Deep Learning with Fractional Order Operaters Lagrangian Method for Space Robot based on Sliding Mode-based Fixed-time Control

Abstract

Many approaches have been influential in the robotics field because of deep learning (DL). As space robots need more reliability and stability, model-free algorithms with deep learning have particular advantages over the traditional methods in space environment. In this paper, we present an original robot current/torque prediction based on robot dynamic system with deep learning. Also, we add sliding mode-based fixed-time controller to improve the control performance. It has analysed manipulator current information through robot dynamic property’s matrix nature from fewer samples. This method has significant benefits in terms of robot current/torque identification and tracking. It also performs well in robustness and learning rates. This generic method has developed to solve a variety of problems using deep learning and data filtering with manipulator dynamics process, which includes deep learning with fractional order differential operators, robot dynamics and Kalman smoothing. We verified our algorithm into a real two-joint space robot on air-floating platform in zero gravity environment. The final results show it can learn to predict current/torque based on robot dynamics and complete the finitetime convergence. This paper made several key contributions to the fields of current/torque identification and prediction with manipulator dynamics and deep learning in space robot models. It performs very well in robot current/torque tracking and predicting new situations.