Cooperative rehabilitation enhances engagement, task performance, and social-motor interaction, yet it demands physical co-presence: users must transmit forces, coordinate movements, and infer intent through haptic contact. Telerehabilitation promises to expand access for patients constrained by distance, mobility, or clinical disparities, yet current techniques remain predominantly audiovisual while leaving users haptically and physically isolated. Here, we introduce HaptiNet, a networked haptic robotic system enabling physical co-presence for geographically distributed users via force-mediated interaction. Each robotic terminal features a low-inertia, long-stroke design with high force-feedback capacity, tailored for haptic rendering in upper-limb training. Building on these terminals, HaptiNet creates a distributed haptic network with an imitation-learning-based delay compensator, enabling users to physically perceive and coordinate with one another over distance. We validated HaptiNet in 284 healthy participants and 111 patients with neurological impairments across progressively realistic settings, including laboratory tests, cross-city deployments, and clinical applications. HaptiNet preserved task-level force rendering consistency across single-user and multi-user scenarios. Compared with solo and visual cooperative training, haptic cooperation improved task performance by 24

The multiuser haptic-enabled robotic system (M-Hers) facilitates shared control among human operators through task-dependent authority allocation, where interaction relationships are typically dictated by task requirements. However, some of these relationships can be nonpassive, generating excess energy that violates passivity constraints and compromises system stability. To address this, we first introduce the interaction architecture (IA) to formalize how operators influence task execution. Based on this framework, we propose a tank-based two-layer task model that ensures system passivity despite nonpassive IAs. This model comprises a virtual object (VO) layer for task rendering and a virtual system (VS) layer that passively executes nonpassive IA behaviors. The VS layer uses a global energy tank to compensate for IA-induced energy violations and modify the VO model when tank energy is depleted. This structure decouples task rendering from low-level robotic control, enabling seamless integration of an arbitrary number of robots with heterogeneous dynamics and control modes. Simulation and experimental results validate the proposed method’s scalability, flexibility, and effectiveness in preserving passivity while accurately realizing diverse IAs. This approach paves the way for scalable and easy-to-deploy control framework that supports multiuser haptic interaction.

Despite extensive investigations into the multi-user haptic-enabled robotic system (M-Hers), achieving scalable control design in the presence of non-passive human operators remains a key challenge. This is primarily due to the increasing complexity of stability conditions and interaction coupling as the number of operators grows. In this study, we address this challenge in two steps. First, we introduce the individual interaction environment (IIE) to isolate the passivity violations, which facilitates the independent control design for each human-robot subsystem, thereby enhancing the scalability with respect to the number of subsystems. Second, within the IIE framework, we identify passivity-violating components caused by partners' active behaviors and propose a novel augmented tank-based controller (ATBC) to guarantee passive IIE while maintaining high rendering accuracy. Specifically, the ATBC employs an energy-related power regulation strategy to enhance interaction safety and a time-varying control gain to mitigate the negative effects of power regulation on rendering fidelity. We validated the proposed method through collaborative haptic tasks on a customized M-Hers composed of three robots in four different scenarios. Comparative studies demonstrate that our approach effectively ensures IIE passivity in the presence of active human behaviors, while ensuring high reproducibility and achieving a favorable balance between passivity and rendering accuracy.

Bimanual motor tasks are commonplace in daily life and are often integrated into rehabilitation therapies. However, previous brain-computer interface (BCI) for robotic-assisted rehabilitation predominantly focused on motor imagery (MI) of single limb. Moreover, the BCI-driven robotic system has been plagued due to the difficulty of decoding electroencephalography (EEG) accurately and robustly. In this study, we presented a novel EEG-MI-BCI system for online bilateral robot-assisted training, consisting of 1) a bimanual EEG-MI paradigm involving the imagination of three coordinated movement directions (left, middle, and right) of both hands, and 2) a shared control strategy that relies on prior knowledge-based assistance for correcting direction decoding errors and robot autonomy for managing movement velocity. The experiment included two parts: a one-step bimanual EEG-MI task and a multi-step bimanual reaching task assisted by a robot. First, one-step offline and online decoding experiments were implemented to assess the feasibility of the proposed bimanual EEG-MI paradigm using six common models. The offline results from eight human participants indicated that all models achieved significantly higher average accuracy compared to the chance level (33.33%), with EEGNet yielding the highest accuracy of 52.93%. In addition, the optimal model, EEGNet, achieved an online accuracy of 49.67%. Second, an online multi-step task was implemented using the bimanual MI paradigm and shared control strategy. The average success rate was 48.33% without assistance, which increased to 71.67%, 80.00%, and 90.00% with assistance at levels of low, moderate, and high, respectively. These results demonstrated the online feasibility of decoding coordinated directions based on the developed EEG-MI-BCI system and real-time control of bilateral robot for potential rehabilitation therapies.

Robot-assisted ankle rehabilitation training imitating physician's professional techniques is highly important for promoting personalized training and improving clinical outcomes. In this work, we propose a two-level kernelized movement primitives (2-level-KMP) imitation learning algorithm under the kernelized movement primitives (KMP) framework, which reproduces physician's experience and optimizes the imitation trajectory during rehabilitation, to realize physician-level performance in robot-assisted ankle rehabilitation training. First, a KMP process combined with a Bayesian optimizer is used to imitate the rehabilitation trajectory. Second, the other KMP process is used to smooth the imitation trajectory further. Then the two KMP processes combined with patient-in-the-loop optimization (PILO) realize temporal rehabilitation adaptation. Finally, the 2-level-KMP algorithm is reproduced on a parallel ankle rehabilitation robot (PARR), which enables the patient's passive rehabilitation training to be empirical and adaptive. Ten ankle dysfunction patients were involved in clinical experiments, with the results showing that the proposed algorithm can accurately reproduce physician's trajectories and modulate trajectories based on patient's feedback. After ten rehabilitation exercises, the number of modulation points calculated from patient's torque feedback decreases by 85.19% on average compared with the beginning stage. A comparison between the 2-level KMP algorithm and existing algorithms shows that the 2-level-KMP algorithm can better ensure smoothness and retain the shape of the trajectory during trajectory modulation, ensuring the safety of ankle rehabilitation and retaining the experience of the physician.

In advancing brain-computer interface (BCI), force feedback has demonstrated potential in enhancing neurophysiological interactions during motor tasks. This study investigated the impact of force feedback on brain activity and the accuracy of decoding movement direction. We developed an electroencephalogram (EEG)-based BCI paradigm with four levels of force feedback (i.e., 0 N, 8 N, 16 N, 24 N) applied during right-hand movements to left and right directions. Six participants were involved to ensure robust results. Three deep learning models—DeepConvNet, ShallowConvNet, and EEGNet—were used to decode movement directions. Findings from event-related desynchronization/event-related synchronization (ERD/ERS) and movement-related cortical potentials (MRCPs) indicated that increased force feedback significantly enhanced the brain’s response to motor stimuli. The decoding results revealed that force feedback notably improved decoding accuracy of DeepConvNet and EEGNet, particularly under medium and high-intensity conditions. Specifically, three models demonstrated accuracy improvements of 11%, 4%, and 12% under high-intensity force feedback, respectively. These results suggest that specific force feedback enhances motor area responsiveness, improving movement intention decoding in BCI. Our study confirms the positive impact of force feedback on BCI performance, highlighting the potential of force feedback-based BCI systems.

Functional near-infrared spectroscopy (fNIRS) seems opportune for neurofeedback in robot-assisted rehabilitation training due to its noninvasive, less physical restriction, and no electromagnetic disturbance. Previous research has proved the cross-session reliability of fNIRS responses to non-motor tasks (e.g., visual stimuli) and fine-motor tasks (e.g., finger tapping). However, it is still unknown whether fNIRS responses remain reliable 1) in gross-motor tasks, 2) within a training session, and 3) for different training parameters. Hence, this study aimed to investigate the within-session reliability of fNIRS responses to gross-motor tasks for different training parameters. Ten healthy participants were recruited to conduct right elbow extension-flexion in three robot-assisted modes. The Passive mode was fully motor-actuated, while Active1 and Active2 modes involved active engagement with different resistance levels. FNIRS data of three identical runs were used to assess the within-session reliability in terms of the map- ( R 2 ) and cluster-wise ( Roverlap ) spatial reproducibility and the intraclass correlation (ICC) of temporal features. The results revealed good spatial reliability ( R 2 up to 0.69, Roverlap up to 0.68) at the subject level. Besides, the within-session temporal reliabilities of Slope, Max/Min, and Mean were between good and excellent (0.60 < ICC < 0.86). We also found that the within-session reliability was positively correlated with the intensity of the training mode, except for the temporal reliability of HbO in Active2 mode. Overall, our results demonstrated good within-session reliability of fNIRS responses, suggesting fNIRS as reliable neurofeedback for constructing closed-loop robot-assisted rehabilitation systems.

The haptic rendering function of bimanual rehabilitation robots is critical in promoting motor learning and neural plasticity. However, achieving high transparency and robust haptic rendering for diverse tasks remains challenging. The reason is that tasks with varying dynamic characteristics require distinct control architectures to maintain a balance between rendering accuracy and stability. To address this issue, we propose a unified control framework capable of adapting to various tasks. In this framework, tasks are classified into four types based on their dynamic characteristics. Aligned with the task type, the control architecture is reconstructed by invoking and integrating different encapsulated blocks, where each block functions as a subsystem with unique capabilities. To verify the proposed framework, a bimanual rehabilitation robotic system was developed and experimentally validated on eight human participants. Results indicate that the average force errors are less than 1 N for non-load moving tasks, and for tasks with a load of 20 N, the average force rendering accuracy exceeds 94%. The results confirm that the framework is capable of reaching a favorable compromise between stability and accuracy for various bimanual training tasks.

Physically-coupled bimanual tasks (activities where a force effect occurs between two human limbs) involve the coordination and cooperation of bilateral arms. Such uncertain contribution of two arms is often studied under static configuration, which is not sufficient to typify all activities of daily life (ADLs). This study aims to investigate people's bilateral force production and control in dynamic tasks. Experiments were conducted with a customized robotic system that is characterized with two handles and programmable force fields between them. Fourteen healthy right-handed human volunteers were instructed to generate force with each hand when performing predefined trajectory tracking tasks, in which the sum of forces contributed by the left and the right hand is required to equal a target force. Significant asymmetry was found in the force output between bilateral hands. With the homologous muscles activated synchronously, the contribution of the left hand was larger, while when the non-homogenous muscles were activated synchronously, the laterality was subject to the moving direction. In addition, when considering the force difference between two hands in terms of direction and magnitude, the former decreased with the increase of the target force, but the latter was more sensitive to moving directions. The results reveal the unique characteristics of non-isometric force control tasks compared with isometric ones.

Individuals with physical limb disabilities are often restricted to perform activities of daily life (ADLs). While efficacy of bilateral training has been demonstrated in improving physical coordination of human limbs, few robots have been developed in simulating people's ADLs integrated with task-specific force field control. This study sought to develop a bilateral robot for better task rendering of general ADLs (gADLs), where gADL-consistent workspace is achieved by setting linear motors in series, and haptic rendering of multiple bimanual tasks (coupled, uncoupled and semi-coupled) is enabled by regulating force fields between robotic handles. Experiments were conducted with human users, and our results present a viable method of a single robotic system in simulating multiple physically bimanual tasks. In future, the proposed robotic system is expected to be serving as a coordination training device, and its clinical efficacy will be also investigated.

Robot-assisted bilateral upper limb training helps to activate the secondary motor brain areas and improve arms’ coordinative capabilities for patients with neurological injuries. Due to the shared workspace of the patient and the robot, it is necessary to ensure human users’ safety in a compliant way. While several approaches have been proposed for safe human-robot interaction, few considered evaluation of human motor function to provide subject-specific and compliant motion constraints. This study proposes a safety metrics for bilateral training from two aspects. On one hand, a human-kinematics-based method is used to customize safe interactive workspace. On the other hand, a repulsive potential function strategy is employed to ensure movement safety when towards workspace boundary, and a performance-based fuzzy logic is developed as an adaptive law to deal with mechanical collision. The proposed strategy was preliminarily validated for bilateral upper limb training with an end-effector robotic system. Experimental results validated the effectiveness and potentiality of the proposed safety strategies.

以机器人辅助的上肢协调康复训练为研究对象,提出一种基于任务表现的自适应控制策略,为肢体运动功能障碍患者提供个性化的机器人辅助,旨在提高患者的主动运动参与度,实现高效的康复训练.首先,介绍上肢末端式双边康复平台以及协调训练任务.然后,引入临床运动评估参数与协调训练指标,采用模糊神经网络模型建立多任务指标与机器人导纳控制参数间的映射关系.最后,通过受试者参与的协调训练实验对所提出方法进行了验证,并与相关文献中的人机交互策略进行了对比分析.实验结果表明,本文方法具有较好的任务指标追踪效果和人机交互平稳性,能够自适应为患者提供个性化的机器人辅助,有助于提高受试者的训练积极性.

Electric motors have been widely used as the actuators of robot and automation systems. This paper aims at achieving the high-precision position control of motor drive systems. For this purpose, a robust control scheme is presented by combining the internal model principle, the sliding mode technique and the extended state observer (ESO). The PID-type controller is firstly designed by using the internal model control (IMC) rules. Since the analysis of the IMC system is performed via a sliding surface, a robust sliding mode control (SMC) law is then synthesized to enhance the control ability of the system to uncertainties. However, this robust solution should make a trade-off between the chattering attenuation and the control accuracy. To handle this drawback, a linear ESO is employed to compensate the modeling errors for a higher control accuracy. The stability analysis is provided via a Lyapunov-based method, and the superiority of the proposed approach was validated by comparative experiments on a motor drive platform.

Objective: To measure the impact of the speed of interface switching on the digital reading user experience on mobile terminals. Methods: The subjective scale scoring method and semi-structured interviews are used to test the influence of the speed of the digital reading interface switching on the user experience, to explore the feedback of the perceived speed of the subject, and collect the subjective feelings of the user after the user-product interaction process ends. And use the method of summarization to summarize the user feedback. Results: The most comfortable interface switching speed when humans read digitally, and the effect of interface switching speed on the psychological perception of users with different operational purposes. Conclusion: The interface switching speed affects the user's reading experience. The different operational purposes of the user have different requirements for the interface switching speed.

望眼神是中医望诊的重要内容,能直接反映患者的病理生理状态.传统的望眼神主要由医生的直接目测进行判断,主观性较强,精确性及一致性较差.本研究运用现代图像处理技术和机器学习等方法对中医眼神的计算机自动识别进行了研究,提取了眨眼频率、单次眨眼时间、长眨眼次数等6个能够反映眼神的数字特征,并通过特征选择筛选出其中5个特征组成了眼神识别特征集,建立了中医眼神特征识别方法,为辅助临床辨证诊断提供了客观依据.

For finding the changing law that the interaction between the photons and the water, the experiment has been finish and the result has been analyzed. Two half circles of them one is black and another is white are in different depth in water and the images are took. The results are shown that the object is just right distinguished when the depth of object in water is two times its diameter. The fitting curves of the brightness and the contrast with exponential function is tolerated. However, the fitting curve of the product of the brightness and the contrast with exponential function is not tolerated. The fitting curve is good with polynomial function.

This paper presents a new automatically quantitative facial features classification system for TCM spirit diagnosis based on facial features. Facial diagnosis is an important diagnostic method in TCM (Traditional Chinese Medicine) and has been used for a long time. However, this traditional diagnostic method is mainly based on observation by TCM doctors and their personal experience. To develop quantification methods for TCM is very important. First, we capture facial features from video images through some algorithms, and then we use some classification models to analyze them. Finally, IG (Information Gain) is used to analyse which kind of features has good performance. Experiment results show that our system has high classification accuracy.

In Traditional Chinese Medicine (TCM), lip diagnosis is an important diagnostic method to judge whether a person is healthy or not. Lip images can reflect the physical conditions of organs in the body. Lip diagnosis has a long history in China and the lips are analyzed by experienced doctors with their nude eyes. This method is not objective and efficient especially in the condition of handling many images. Developing an automatic way to split lips from an image is an important and necessary step. What’s more, lip segmentation can provide improvement in the areas of speech recognition and speaker authentication. To segment lips and facial complexions, many methods are proposed which are based on color spaces such as RGB, HSV, Lab, etc. Other methods are based on different models such as snake, geometry model, etc. This paper proposes a lip segmentation method based on facial complexion template. A facial complexion template can be constructed when the face is detected. We construct the facial complexion template using Hue channel and Saturation channel of color information. By removing the skin similar to facial complexion template values an initial lip image can be got. Finally, by smoothing the lip contour an optimized lip segmentation result can be obtained.