基于径向基函数神经网络的移动机器人多变量固定时间编队控制

针对带多不确定性的一组非完整移动机器人的编队控制收敛问题，提出了基于径向基函数神经网络的移动机器人多变量固定时间领航者-跟随者编队控制算法.RBFNN补偿了系统所受的多不确定性，并消除了鲁棒控制的抖振现象.基于固定时间理论和Lyapunov方法进行了控制算法设计，使所提出的控制方法保证了编队控制系统中的所有信号全局固定时间收敛，在任意系统初始条件下，在通过参数设计的固定时间内，使机器人编队达到期望编队.仿真结果显示了所提出算法的有效性.

Radial Basis Function Neural Network-based Multivariable Fixed-time Formation Control of Mobile Robots

For formation control convergence problem of a group of nonholonomic mobile robots with multiple uncertainties, a multivariable fixed-time leader-follower formation control method based on radial basis function neural network (RBFNN)is proposed. Adaptive RBFNN is used to compensate for the multiple uncertainties of the system, eliminating the input chattering phenomenon of robust control. The control algorithm is designed using multivariable fixed-time control theory and Lyapunov method. The control method can guarantee the global fixed-time convergence of all the signals in the formation control system. With the presented fixed-time control scheme, the pre-designated mobile robot formation can be achieved within a fixed settling time under arbitrary initial system states. Simulation results demonstrate the effectiveness of the method.