Generation of limb trajectories with a sequential network

Massone,; Bizzi,

doi:10.1109/ijcnn.1989.118721

Cited by 9 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Employment of nemal networks to learn the entire control task from sensor to actuator or end effector has been successful for two or three degree of freedom systems [2,3], but attempts to apply these to higher order, more realistic robots 304 A. TASCILLO have been discouraging [4]. The most common assumption of conventional parameter estimation techniques is that initial conditions be close to their target values.…”

Section: Neural Robotic Controlmentioning

confidence: 99%

Diagnostic neural adaptive control of drifting systems

Tascillo

1995

J Intell Robot Syst

View full text Add to dashboard Cite

Abstract.A hierarchical network of neural network planning and control is employed to successfully accomplish a task such as grasping in a cluttered real world environment. In order for the individual robot joint controllers to follow their specific reference commands, information is shared with other neural network controllers and planners within the hierarchy. Each joint controller is initialized with weights that will acceptably control given a change in any of several crucial parameters across a broad operating range. When increased accuracy is needed as parameters drift, the diagnostic node fuzzy supervisor interprets the controller network's diagnostic outputs and transitions the weights to a closest fit specific child controller. Future reference commands are in turn influenced by the diagnostic outputs of every robot joint neural network controller. The neural network controller and diagnostics are demonstrated for linear and nonlinear plants.

show abstract

Section: Neural Robotic Controlmentioning

confidence: 99%

Diagnostic neural adaptive control of drifting systems

Tascillo

1995

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…After the forward mapping was trained,1.5 -another three-layer network (four inputs, two hidden layers with 12 hidden units each, and three outputs) was used to train the controller in a two-stage learning method. The four inputs consist of two final desired end effector positions and two feedback current end effector positions from the master forward mapping network[26]. There are 15 maneuvering paths (seeFig.…”

mentioning

confidence: 99%

Iterative inversion of neural networks and its application to adaptive control

Hoskins

Hwang

Vagners

1992

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

An iterative constrained inversion technique is used to find the control inputs to the plant. That is, rather than training a controller network and placing this network directly in the feedback or feedforward paths, the forward model of the plant is learned, and iterative inversion is performed on line to generate control commands. The control approach allows the controllers to respond online to changes in the plant dynamics. This approach also attempts to avoid the difficulty of analysis introduced by most current neural network controllers, which place the highly nonlinear neural network directly in the feedback path. A neural network-based model reference adaptive controller is also proposed for systems having significant dynamics between the control inputs and the observed (or desired) outputs and is demonstrated on a simple linear control system. These results are interpreted in terms of the need for a dither signal for on-line identification of dynamic systems.

show abstract

Neural Network Modeling

Levine

2002

Stevens' Handbook of Experimental Psychology

View full text Add to dashboard Cite

This chapter reviews major examples of neural network models relevant to several areas of psychology. These include sensory processes, including short‐term memory, preattentive vision, attention, and code development; control of individual movements and movement sequences; classical and operant conditioning, and reinforcement learning; involvement of several brain areas in cognitive‐emotional interactions; categorization and classification; decision making; language understanding; reasoning and analogy; mental and cognitive disorders; and a few areas of social psychology. One simple example is given of the process of generating equations for a neural network model, with the terms of the equations being motivated by the psychological operations those terms describe.

show abstract

Generation of limb trajectories with a sequential network

Cited by 9 publications

References 25 publications

Diagnostic neural adaptive control of drifting systems

Diagnostic neural adaptive control of drifting systems

Iterative inversion of neural networks and its application to adaptive control

Neural Network Modeling

Contact Info

Product

Resources

About