Multirotor drones are widely used in fields such as environmental monitoring, agricultural inspection, and package delivery, but they still face numerous challenges in durability and aerial operation capabilities. To address these issues, this paper presents a biomimetic leg-claw mechanism (LCM) inspired by the biomechanics of birds. The claw of the LCM adopts a bistable gripper design that can rapidly close through external impact or actively close via the coordination of internal mechanisms. Additionally, its foldable, parallelogram-shaped legs bend under external forces, stretching the main tendon. A ratchet and pawl mechanism at the knee joint locks the leg in the bent position, thereby enhancing the gripping force of the claw. This paper calculates and experimentally verifies the degrees of freedom in different states, the forces required to open and close the gripper, the application scenarios of active and passive grasping, and the maximum load capacity of the mechanism. Furthermore, perching experiments demonstrate that the LCM enables the drone to perch stably on objects of varying diameters.

Prolonged and high-intensity human–robot interaction can cause muscle fatigue. This fatigue leads to changes in both the time domain and frequency domain of the surface electromyography (sEMG) signals, which are closely related to human body movements. Consequently, these changes affect the accuracy and stability of using sEMG signals to recognize human body movements. Although numerous studies have confirmed that the median frequency of sEMG signals decreases as the degree of muscle fatigue increases—and this has been used for classifying fatigue and non-fatigue states— there is still a lack of quantitative characterization of the degree of muscle fatigue. Therefore, this paper proposes a method for quantitatively characterizing the degree of muscle fatigue during periodic exercise, based on the high-frequency components obtained through ensemble empirical mode decomposition (EEMD). Firstly, the sEMG signals of the estimated individuals are subjected to EEMD to obtain the high-frequency components, and the short-time Fourier transform is used to calculate the median frequency (MF) of these high-frequency components. Secondly, the obtained median frequencies are linearly fitted, and based on this, a standardized median frequency distribution range (SMFDR) of sEMG signals under muscle fatigue is established. Finally, a muscle fatigue estimator is proposed to achieve the quantification of the degree of muscle fatigue based on the SMFDR. Experimental validation across five subjects demonstrated that this method effectively quantifies cyclical muscle fatigue, with results revealing the methodology exhibits superiority in identifying multiple fatigue states during cyclical movements under consistent loading conditions.

Addressing the issue of excessive manual intervention in discharging fermented grains from underground tanks in traditional brewing technology, this paper proposes an intelligent grains-out strategy based on a multi-degree-of-freedom hybrid robot. The robot’s structure and control system are introduced, along with analyses of kinematics solutions for its parallel components and end-effector speeds. According to its structural characteristics and working conditions, a visual-perception-based motion control method of discharging fermented grains is determined. The enhanced perception of underground tanks’ positions is achieved through improved Canny edge detection algorithms, and a YOLO-v7 neural network is employed to train an image segmentation model for fermented grains’ surface, integrating depth information to synthesize point clouds. We then carry out the downsampling and three-dimensional reconstruction of these point clouds, then match the underground tank model with the fermented grain surface model to replicate the tank’s interior space. Finally, a digging motion control method is proposed and experimentally validated for feasibility and operational efficiency.

Vessel segmentation is a fundamental task in medical image analysis and plays an important role in disease diagnosis and treatment assessment. However, existing segmentation methods often show limited adaptability to feature extraction from single-channel X-ray coronary angiograms, which restricts their performance in segmenting small vessels and low-contrast vascular regions. To address these limitations, this study proposes a Channel-Attention U-Net, termed CA-UNet, which integrates residual connections and a channel attention mechanism. Based on the conventional encoder–decoder architecture of U-Net, the proposed method introduces a residual-enhanced double-convolution block to alleviate gradient vanishing in deeper networks. In addition, a dual-pooling channel attention module is incorporated to enhance the selection of discriminative vascular features. Furthermore, the data loading, normalization, and augmentation strategies are optimized to improve the adaptability of the network to single-channel PGM grayscale images. Under three-fold out-of-fold evaluation, CA-UNet achieved the highest mean Dice coefficient (0.7450) and IoU (0.5972) among the evaluated models, while maintaining real-time-rate inference at 41.7 frames per second. These results indicate that CA-UNet provides an effective balance of segmentation accuracy, stability, and computational efficiency for vessel segmentation.

Preliminary estimation of lower-limb motor function is important in rehabilitation research, especially for biomechanical assessment of post-stroke hemiplegic gait. However, subject-specific musculoskeletal modeling in this population is challenging because standard maximum voluntary contraction (MVC) testing is often unsafe or unreliable for normalizing surface electromyography (sEMG) signals. To address this limitation, a normalized correction coefficient was introduced for pathological sEMG preprocessing, and an improved Hill-type muscle model (iHMM) was established to account for submaximal activation conditions. By combining inverse dynamics, static optimization, and a subject-specific lower-limb dynamic model, the proposed framework was used to estimate musculotendon force, knee joint torque, knee joint kinematics, and shank center-of-mass trajectory. In a preliminary validation involving six hemiplegic subjects, the predicted knee joint torques showed moderate to good agreement with the reference results, with correlation coefficients ranging from 0.724 to 0.807 and RMSE values ranging from 3.872 to 7.814 Nm. These preliminary results support the feasibility of the proposed framework for subject-specific biomechanical analysis of the hemiplegic lower extremity and suggest its potential utility in individualized rehabilitation assessment.