Control of uncertain constrained nonholonomic mobile manipulator based on recurrent neural network

Control of an uncertain nonholonomic mobile manipulator based on the Diagonal Recurrent Neural Network

“…Using Lagrangian approach, the mobile manipulator can be described as A assumed to be known because it is a function of fixed geometry of the system [1].…”

“…Control of such systems is challenged by the following characters of the system: i) the motion of the wheeled base is subject to nonholonomic constraints. Smooth theory and design mechanism of classical nonlinear variation is not applicable; ii) the system dynamics is highly nonlinear and always unknown due to the change of load and structure complexity [1].…”

“…Theorem 1: Considering the mechanical system described by (2), the following holds for any ( (0), (0)) ζ ζ satisfying both the nonholonomic constraint: asymptotic stability, i. e., e ζ and e ζ asymptotically converge to zero, is achieved if s K is positive definite, sgn K E ≥ and the parameter adaptation laws are given by [1] ˆ{ }…”