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.

Meeting Name

First IEEE Conference on Control Applications, 1992


Chemical and Biochemical Engineering

Keywords and Phrases

Distributed Control; Forward Modeling; Functionality; Hybrid Hierarchical/Distributed Organization; Learning (Artificial Intelligence); Motion Decision-Making Process; Neural Nets; Neural Networks; Path Planning; Robot Arm Control; Robotic Manipulator; Robots; Supervised/Unsupervised Learning Models; Trajectory Planning

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 1992 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jan 1992