By training the deep neural network model, the hidden features in Surface Electromyography(sEMG) signals can be extracted. The motion intention of the human can be predicted by analysis of sEMG. However, the models recently proposed by researchers often have a large number of parameters. Therefore, we designed a compact Convolution Neural Network (CNN) model, which not only improves the classification accuracy but also reduces the number of parameters in the model. Our proposed model was validated on the Ninapro DB5 Dataset and the Myo Dataset. The classification accuracy of gesture recognition achieved good results.

This paper proposes an adaptive control scheme based on deferred prescribed performance control to address the angle-constrained formation control problem for multiple nonholonomic automated vehicles subject to model uncertainties and external disturbances. In contrast to conventional distance-based or bearing-based approaches, angle-based formation offers greater flexibility in geometric configuration and enhanced practicality. First, an angle-constraint matrix is constructed, and a shifting function is introduced to achieve deferred prescribed performance, which relaxes the stringent initial error constraints and enables a unified control framework for arbitrary initial states. An adaptive estimation strategy is then constructed to compensate for unknown dynamics caused by parameter uncertainties and external disturbances, ensuring the asymptotic convergence of each vehicle’s error; overall closed-loop stability is then verified via a Lyapunov function analysis. Finally, numerical simulations verify that the errors of all vehicles enter and remain within the predefined performance function bounds within the specified deferred time. The simulation results demonstrate that the proposed method achieves good convergence performance under various initial conditions. Compared with the traditional prescribed performance control method, it exhibits faster convergence and improved smoothness. The proposed method relies only on minimal neighbor interaction information, significantly reducing the perception link and computational burden. Moreover, it imposes no strict requirements on the initial states, making it more practical and deployment-friendly. These features make the method better suited to real-world scenarios and endow it with strong engineering application potential.

In this paper, the anti-disturbance coordinated control is investigated for the multiple mobile manipulators with disturbances. Some disturbances are induced by the random white noise; the others are assumed to be described by an external system. These disturbances are rejected and attenuated based on the disturbance-observer-based-control (DOBC) method and the adaptive control approach. Subsequently, a robust adaptive antidisturbance coordinated control strategy is proposed for the multiple mobile manipulators based on the back-stepping control scheme. In accordance with Lyapunov stability theory and the stochastic control theory foundation, the tracking error systems are guaranteed to be exponentially practically stable in mean square. Finally, an example is used to verify the effectiveness of the presented control method.