Sliding mode control of mobile robot formations based on neural networks.

A combined kinematic/adaptive neural sliding mode control law is proposed for leader follower based formation control of multiple nonholnomic mobile robots. The radial basis function neural network (RBFNN) was introduced to approximate the nonlinear uncertain part of dynamics of the follower and its leader, and the adaptive robust controller compensated modeling errors of uncertainties by neural network. The results show that this approach not only solves parameter and non-parameter uncertainties of mobile robots, but also ensures the desired trajectory tracking of robot formation in the case of maintaining formation. The stability of the control system was proved by using the Lyapunov theory. [ABSTRACT FROM AUTHOR]