Title :
Effects of using different neural network structures and cost functions in locomotion control
Author_Institution :
Inst. of Maritime Technol., Nat. Taiwan Ocean Univ., Keelung, Taiwan
Abstract :
Effects of using different neural network structures and cost functions in locomotion control are investigated. Simulations focus on refinement and a thorough understanding of an artificial intelligent learning scheme. This scheme uses a neural network controller with backpropagation through time learning rule. Through learning, the controller can generate locomotion trajectory along a pre-defined path. Different issues regarding the scheme have been examined. They include the effects of using different numbers of hidden units and the effects of using only position parameters in the cost function
Keywords :
backpropagation; intelligent control; legged locomotion; neural nets; path planning; backpropagation; biped robots; cost functions; intelligent control; learning rule; locomotion control; neural network; Artificial intelligence; Artificial neural networks; Backpropagation; Cost function; Intelligent networks; Learning; Leg; Legged locomotion; Neural networks; Robots;
Conference_Titel :
American Control Conference, 2000. Proceedings of the 2000
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-5519-9
DOI :
10.1109/ACC.2000.879225
