Aiming at the problem of convergence speed and chattering in sliding mode variable structure control of manipulator, an improved exponential reaching law and nonlinear sliding surface are proposed, and the Lyapunov function is used to analyze its stability. According to the dynamic model of the 6-DOF UR5 manipulator and the proposed reaching law and sliding surface, the corresponding control scheme is designed. The control performance of the proposed control scheme is verified by tracking the end trajectory of the manipulator on the MATLAB and CoppeliaSim robot simulation platform. The experimental results show that the proposed control scheme can not only significantly improve the convergence speed and make the system converge quickly, but also can effectively reduce the chattering of the system. Even in the presence of disturbance signals, fast and stable tracking can be achieved while ensuring the robustness of the system, and the chattering of the robotic arm system can be weakened to a certain extent. Compared with the classical control method based on the computational torque method and the traditional sliding mode control scheme based on the exponential reaching law, the proposed scheme has certain advantages in terms of tracking accuracy, convergence speed, and reducing system chattering, and effectively improves the overall control performance of the system.

This work provides a 3D hand attitude estimation approach for fixed hand posture based on a CNN and LightGBM for dual-view RGB images to facilitate the application of hand posture teleoperation. First, using dual-view cameras and an IMU sensor, we provide a simple method for building 3D hand posture datasets. This method can quickly acquire dual-view 2D hand image sets and automatically append the appropriate three-axis attitude angle labels. Then, combining ensemble learning, which has strong regression fitting capabilities, with deep learning, which has excellent automatic feature extraction capabilities, we present an integrated hand attitude CNN regression model. This model uses a Bayesian optimization based LightGBM in the ensemble learning algorithm to produce 3D hand attitude regression and two CNNs to extract dual-view hand image features. Finally, a mapping from dual-view 2D images to 3D hand attitude angles is established using a training approach for feature integration, and a comparative experiment is run on the test set. The results of the experiments demonstrate that the suggested method may successfully solve the hand self-occlusion issue and accomplish 3D hand attitude estimation using only two normal RGB cameras.