With advancements in artificial intelligence, wearable motion recognition systems based on flexible nanomaterial sensors exhibit excellent potential for harmonious human–machine interaction. However, the sensing stability and demand of large‐scale arrays limit the application of flexible nanomaterial sensors. Herein, a data glove system based on simple multiwalled carbon nanotube (MWCNT) sensors and a lightweight deep‐learning algorithm to achieve accurate gesture recognition is proposed. A regional‐crack mechanism is introduced through the microspine structure to enhance the strain sensitivity. Moreover, an efficient signal processing strategy based on an adaptive wavelet threshold function to improve the robustness and anti‐interference of signals obtained from MWCNT sensors, which exhibit strong generalization and can be used in other nanomaterial strain sensor. Based on the depth‐wise separable convolution, a novel hybrid convolutional neural network (CNN) long short‐term memory (LSTM) model for gesture recognition is constructed. The proposed model achieves an average accuracy of 97.5% and recognition accuracy of 30 gestures with an average recognition time of 2.173 ms based on only five sensors. The fabricated data glove is a promising platform for low‐cost and wearable human–machine interaction that can be directly interfaced in applications such as robotic hands, smart cars, and first‐person shooting games.

Continuous monitoring of physical motion, which can be successfully achieved via a wireless flexible wearable electronic device, is essential for people to ensure the appropriate level of exercise. Currently, most of the flexible LC pressure sensors have low sensitivity because of the high Young’s modulus of the dielectric properties (such as PDMS) and the inflexible polymer films (as the substrate of the sensors), which don’t have excellent stretchability to conform to arbitrarily curved and moving surfaces such as joints. In the LC sensing system, the metal rings, as the traditional readout device, are difficult to meet the needs of the portable readout device for the integrated and planar readout antenna. In order to improve the pressure sensitivity of the sensor, the Ecoflex microcolumn used as the dielectric of the capacitive pressure sensor was prepared by using a metal mold copying method. The Ecoflex elastomer substrates enhanced the levels of conformability, which offered improved capabilities to establish intimate contact with the curved and moving surfaces of the skin. The pressure was applied to the sensor by weights, and the resonance frequency curves of the sensor under different pressures were obtained by the readout device connected to the vector network analyzer. The experimental results show that resonant frequency decreases linearly with the increase of applied pressure in a range of 0–23,760 Pa with a high sensitivity of −2.2 MHz/KPa. We designed a coplanar waveguide-fed monopole antenna used to read the information of the LC sensor, which has the potential to be integrated with RF signal processing circuits as a portable readout device and a higher vertical readout distance (up to 4 cm) than the copper ring. The flexible LC pressure sensor can be attached to the skin conformally and is sensitive to limb bending and facial muscle movements. Therefore, it has the potential to be integrated as a body sensor network that can be used to monitor physical motion.

Long-term and stable monitoring of bioelectrical signals represented by electrocardiogram (ECG) has a great application value for wearable electronics. The ECG monitoring require low-cost, flexible and robust electrical system that can work throughout daily activities. In this article, we propose a paper-assisted strategy to fabricate a tattoo ECG electrode based on the low-cost water transfer printing technology. Similar to the tattoo attached on the skin, the fabricated electrode allows complying with the skin deformation comfortably and accommodating the local strains. The ECG signals collected by the tattoo electrode have a high signal to noise ratio, robustness, mechanical stability and strong immunity to motion artifact even under the severe deformation of skin. The tattoo electrode enables convenient and long-period ECG monitoring during various activities, including exercising, sweating, rubbing, and flushing. As a proof-of-concept, a soft wireless ECG system is developed by integrating with the tattoo electrode, commercialized IC chips, and a low-energy Bluetooth module to achieve the functions of signal acquisition, data processing and communication. The measured results show that the proposed strategy has a promising application for wearable health monitoring system.

The integration of vision–language models (VLMs) with robotic systems represents a transformative advancement in autonomous task planning and execution. However, traditional robotic arms relying on pre-programmed instructions exhibit limited adaptability in dynamic environments and face semantic gaps between perception and execution, hindering their ability to handle complex task demands. This paper introduces GPTArm, an environment-aware robotic arm system driven by GPT-4V, designed to overcome these challenges through hierarchical task decomposition, closed-loop error recovery, and multimodal interaction. The proposed robotic task processing framework (RTPF) integrates real-time visual perception, contextual reasoning, and autonomous strategy planning, enabling robotic arms to interpret natural language commands, decompose user-defined tasks into executable subtasks, and dynamically recover from errors. Experimental evaluations across ten manipulation tasks demonstrate GPTArm’s superior performance, achieving a success rate of up to 91.4% in standardized benchmarks and robust generalization to unseen objects. Leveraging GPT-4V’s reasoning and YOLOv10’s precise small-object localization, the system surpasses existing methods in accuracy and adaptability. Furthermore, GPTArm supports flexible natural language interaction via voice and text, significantly enhancing user experience in human–robot collaboration.

Frequent monitoring of blood coagulation status is essential for patients receiving treatment with some oral anticoagulant agents. In this paper, we present a microelectromechanical film bulk acoustic resonator for the measurement of blood coagulation parameters. The resonator was made of an aluminum nitride piezoelectric film and operated in thickness shear resonance mode with a frequency of about 2 GHz. The resonant frequency showed a linear relationship with the viscosity of the environmental liquid over the wide range of 1–25 cP, falling within the physiological range of human blood. The coagulation process of human blood was monitored by following the frequency downshift due to the viscosity change. Therefore, the frequency response was used to determine quantitatively three clinically significant parameters being the enzymatic cascade time, the coagulation time and the clot degree. As a practical demonstration, the proposed micro-resonator was applied to monitor coagulation for one month in a patient taking the oral anticoagulant, warfarin, daily. The results measured by the resonator were consistent with those of the standard coagulometer. As a result of the excellent potential for integration, miniaturization and the availability of direct digital signals, the shear mode film bulk acoustic resonator has promising application for clinical and personal coagulation monitoring.