Adaptive robot control using a processor network

Autor:	D.A. Fraser, F. Azhar
Rok vydání:	2002
Předmět:	ComputingMethodologies_PATTERNRECOGNITION Adaptive control Artificial neural network Control theory Computer science Real-time computing Feed forward Quality control Revolute joint Backpropagation System dynamics Robot control
Zdroj:	PDP
DOI:	10.1109/empdp.1993.336384
Popis:	Control of a revolute robot manipulator has been distributed over a transputer network. Feedforward and feedback position control filters for the three major axes have been implemented as neural nets. With one hidden layer and trained using back-propagation. The feedforward filter continues to adapt during operation and shows a steady improvement in control quality, and the ability to adapt to changes in the system dynamics. >
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::ade7868c84986c8db9e2f742fac90645 https://doi.org/10.1109/empdp.1993.336384 Zobrazit plný text záznamu