| Abstrakt: |
The robot is a very complex multi-input multi-output nonlinear system. Due to the inaccuracy of measurement and modeling, coupled with changes in load and the effects of external disturbances, it is virtually impossible to obtain a complete kinetic model. The strong robustness of sliding mode variable structure control makes it particularly suitable for solving the trajectory tracking problem of robots. In this paper, a better real-time adaptive control framework is designed to realize the robust target tracking of mobile robots. Based on the TSK neural network, an efficient control framework combining neural network controller and compensation controller is proposed. Based on the new framework research and improvement of neural network controller, considering the factors of emotional influence decision-making, the existing brain emotional learning neural network is improved and researched, and the brain-emotion learning neural network with radial basis function is proposed. The simulation results show that the trajectory tracking ability, anti-disturbance ability and robustness of the mobile robot are improved to some extent, which verifies the feasibility and efficiency of the proposed control method. |
Full text from SpringerLink