Robot manipulator control for accurate trajectory tracking with unknown system dynamics and time-varying external disturbances is a challenging issue. This article aimed to propose a novel discrete-time learning-based neural network control with prescribed performance (LNNCPP) to solve this issue. This control scheme consists of offline and online learning phases. In the offline learning phase, an adaptive neural network controller (ANNC) satisfying the persistent excitation condition can achieve accurate closed-loop learning of unknown system dynamics along recurrent trajectory during the tracking control. This offline learning focuses on the learning in dynamic environments requiring neither the evaluation of inverse dynamical model nor the time-consuming training. The learned knowledge can be stored as constant network weights. The online learning of the LNNCPP is developed based on the learned knowledge and the prescribed performance (PP) to counter the external disturbances and to guarantee the PP of tracking errors. The LNNCPP was compared with the ANNC, ANNC with PP and sliding model control by simulation and real-world experiment. Results showed that the LNNCPP had improved tracking accuracy, better transient performance and lower oscillations with the dynamic changes and external disturbances. This method may promote the tracking accuracy and stability for robotic manipulators towards unstructured environments.

To improve the recognition rate of lower limb actions based on surface electromyography (sEMG), an effective weighted feature method is proposed, and an improved genetic algorithm support vector machine (IGA-SVM) is designed in this paper. First, for the problem of high feature redundancy and low discrimination in the surface electromyography feature extraction process, the weighted feature method is proposed based on the correlation between muscles and actions. Second, to solve the problem of the genetic algorithm selection operator easily falling into a local optimum solution, the improved genetic algorithm-support vector machine is designed by championship with sorting method. Finally, the proposed method is used to recognize six types of lower limb actions designed, and the average recognition rate reaches 94.75%. Experimental results indicate that the proposed method has definite potentiality in lower limb action recognition.

Dexterous multi-finger robotic grasping faces two primary limitations: (1) traditional demonstration-based learning requires a separate trajectory to be trained for each object type, resulting in limited generalization across different objects; and (2) single-agent reinforcement learning struggles to coordinate the asynchronous motions of the thumb and fingers with heterogeneous joints, leading to inefficient exploration and slow convergence. To overcome these limitations, this study proposed two core innovations, including (1) a dynamic modulation kernel movement primitive (DM-KMP) algorithm, which combines dynamic movement primitives with kernel-based movement primitives to preserve trajectory topology and local probabilistic modulation characteristics; and (2) a novel potential-guided weight scheduling multi-agent deep deterministic policy gradient method (PWS-MADDPG), in which the thumb and fingers are modeled as independent agents. This enables the generation of grasping trajectories for diverse object categories using only a limited number of demonstrations. By leveraging a potential field model to optimize action selection, this method accelerates model convergence. Moreover, a multi-modal reward function with weight scheduling was designed to facilitate a seamless transition from individual optimization to coordinated team behavior. Experiment results demonstrated that the proposed PWS-MADDPG achieved a grasping success rate of 85.48% on a dexterous hand grasping across 11 object categories, outperforming the existing approaches—with a 40.31% improvement over the DDPG algorithm and a 20.05% improvement over the MADDPG algorithm. Furthermore, to verify the grasping stability and adaptability of the system in real-world scenarios, a grip-force validation experiment was designed using a custom cylindrical apparatus embedded with five six-axis sensors. These results demonstrate that the robotic hand using this novel method can maintain stable grasping and adaptively regulate grip and load forces in response to incremental external loads, based on a control policy that is trained in both simulation and real-world environments. These findings suggest that this method has strong Sim-to-Real transferability, biological plausibility in force adjustment, and robustness to environmental disturbances, enhancing both the training efficiency and generalization in simulation, and demonstrating high grasping robustness and successful rates in the real-world tasks. The proposed method holds strong potential for high-precision, safety-critical applications, including intelligent manufacturing, prosthetic control, and living assistance.