Nonholonomic systems: controllability and complexity
Selected papers of the conference on Algorithmic complexity of algebraic and geometric models
Introduction to Robotics: Mechanics and Control
Introduction to Robotics: Mechanics and Control
Evolutionary programming techniques for constrained optimizationproblems
IEEE Transactions on Evolutionary Computation
Designing a genetic neural fuzzy antilock-brake-system controller
IEEE Transactions on Evolutionary Computation
Adaptive sliding mode controller for a class of second-order underactuated systems
CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
| Hi-index | 0.00 |
This paper introduces a new concept for designing a fuzzy logic based switching controller in order to control underactuated manipulators. The proposed controller employs elemental controllers, which are designed in advance. Parameters of both antecedent and consequent parts of a fuzzy indexer are optimized by using evolutionary computation, which is performed off-line. Design parameters of the fuzzy indexer are encoded into chromosomes, i.e., the shapes of the Gaussian membership functions and corresponding switching indices of the consequent part are evolved to minimize the angular position errors. Such parameters are trained for different initial configurations of the manipulator and the common rule base is extracted. Then, these trained fuzzy rules can be brought into the online operations of underactuated manipulators. 2-DOF underactuated manipulator is taken into consideration so as to illustrate the design procedure. Computer simulation results show that the new methodology is effective in designing controllers for underactuated robot manipulators.