This study presents a multimodal human-exoskeleton cooperative control method to realize different control modes smoothly switching each other with satisfactory stable performance. Considering existed mismatch gaits of the operator comparison with the exoskeleton, the corresponding operator's gait is planned by central pattern generators (CPGs) to reduce human-exoskeleton impedance and generate real-time desired trajectory, which are used as the trajectory demand input of the exoskeleton control. Then, the admittance modulation factors is proposed to realize three motion control modes of lower limb exoskeleton, i.e., active, passive, and assist-as-needed. Meanwhile, an adaptive backstepping controller with the radial basis function neyral network estimation law is designed to guarantee the position tracking errors in uniformly ultimately boundedness under model uncertainty. Finally, the experimental studies are performed with an able-bodied operator by regulating the CPGs model parameters and modulation factors to verify the proposed multimodal human-exoskeleton cooperative control.

This study presents an observer-based adaptive fuzzy dynamic surface force control strategy for pneumatic polishing system with uncertain contact environment model and full-state constraints. First, a fuzzy logic system is employed to approximate the uncertain nonlinear dynamics of the pneumatic polishing system end-effector, and a fuzzy state observer is designed to estimate the unmeasured states. Further, to enhance the controller’s response speed, a variable separation method employing fuzzy basis functions and the dynamic surface control technique are adopted to address algebraic loop issues and prevent computational complexity explosion. A logarithmic-type barrier Lyapunov function is embedded into each step of the controller design to ensure that all system states satisfy the predefined constraints. Finally, an adaptive fuzzy dynamic surface force controller with full-state constraints is developed to ensure fast and accurate control of the polishing force in an uncertain contact environment while maintaining all states within predefined constraints. The effectiveness and applicability of the proposed control algorithm are experimentally verified using a pneumatic polishing system.

Introduction: Human gait motion intention recognition is very important for the lower extremity exoskeleton robot to accurately synchronize and respond to the user’s natural motion. And motion intention recognition is generally performed through sEMG. Deep learning neural networks perform well in dealing with high-dimensional data and nonlinear relationships such as sEMG, but different deep learning neural networks have their own advantages in dealing with different types of data. Therefore, a multi-branch deep learning neural network, which enables different neural networks to process different feature items, could achieve more accurate and efficient motion intention recognition. The purpose of this study is to 1) Establish a multi-branch deep learning neural network model to achieve accurate gait recognition and effective estimation of joint angles. 2) Quantify the performance of the multi-branch deep learning neural network model in gait recognition and joint angle prediction using sEMG.Methodology: This study involved the collection of sEMG and plantar pressure data during walking in human subjects. Firstly, the collected signals are filtered and denoised to ensure the quality and reliability of the data. Calculate the time domain features and the frequency domain features to capture the key information of gait. Then, using the sensitivity difference of different structural neural networks to different feature data, a multi-branch deep learning neural network model is developed, in which the extracted features are used as the input of the model. The output of the model includes gait cycle and joint angle, so as to realize the accurate recognition of human gait and the effective estimation of joint angle.Results: The results show that the proposed method has high accuracy in identifying human gait and estimating joint angles. The multi-branch neural network model successfully integrates time-domain and frequency-domain features and provides reliable prediction of gait cycle and joint angle. The highest accuracy of gait recognition is 95.42%, the lowest is 90.11%, and the average is 92.16%. The average error of joint angle estimation is 3.19.Discussion: This study designed a human walking gait recognition and joint angle prediction model to achieve accurate human lower limb motion intention recognition.The model can be integrated into the sEMG sensor to design a angular biosensors, which can predict the human joint angle in real time.

A multilevel control strategy is proposed for a lower limb exoskeleton to realize different human training modes. In the high-level control layer, the human training mode is decided by the operator’s motion intention to generate the reference gait trajectory. Meanwhile, both the joint estimation torque by the long short-term memory (LSTM) network and the human–exoskeleton interactive torques are used to evaluate the wearable comfort performance of the operator. In the middle-level control layer, a variable admittance controller is designed to plan three training modes of human–exoskeleton cooperative motion: passive, active, and passive-to-active mode (PAM). In the low-level control loop, a fixed-time convergent controller with radial basis function neural network (RBFNN) estimation law and input deadzone compensation is presented to guarantee the exoskeleton joint position tracks the desired trajectory of the admittance loop output. To avoid the Zeno phenomenon of the designed controller, an event-triggered mechanism (ETM) is used to determine the execution time for sampling and transmitting signals. Finally, the effectiveness of the proposed control strategy is verified by both simulation and experimental results.

Exoskeletons generally require accurate dynamic models to design the model-based controller conveniently under the human-robot interaction condition. However, due to unknown model parameters such as the mass, moment of inertia and mechanical size, the dynamic model of exoskeletons is difficult to construct. Hence, an enhanced whale optimization algorithm (EWOA) is proposed to identify the exoskeleton model parameters. Meanwhile, the periodic excitation trajectories are designed by finite Fourier series to input the desired position demand of exoskeletons with mechanical physical constraints. Then a backstepping controller based on the identified model is adopted to improve the human-robot wearable comfortable performance under cooperative motion. Finally, the proposed Model parameters identification and control are verified by a two-DOF exoskeletons platform. The knee joint motion achieves a steady-state response after 0.5 s. Meanwhile, the position error of hip joint response is less than 0.03 rad after 0.9 s. In addition, the steady-state human-robot interaction torque of the two joints is constrained within 15 $${\text{N}\cdot\text{m}}$$ N · m . This research proposes a whale optimization algorithm to optimize the excitation trajectory and identify model parameters. Furthermore, an enhanced mutation strategy is adopted to avoid whale evolution's unsatisfactory local optimal value.