LSPB Trajectories Tracking Using Intelligent Self Constructing Recurrent Neural Robot Controller


An intelligent tracking control system is designed for nonlinear robot manipulator. The controller which is implemented into the trajectory planner utilizes a recurrent self constructing RBF network in order to capture the system dynamics. The structure learning algorithm creates online new hidden neurons to increase the learning ability of the controller and removes insignificant neurons to reduce the computation load. The adaptive laws are derived in the sense of Lyapunov so that the whole closed loop is stable with no restrictive conditions on the design constants for the stability. A comparative analysis is performed between this controller and a feed-forward self constructing RBF controller in case of Linear Segments with Parabolic Blends trajectories tracking. The proposed controller presents higher performance for different cases of uncertainties in manipulator parameters.

  • Abstract
  • Introduction
  • Controller Tracking Design for Manipulator
  • Structure Learning Phase
  • Parameters Learning Algorithm
  • Simulations
  • Conclusion
  • References

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In