Neural networks for control systems - A survey

By K. Hunt, D. Sbarbaro-Hofer, Rafal W. Zbikowski, Peter J. Gawthrop. 1992

Subfields: Model Architectures, Robotics & Control

How researchers see this paper

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

In Model Architectures

In Robotics & Control

Citations in the corpus

Data-efficient Deep Reinforcement Learning for Dexterous Manipulation (2017, background): “(Webros, 1990; Tesauro, 1995; Hunt et al., 1992; Hafner & Riedmiller, 2007), and recent success with deep learning has driven the development of new end-to-end training methods for challenging control problems (Mnih et al.”
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates (2016, background): “Although there has been considerable research on reinforcement learning with general-purpose neural networks for some time [13], [14], [15], [16], [17], such methods have only recently been developed to the point where they could be applied to continuous control of highdimensional systems, such as 7”
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning (2017, methodology): “work to model plant dynamics [27], [28], more recent model-based algorithms have achieved only limited success in applying such models to the more complex benchmark”
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees (2018, methodology): “linear models (Levine & Koltun, 2013; Lioutikov et al., 2014; Levine & Abbeel, 2014; Yip & Camarillo, 2014), mixture of Gaussians (Khansari-Zadeh & Billard, 2011), to neural networks (Hunt et al., 1992; Nagabandi et al., 2017; Kurutach et al., 2018; Tangkaratt et al., 2014; Sanchez-G”
Neural Networks for Control (1993, background): “Moreover, the availability of these papers and their extensive bibliographies has the advantage of allowing indirect citations; a reference such as: [20:175] will mean " item [175] in the bibliography given in the paper [20].”
Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability (2001, methodology): “While early work in ANNs used anthropomorphic arguments to introduce the methods and models used, today neural networks used in engineering are related to algorithms and computation and do not question how brains might work (Hunt et al. 1992).”
Self-Organizing Feature Maps for Modeling and Control of Robotic Manipulators (2003, background): “Massone (1995) and Hunt et al. (1992) listed a series of drawbacks of the direct-inverse modeling paradigm.”
Neural Network Applications in Power Electronics and Motor Drives—An Introduction and Perspective (2007, background): “5(a) shows the general structure of a two-layer real-time RNN which was proposed and trained by Williams and Zipser in 1989 [1].”
Cautious Model Predictive Control Using Gaussian Process Regression (2017, methodology): “Learning methods for automatically identifying dynamical models from data have gained significant attention in the past years [1] and more recently also for robotic applications [2], [3].”
Smooth function approximation using neural networks (2005, background): “Digital Object Identifier 10.1109/TNN.2004.836233 representation of an unknown system and, possibly, its control law [11], [12].”
A survey of iterative learning control (2006, background): “guarantee [2], whereas ILC usually converges adequately in just a few iterations.”
Output Reachable Set Estimation and Verification for Multilayer Neural Networks (2017, background): “Applications include adaptive control [1, 2, 3, 4], pattern recognition [5, 6], game playing [7], autonomous vehicles [8] ,and many others.”