Neural Network Control Of Robot Manipulators And Non-Linear Systems

By Frank L. Lewis, A. Yesildirak, S. Jagannathan. 1998

From the Publisher: This graduate text provides an authoritative account of neural network (NN) controllers for robotics and nonlinear systems and gives the first textbook treatment of a general and streamlined design procedure for NN controllers. Stability proofs and performance guarantees are provided which illustrate the superior efficiency of the NN controllers over other design techniques when the system is unknown. New NN properties, such as robustness and passivity are introduced, and new weight tuning algorithms are presented. Neural Network Control of Robot Manipulators and Nonlinear Systems provides a welcome introduction to graduate students, and an invaluable reference to professional engineers and researchers in control systems.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

End-to-End Training of Deep Visuomotor Policies (2015, methodology): “small, simple networks (Pomerleau, 1989; Hunt et al., 1992; Bekey and Goldberg, 1992; Lewis et al., 1998; Bakker et al., 2003; Mayer et al., 2006), and has largely been supplanted by methods that use carefully designed policies that can be learned efficiently with reinforcement learning (Kober et al”
Distributed adaptive control for synchronization of unknown nonlinear networked systems (2010, methodology): “Then, the NN estimation error ε(x) is bounded by ‖ε‖ ≤ εM on Ω , with εM a fixed bound (Hornik et al., 1989; Lewis et al., 1999) Weierstrass higher-order approximation theorem.”
Robust adaptive finite‐time parameter estimation and control for robotic systems (2015, background): “As a specific kind of nonlinear multiple-input multiple-output (MIMO) systems, robotic manipulators [14, 15] have been widely used.”
Neural network approximation of piecewise continuous functions: application to friction compensation (1997, background): “universal approximation property for NN [8], [ 19 ], [20], [30], [32], [33], [34].”
Decentralized Robust Adaptive Control for the Multiagent System Consensus Problem Using Neural Networks (2009, methodology): “Several modified neural-network-based control methods with applications to the robot and nonlinear system can be found in [ 24 ] and [25].”
Adaptive Control of a Class of Nonlinear Pure-Feedback Systems Using Fuzzy Backstepping Approach (2008, background): “U, and there exists an e> 0 and a number T (e, x0) such that � x(t)� 20 ].”
Stable Adaptive Control and Estimation for Nonlinear Systems (2001, background): “…been made in approximator-based control with rigorous mathematical treatments, and detailed analysis of stability, robustness and convergence of the closed-loop systems (Ge et al., 1998, 2001; Lewis et al., 1999; Lewis & Parisini, 1998; Narendra & Lewis, 2001; Poznyak et al., 2001; Wang, 1994).”
Deep learning in robotics: a review of recent research (2017, background): “ for robotics control as early as the 1980s [12]. It was quickly recognized that nonlinear regression provided the 3 functionality that was needed for operating dynamical systems in continuous spaces [13, 14], and closely related fuzzy systems seemed well suited for nominal logical control decisions”
Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence Proof (2008, methodology): “In this section, we review how to implement the HDP value iteration algorithm with two parametric structures such as NNs [ 22 ], [37].”
Leader-Based Optimal Coordination Control for the Consensus Problem of Multiagent Differential Games via Fuzzy Adaptive Dynamic Programming (2015, methodology): “ ,bθ˜ (31) or keik > v u u u t P j={N i,i} k((lij +bij) ⊗In)fej(t)k2 + 1 2a i ε¯2 i 2Γiλmin(Qii) −2(N¯i +1) ,be i (32) hold, then L˙ i < 0. Therefore, using Lyapunov-like theorem (see, [42] and [43]), it can conclude that the local consensus errors ei and weight estimation errors θ˜i are unifo”