Life care for disabled or semi-disabled elderly has become an increasingly common problem in society. In this paper, a novel wheelchair-stretcher assistive robot, which can meet the physiological needs of patients, is investigated and designed. The following tasks are conducted: (1) the mecanum wheel is adopted as the executive device of the walking mechanism, and its kinematics is analyzed in detail. (2) A five-link mechanism with single degree of freedom is proposed to realize the folding motion of the robot. Through the minimum conclusive area method, the optimal sizes of the armrests link and the side link are 507.9, and 332.5 mm, respectively. Based on the force analysis of the linkage mechanism, six torsion springs and RV (rotate vector) reduction motor are used as the driving device, which reduces the driving torque of the motor. (3) Based on the STM32 (STMicroelectronics 32-bits Microcontroller) chip, and combined with the theoretical analysis, the mechanical structure and the control system of the whole prototype are designed, and the feasibility of each module is verified by experimental research. The results confirm that the proposed robot has good performance, and that the control algorithm for the walking mechanism and the lifting mechanism are suitable.

Hand rehabilitation is critical to the recovery of post-stroke patients. However, designing a modular mechanism of the hand to improve the human-machine compatibility and precision of operation is still a challenge. This paper proposes a new type of hand exoskeleton rehabilitation robot with nine degrees of freedom. With the flexible rods, the passive range of motion for finger adduction/abduction is extended under the premise of independent flexion/extension of the metacarpophalangeal and proximal interphalangeal joint. Based on hand anatomy, the relationship between the offset of the metacarpophalangeal joint and the body height in the process of flexion and extension is discussed, and it is applied to the structure optimization and control system. The genetic algorithm is employed to achieve the size optimization, and the kinematics is analyzed. Finally, a prototype is built and preliminary experiments are carried out, including the range of motion and the grasping ability of the robot. The experimental results show that the robot can realize the patients’ hand rehabilitation function and has certain adaptability.

Most existing finger rehabilitation robots are structurally complex and cannot be adapted to multiple work conditions, such as clinical and home. In addition, there is a lack of attention to active adduction/abduction (A/A) movement, which prevents stroke patients from opening the joint in time and affects the rehabilitation process. In this paper, an end-effector finger rehabilitation robot (EFRR) with active A/A motion that can be applied to a variety of applications is proposed. First, the natural movement curve of the finger is analyzed, which is the basis of the mechanism design. Based on the working principle of the cam mechanism, the flexion/extension (F/E) movement module is designed and the details used to ensure the safety and reliability of the device are introduced. Then, a novel A/A movement module is proposed, using the components that can easily individualized design to achieve active A/A motion only by one single motor, which makes up for the shortcomings of the existing devices. As for the control system, a fuzzy proportional-derivative (PD) adaptive impedance control strategy based on the position information is proposed, which can make the device more compliant, avoid secondary injuries caused by excessive muscle tension, and protect the fingers effectively. Finally, some preliminary experiments of the prototype are reported, and the results shows that the EFRR has good performance, which lays the foundation for future work.

Patient transfer has always been a difficult problem in the hospital. For medical staff, there are problems including high risk of infection, heavy physical labor and low efficiency of transfer; for patients, there are problems including poor comfort and secondary injury. In this paper, a novel bilateral patient transfer robot is investigated and designed. The following tasks are conducted: (1) Based on the process of patient transfer, a transfer model, which consists of two degrees of freedom, is proposed, and the working principle of bilateral patient transfer robot is obtained and analyzed in detail. (2) Force analysis of the patient transfer robot is conducted. The corresponding relationship between the patient comfort and the insertion angle is proposed, and the optimal sizes of mechanical structure are obtained. (3) Based on the theoretical analysis, the mechanical structure and the control system of the robot are designed, and the prototype is manufactured. (4) Experimental research is conducted. The results show that the prototype can complete the required motion performance with a carrying capacity up to 150 kg and patient comfort is excellent. The results of this paper prove that this kind of patient transfer robot has good performance, it can also reduce the burden on medical staff.

Accurate and rapid detection of anatomical structures, such as the glottis, is critical during tracheal intubation (TI) to ensure patient safety and procedural success. However, it remains a challenge due to the limited field of view and computational resources of video laryngoscopy, especially for difficult airway situations. Existing deep learning (DL) models struggle to balance high accuracy and real-time clinical deployment. To address these issues, we propose TI-YOLO (TI-You Only Look Once), a lightweight and efficient object detection model built upon the YOLOv11 architecture. TI-YOLO introduces the Bidirectional Feature Pyramid Network (BiFPN) module for multi-scale feature fusion, effectively enhancing the ability to detect anatomical structures of different sizes. TI-YOLO integrates the Deformable Attention Transformer (DAT) module to enhance the perception of crucial regions, improving detection accuracy and robustness. To further reduce the consumption of computational resources while maintaining efficiency, TI-YOLO is optimized by reconstructing the backbone based on MobileNetV4. Furthermore, TI-YOLO employs the Slide Weight Function (SWF) as a loss function during model training to mitigate the class imbalance within the dataset. One self-built dataset is used to validate the effectiveness of TI-YOLO. Compared to the original YOLOv11, TI-YOLO achieves mean Average Precision at IoU 0.50 (mAP50) scores of 0.902, with improvements of 3.8%. Meanwhile, TI-YOLO balances detection accuracy and computational efficiency with a 10.5% reduction in floating-point operations (FLOPs) and a 28.9% reduction in parameters, and the model weight is only 4.6 MB. Additionally, to evaluate TI-YOLO real-time inference capability, we quantize and deploy it on a low-cost embedded OrangePi 5 platform. The inference speed reaches over 50 frames per second (FPS), meeting real-time clinical requirements.