移动机器人的自适应神经网络滑模控制

Adaptive Neural Network Sliding Mode Control of Mobile Robots

针对移动机器人模型的不确定性和非线性,给出了基于反步动力学控制和自适应径向基神经网络(Radial Basis Function Neural Network,RBFNN)调节滑模增益的PI型滑模动态控制(Sliding Mode Control,SMC)的混合算法,以增强对随机不确定性因素的适应性和消除滑模控制输入的抖动现象。并在此基础上,又进一步利用Lyapunov函数证明了控制系统的稳定性,最后给出了仿真结果。仿真结果表明,该控制算法在持续性扰动和不确定性情况下可以平滑控制输入,消除跟踪误差,系统具有快速收敛性,鲁棒性强。

Aiming at the uncertainty and nonlinearity of the mobile robot model, PI-type sliding modedynamic control （SMC） based on backstepping mechanics control and adaptive radial basis function neuralnetwork （RBFNN） for adjusting the sliding mode gain is proposed to enhance the adaptability of the randomuncertainty factor and eliminate the jitter phenomenon of sliding mode control input. On the basis of this, theLyapunov function is used to prove the stability of the control system. Finally, the simulation results aregiven. The simulation results show that the control algorithm can control the input smoothly and eliminatethe tracking error under the condition of persistent disturbances and uncertainties. The system has fastconvergence and strong robustness.