Stable Adaptive Neural Network Control

By Shuzhi Sam Ge, C. Hang, Tong-heng Lee, Tao Zhang. 2001

913 citations recorded by the source corpus.

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Deep learning in neural networks: An overview (2014, methodology): “1 RL Through NN World Models Yields RNNs With Deep CAPs In the special case of an RL NN controller C interacting with a deterministic environment, a separate FNN called M can learn to become C’s world model through system identification, predicting C’s inputs from previous actions and inputs (e.g., ”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “The first combination of an RL RNN C and an UL RNN M was ours and dates back to 1990 [223, 222, 226, 227], generalizing earlier similar controller/model systems (CM systems) based on FNNs [298, 179]; compare related work [177, 119, 301, 300, 209, 120, 178, 302, 73, 45, 144, 166, 153, 196, 60][245, S”
Adaptive neural control of nonlinear time-delay systems with unknown virtual control coefficients (2004, methodology): “817055 in [9], and semi-globally stable adaptive controllers are developed, which do not require the estimate of the unknown function .”
Adaptive dynamic surface control of nonlinear systems with unknown dead zone in pure feedback form (2008, methodology): “Using a novel family of integral Lyapunov functions, adaptive backstepping control was presented (Ge et al., 2001; Zhang, Ge, & Hang, 2000) for a class of strict-feedback systems.”
Robust adaptive neural control for a class of perturbed strict feedback nonlinear systems (2002, methodology): “In order to cope with highly uncertain nonlinear systems, as an alternative, approximator-based adaptive control approaches have also been extensively studied in the past decade using Lyapunov stability theory [2], [3], [18], [19], [23], [24], [27].”
Prescribed Performance Adaptive Control for Multi-Input Multi-Output Affine in the Control Nonlinear Systems (2010, background): “However, it can be easily verified that the transformed systems of significant classes of MIMO affine in the control nonlinear systems (namely feedback linearizable [5] and block-triangular [7]) are stabilizable no matter what performance bounds are imposed via , , .”
High-order fully actuated system approaches: Part IV. Adaptive control and high-order backstepping (2020, methodology): “…networks and fuzzy functions have been widely employed for approximation-based adaptive control of some classes of complex uncertain nonlinear dynamical systems (e.g. Brown & Harris, 1994; Farrell & Polycarpou, 2006; Ge et al., 2001; Lewis et al., 2002; Spooner et al., 2002; Zhang & Liu, 2006).”
Neural-network control of nonaffine nonlinear system with zero dynamics by state and output feedback (2003, methodology): “It should be noted that, (48) and (49) are special classes of several adaptive laws proposed in [25].”
Dynamic Surface Control Using Neural Networks for a Class of Uncertain Nonlinear Systems With Input Saturation (2015, neutral): “In many references of robust adaptive control for uncertain nonlinear systems, RBFNNs are usually employed as approximation models for the unknown nonlinear and continuous function terms using their inherent approximation capabilities [54].”