Globally stable neural robot control capable of payload adaptation
- 24 August 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 639-642 vol.1
- https://doi.org/10.1109/ijcnn.1993.713996
Abstract
A set of four separate three-layer-perceptrons (3LP) learns matrix components representing mass-coupling, coriolis, viscose, and static friction forces in an inverse robot model as a function of the robot's current position and payload. Based on training with point-to-point trajectories between random start- and goal-points that are executed with various load masses, the inverse model gradually acquires high precision over the entire robot working range. A controller using the 3LP-networks inside the feedback loop is shown to be globally L/sub /spl infin//-stable. The stability criterion is based on guaranteed model error bounds for the complete continuous working range and for all load masses in a certain range. Results of the stability analysis and of load-adaptive control are demonstrated for a realistically simulated planar 4-joint-machine.Keywords
This publication has 4 references indexed in Scilit:
- I/O-Stability for Robot Control with a Global Neural Net Inverse Model in the Feedback LoopPublished by Springer Nature ,1993
- Feedback-Error-Learning Neural Network for Supervised Motor LearningPublished by Elsevier ,1990
- Roboust nonlinear control of robot manipulatorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985
- Fast Nonlinear Control with Arbitrary Pole-Placement for Industrial Robots and ManipulatorsThe International Journal of Robotics Research, 1982