基于神经网络的不确定移动机器人鲁棒自适应跟踪控制

针对含运动学未知参数以及动力学模型不确定的非完整轮式移动机器人轨迹跟踪问题，基于Radical Basis Function(径向基函数)神经网络，提出了一种鲁棒自适应控制器.首先，考虑移动机器人运动学参数未知的情况，提出了一种含自适应参数的运动学控制器，用以补偿参数不确定性导致的系统误差；其次，利用神经网络控制技术，对于机器人在移动中动力学模型不确定问题，提出了一种具有鲁棒性的动力学控制器，使得移动机器人可以在不知道具体动力学模型的情况下跟踪到目标轨迹；最后利用Lyapunov稳定性理论证明了整个系统的稳定性.通过数值仿真验证了所设计的控制器的可行性.

Robust Adaptive Tracking Control of Uncertain Mobile Robot Based on Neural Network

Aiming at the trajectory tracking problem of nonholonomic wheeled mobile robots with unknown kinematic parameters and uncertain dynamic models, a robust adaptive controller is designed based on Radical Basis Function neural network. Firstly, considering the unknown kinematic parameters of the mobile robot, a kind of kinematic controller with adaptive parameters is proposed to compensate the system error caused by parameter uncertainty; Secondly, by using neural network control technology, a robust dynamic controller is put forward to solve the problem of uncertain dynamic model of the robot in motion, so that the mobile robot can track the target trajectory without knowing the specific dynamic model; Finally, the stability of the whole system is proved by using the Lyapunov stability theory. Simulation results demonstrate the effectiveness of the designed controller.