The chapter is devoted to the design of an intelligent neural network based control system for underwater robots. A new algorithm for intelligent con- troller learning is derived using the speed gradient method. The proposed systems provide robot dynamics close to the reference ones. Simulation re- sults of neural network control systems for underwater robot dynamics with parameter and partial structural uncertainty have confirmed the perspectives and effectiveness of the developed approach.
Underwater Robot Intelligent Control Based on Multilayer Neural Network / Oskin, Dimitry; Dyda, Alexander; Longhi, Sauro; Monteriù, Andrea. - STAMPA. - (2015), pp. 147-166.
Underwater Robot Intelligent Control Based on Multilayer Neural Network
Longhi, Sauro;Monteriù, Andrea
2015-01-01
Abstract
The chapter is devoted to the design of an intelligent neural network based control system for underwater robots. A new algorithm for intelligent con- troller learning is derived using the speed gradient method. The proposed systems provide robot dynamics close to the reference ones. Simulation re- sults of neural network control systems for underwater robot dynamics with parameter and partial structural uncertainty have confirmed the perspectives and effectiveness of the developed approach.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.