This paper presents an adaptive neural network (NN) control of a two-degree-of-freedom manipulator driven by an electrohydraulic actuator. To restrict the system output in a prescribed performance constraint, a weighted performance function is designed to guarantee the dynamic and steady tracking errors of joint angle in a required accuracy. Then, a radial-basis-function NN is constructed to train the unknown model dynamics of a manipulator by traditional backstepping control (TBC) and obtain the preliminary estimated model, which can replace the preknown dynamics in the backstepping iteration. Furthermore, an adaptive estimation law is adopted to self-tune every trained-node weight, and the estimated model is online optimized to enhance the robustness of the NN controller. The effectiveness of the proposed control is verified by comparative simulation and experimental results with Proportional-integral-derivative and TBC methods.

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.

Due to randomness and uncertainty of individual walking gait, this study uses the sparse Gaussian process (SGP) to construct a knee motion probabilistic model related to its corresponding hip motion. Since the SGP can quantify output uncertainty, a time-varying constrained boundary of knee position is presented to guarantee the operator's safety and comfort in human-exoskeleton cooperative motion. First, a low-cost gait acquisition system (called CJD-1) composed of inertial measurement unit is constructed to collect the operator's gait information. Then, a virtual interaction torque field and an output-dependent universal barrier function are designed to realize the coordinated transformation of the time-varying constrained boundary generated by the SGP. Hence, the exoskeleton joint position is constrained by the desired output constrained boundary, which is complied with the operator's gait law. Then, a backstepping controller with a finite-time extended state observer is proposed to estimate and compensate unmeasured joint velocity and lumped uncertainty. The effectiveness of the proposed control scheme is verified by both simulations and experimental results of human-exoskeleton cooperative motion.