Planning and control of a robotic manipulator using neural networks
Luis Carlos Rabelo, X.J.R. Avula, H. Ma, A. Malkani, J.-S. Tsai · 2003
An architecture which utilizes two artificial neural systems for planning and control of a robotic arm is presented. The first neural network system participates in the trajectory planning and the motion decision-making process. The second neural network system provides the correct sequence of control actions with a high accuracy due to the utilization of an unsupervised/supervised neural network scheme. The utilization of a hybrid hierarchical/distributed organization, supervised/unsupervised learning models, and forward modeling yielded an architecture with capabilities of high level functionality.>