Name
Abstract | ||
|---|---|---|
In this paper, we develop a decentralized neural network control design for robotic systems. Using this design, it is not necessary to derive the robotic dynamical system (robotic model) for the control of each of the robotic components, as in traditional robot control. The advantage of the proposed neural network controller is that, under a mild assumption, unknown nonlinear dynamics such as inertia matrix and Coriolis/centripetal matrix and friction, as well as interconnections with arbitrary nonlinear bounds can be accommodated with on-line learning. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1016/j.automatica.2008.06.005 | Automatica |
Keywords | Field | DocType |
Adaptive control,Large-scale systems,Robotic systems | Robot control,Nonlinear system,Centripetal force,Matrix (mathematics),Control theory,Control engineering,Sylvester's law of inertia,Adaptive control,Artificial neural network,Mathematics,Dynamical system | Journal |
Volume | Issue | ISSN |
45 | 1 | 0005-1098 |
Citations | PageRank | References |
5 | 0.57 | 10 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kok Kiong Tan | 1 | 923 | 99.57 |
| Su-Nan Huang | 2 | 505 | 61.65 |
| Tong Heng Lee | 3 | 3489 | 279.54 |