[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Jacobs et al., 1991 - Google Patents

A modular connectionist architecture for learning piecewise control strategies

Jacobs et al., 1991

Document ID
14981755128514327847
Author
Jacobs R
Jordan M
Publication year
Publication venue
1991 American Control Conference

External Links

Snippet

Methodologies for designing piecewise control laws, such as gain scheduling, are useful because they circumvent the problem of determining a fixed global model of the plant dynamics. Instead, the dynamics are approximated using local models that vary with the …
Continue reading at ieeexplore.ieee.org (other versions)

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding or deleting nodes or connections, pruning
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators

Similar Documents

Publication Publication Date Title
Mohajerin et al. Multistep prediction of dynamic systems with recurrent neural networks
Jacobs et al. Learning piecewise control strategies in a modular neural network architecture
Sanger Neural network learning control of robot manipulators using gradually increasing task difficulty
Atkeson et al. Using associative content-addressable memories to control robots
Wai et al. Intelligent tracking control for robot manipulator including actuator dynamics via TSK-type fuzzy neural network
Li et al. Self-organizing neuro-fuzzy system for control of unknown plants
Karakaşoǧlu et al. A recurrent neural network-based adaptive variable structure model-following control of robotic manipulators
Jacobs et al. A modular connectionist architecture for learning piecewise control strategies
Sanner et al. Neuromorphic pitch attitude regulation of an underwater telerobot
Yen Identification and control of large structures using neural networks
Yousef et al. Adaptive fuzzy semi‐decentralized control for a class of large‐scale nonlinear systems with unknown interconnections
Ronco et al. Neural networks for modelling and control
Sun et al. A fast algorithm for finding global minima of error functions in layered neural networks
Abdolmaleki et al. Contextual policy search for linear and nonlinear generalization of a humanoid walking controller
Selinsky et al. The role of a priori knowledge of plant dynamics in neurocontroller design
Apolloni et al. A co-operating neural approach for spacecrafts attitude control
Yen Autonomous neural control in flexible space structures
Kiguchi et al. Neural network controllers for robot manipulators application of damping neurons
Robert A Modular Connectionist Architecture For Learning Piecewise Control Strategies
Wang et al. Self-adaptive neural architectures for control applications
Alepuz et al. Motor learning for manoeuvring control of a remotely operated vehicle
Bazaei et al. Online neural identification of multi-input multi-output systems
Wilson et al. Experiments in control of a free-flying space robot using fully-connected neural networks
Helferty et al. Adaptive control of a legged robot using a multi-layer connectionist network
Kitamura et al. Autonomous motion planning and learning control of a biped locomotive robot