Neural network payload estimation for adaptive robot control

Publisher Website
Google Scholar
Abstract
This paper proposes a new concept for utilizing artificial neural networks to enhance the high-speed tracking accuracy of robotic manipulators. Tracking accuracy is a function of the controller's ability to compensate for disturbances produced by dynamical interactions between the links. A model-based control algorithm uses a nominal model of those dynamical interactions to reduce the disturbances. The problem is how to provide accurate dynamics information to the controller in the presence of payload uncertainty and modeling error. Neural network payload estimation uses a series of artificial neural networks to recognize the payload variation associated with a degradation in tracking performance. The network outputs are combined with a knowledge of nominal dynamics to produce a computationally efficient direct form of adaptive control. The concept is validated through experimentation and analysis on the first three links of a PUMA-560 manipulator. Networks trained on both single-joint and multi-joint trajectory data are investigated. A multilayer perceptron architecture with two hidden layers is used throughout. Integration of the principles of neural network pattern recognition and model-based control produces a tracking algorithm with enhanced robustness to incomplete dynamic information. Tracking efficacy is shown to compare favorably with a conventional adaptive technique based on Lyapunov theory, and applicability to robust control algorithms is demonstrated. The contribution from this research is a clear illustration of the performance improvement potential, and limitations, of the proposed concept.

This publication has 28 references indexed in Scilit: