Robust adaptive neural network control for environmental boundary tracking by mobile robots

Abstract

SUMMARY The paper addresses the problem of environmental boundary tracking for the nonholonomic mobile robot with uncertain dynamics and external disturbances. To do environmental boundary tracking, a reference velocity is designed for the nonholonomic mobile robot. In this paper, a radial basis function neural network (NN) is used to approximate a nonlinear function containing the uncertain model terms and the elements of the Hessian matrix of the environmental concentration function. Then, the NN approximator is combined with a robust control to construct a robust adaptive NN control for the mobile robot to track the desired environment boundary. It is proved that the tracking error can be guaranteed to converge to zero in the ultimate. Simulation results are presented to illustrate the stability of the robust adaptive control. Copyright © 2011 John Wiley & Sons, Ltd.

Asymptotic stabilization via adaptive fuzzy control

“…Thus, according to (18), the domain of attraction S can be made large to be close to D z0 by increasing Q and k concurrently. However, a large k reduces the learning speed ofθ in (13), which degrades control performance or even destroys system stability. Here, the selection of γ to be equal to γ 0 /λ min (P ) in the adaptive law of (13) completely resolves this problem.…”

“…where A li i are linguistic variables of fuzzy rules, i = 1, 2, κ 1 = π/6, κ 2 = π/3, and l i = 1, 2, · · · , 5; second, to determine the adaptive law in (13), let M θ = 100, γ 0 = 1000, k = [10, 25] T and Q = diag (10,10), and obtain P = [15, 0.2; 0.2, 0.52] and λ min (P ) = 0.5172 by resolving (9).…”

Comparison of MANET self-organization methods for boundary detection/tracking of heavy gas cloud

“…The decision about the direction of movement can be based on trigonometric reasoning [30] or gradient of concentration [31]. Additionally, in [31] use of artificial neural networks for the nonholonomic mobile robot to move in the designed direction is described.…”

Adaptive motion control of wheeled mobile robot with unknown slippage

“…But, it is difficult to obtain an accurate mathematical model for applying computed torque controllers or other model-based controllers in practice. Following the neural network (NN) development, the neural network-based control of mobile robots has been the subject of intense research in recent years (Fierro & Lewis, 1998;Jolly, Kumar, & Vijayakumar, 2009;Sun, Pei, Pan, & Zhang, 2013;Wang, Ge, Lee, & Lai, 2006). These researches had produced new methods for solving the main difficulties.…”

“…The tracking control using an adaptive smart neural network for WMR was investigated (Wang et al 2006), and it produced fine motion control based on partially unknown dynamics. Sun et al (2013) proposed a robust adaptive NN control for the nonholonomic mobile robot to track the desired environmental boundary. These control methods stated above are designed under the constraint of pure roll and no slip.…”