The problem of designing an analytical gain tuning and stable PID controller for nonlinear robotic systems is a long-lasting open challenge. This problem becomes even more intricate if unknown system dynamics and external disturbances are involved. This paper presents a novel adaptive neural-based control design for a robot with incomplete dynamical modeling and facing disturbances based on a simple structured PID-like control. Radial basis function neural networks are used to estimate uncertainties and to determine PID gains through a direct Lyapunov method. The controller is further augmented to provide constrained behavior during system operation, while stability is guaranteed by using a barrier Lyapunov function. The paper provides proof that all signals in the closed-loop system are bounded while the constraints are not violated. Finally, numerical simulations provide a validation of the effectiveness of the reported theoretical developments.
Constrained Neural Adaptive PID Control for Robot Manipulators
2020-01-01
Journal of the Franklin Institute, (2020)
Article (Journal)
Electronic Resource
English
DDC: | 629 |
Model-Based Adaptive Control for Geometrically Constrained Robot Manipulators
British Library Online Contents | 1995
|Model-Based Adaptive Control for Geometrically Constrained Manipulators
British Library Online Contents | 1995
|Adaptive control of space-based robot manipulators
Tema Archive | 1991
|Adaptive control of space based robot manipulators
NTRS | 1991
|Adaptive Control of Space Robot Manipulators with Task Space Base on Neural Network
BASE | 2014
|