Adaptive Neural Network-based Synchronization Control of Multiple Robotic Manipulators: Dynamic Surface Control Approach

This work proposes an adaptive synchronization control scheme for multiple robotic manipulators to track a desired trajectory. The radial basis function-neural networks (RBF-NNs) are used to represent the model of the uncertain and heterogeneous dynamics of the follower robots in the multiple robotic systems. Then, the proposed method based on the dynamic surface control approach is designed. Stability analysis of the closed-loop system shows that all the signals of the closed-loop system are uniformly ultimately bounded. The proposed method solves the synchronization and tracking problem in the multiple robotic systems with uncertain dynamics. Furthermore, it eliminates the “explosion of complexity” problem. The proposed method is applied to a set of Euler-Lagrange multiple robotic manipulators. The simulation results demonstrate the efficiency of the proposed method.