonomous agents, to inform the design of human-compatible teammates. We summarize the solutions employed by human dyads, as well as the verbal communication and division of labour strategies observed in four-person teams using virtual simulations. Additionally, we provide an overview of the design of artificial agents that replicate human-like dynamics using task-dynamical models, and which can be integrated into human-autonomy teams. Finally, we conclude with open questions regarding the preservation of situation awareness and trust within human-autonomous swarming teams. This article is part of the theme issue 'The road forward with swarm systems'. [ABSTRACT FROM AUTHOR]

Objective: To reduce hip joint muscles' activation during walking with an active hip exoskeleton. Background: Few studies examine the optimal active assistance timing of the hip exoskeleton based on muscle activation characteristics. Methods: Sixteen gender-balanced healthy adults (mean age 28.8 years) performed four tasks (each over 20 min). Tasks were different in loading and assistance. Muscle activation was collected by surface electromyography. The collected oxygen consumption evaluated the performance of the proposed active assistance strategy. Results: Experimental results verified that lower muscle activation and metabolism could be achieved when the active assistance gait phase was 9–60% of the gait cycle than that of all-gait-cycle active assist. Conclusions: Regulating the exoskeleton's active assistance timing according to muscles' activation characteristics can improve functional assistance. [ABSTRACT FROM AUTHOR]

The cockpit is evolving from passive, reactive interaction toward proactive, cognitive interaction, making precise predictions of driver intent a key factor in enhancing proactive interaction experiences. This paper introduces Cockpit-Llama, a novel language model specifically designed for predicting driver behavior intent. Cockpit-Llama predicts driver intent based on the relationship between current driver actions, historical interactions, and the states of the driver and cockpit environment, thereby supporting further proactive interaction decisions. To improve the accuracy and rationality of Cockpit-Llama's predictions, we construct a new multi-attribute cockpit dataset that includes extensive historical interactions and multi-attribute states, such as driver emotional states, driving activity scenarios, vehicle motion states, body states and external environment, to support the fine-tuning of Cockpit-Llama. During fine-tuning, we adopt the Low-Rank Adaptation (LoRA) method to efficiently optimize the parameters of the Llama3-8b-Instruct model, significantly reducing training costs. Extensive experiments on the multi-attribute cockpit dataset demonstrate that Cockpit-Llama's prediction performance surpasses other advanced methods, achieving BLEU-4, ROUGE-1, ROUGE-2, and ROUGE-L scores of 71.32, 80.01, 76.89, and 81.42, respectively, with relative improvements of 92.34%, 183.61%, 95.54%, and 201.27% compared to ChatGPT-4. This significantly enhances the reasoning and interpretative capabilities of intelligent cockpits. [ABSTRACT FROM AUTHOR]

Leveraging the fluidity and excellent conductivity of liquid metal (gallium‐indium alloy), liquid metal (LM) can be utilized to manufacture flexible and stretchable electronic products for applications in soft robotics, wearable devices, and human–machine interaction. However, the high surface tension and low surface adhesion of LM hinder its patterning and high‐resolution fabrication of soft electronics. Here a recyclable LM‐silicon dioxide (LMS) ink is proposed. Under stirring, silicon dioxide (SiO2) particles are encapsulated by the oxide layer of the LM, consuming the oxide layer. Meanwhile, gallium in the LM reacts with oxygen from the air to form a new oxide layer, enhancing the adhesion of the LM to the substrate while maintaining its conductivity. The in‐situ printing of LMS ink is verified on various materials (e.g., paper, polymer, and glass) with a resolution of up to 165 µm and an exceptional conductivity of ≈6.53 × 106 S m−1. The printed patterns can be erased with an anhydrous ethanol solution, allowing the recovered LMS ink to be reused for multiple writing cycles. The general method for direct LM circuits printing can fabricate various wearable sensors for soft electronic devices and human–machine interaction. [ABSTRACT FROM AUTHOR]

Sensor arrays are essential for effective human‐machine interaction (HMI), enabling systems to perceive, interpret, and respond to human actions. However, traditional sensor arrays often involve complex manufacturing processes and excessive wiring due to point‐to‐point connections. To address these challenges, a type of self‐powered, low‐cost sensor array is described that minimizes these issues. Utilizing the principles of contact electrification and electrostatic induction, the array consists of two or more interconnected electrostatic induction units. When a unit is triggered, it generates a unique voltage signal relative to other connected units, resulting in diverse signals with specific waveforms and peak magnitudes. This diversity allows the sensor array to output multiple addressable signals through a limited number of channels or a single channel, enhancing efficiency and simplicity. The versatility of these sensor arrays in various HMI applications is demonstrated, including game joysticks, electronic skins, robot controllers, and leaf‐based electronic piano keyboards, showcasing their potential to transform HMI technology. [ABSTRACT FROM AUTHOR]

The dynamic electromechanical coupling behavior of composite materials is highly dependent on external excitation frequency. While degradable biomolecular materials typically exhibit lower piezoelectric coefficients compared to ceramics, neglecting their frequency‐dependent performance in the design of piezoelectric devices further leads to less efficient utilization of their piezoelectric properties. This oversight greatly hinders the practical application of these materials. To address this, a novel fractional derivation (FD) theory‐assisted model is introduced to reversely design the glycine‐polyvinyl alcohol (PVA) thin films for versatile enhanced bio‐applications. An electromechanical coupling model incorporating FD theory is developed to learn the relationships between FD parameters, film dimensions, and dynamic electromechanical properties. This model accurately predicts the electromechanical performance of the films across a wide frequency range, validated by both finite element simulations and experimental results. This therefore allows to establish key design principles for piezoelectric thin film in bioenergy harvesting and sensing, by tailoring thin film parameters to enhance the piezoelectric performance at specific stimuli frequencies. Demonstrations of glycine‐PVA film devices guided by this model reveal excellent performance in ultrasonic energy harvesting and carotid artery bio‐signal sensing. This study provides a robust theoretical framework for designing and optimizing biodegradable piezoelectric materials for various practical applications. [ABSTRACT FROM AUTHOR]