ABSTRACT This paper proposes a neural network‐based adaptive sliding mode controller combined with a nonlinear disturbance observer to enhance the stability and precision of the upper limb rehabilitation robot in uncertain environments. The upper limb movement intention is initially captured using an optical motion capture system and a surface electromyography acquisition system. An adaptive sliding mode control method, powered by a neural network, dynamically adjusts the controller's parameters to effectively address system uncertainties and external disturbances. The nonlinear disturbance observer in the controller helps identify and mitigate disturbances from the external environment, including Fourier‐type, power‐type, and mixed disturbances. Furthermore, the stability of the human‐machine interaction controller is rigorously verified using the Lyapunov theorem. Simulation results demonstrate that the proposed neural network‐based adaptive sliding mode control method significantly improves the performance and robustness of the upper limb rehabilitation robot.

In order to autonomously design the optimal descending trajectory for spacecraft soft landing on an asteroid, an onboard guidance based on the bidirectional extreme learning machine (B-ELM) is proposed. The optimization problem is formulated and transformed into a two-point boundary value problem (TPBVP). And then, based on the sample trajectories obtained off-line, a single-hidden layer feed-forward neural network (SLFN) trained by B-ELM is employed to design the optimal descending trajectory onboard. Finally, Monte Carlo simulations are performed to verify the effectiveness of the proposed guidance. Also, the learning process of the B-ELM is compared with traditional algorithms in simulations. Simulation results show that the guidance via the B-ELM trained SLFN meets the requirement of the soft landing in a lower learning and implementation cost.