Hierarchical Fuzzy Control of Robotic Manipulators

Issue title: Fuzzy Logic and Neural Networks: Theory and Applications

Article type: Research Article

Authors: Kumbla, Kishan Kumar | Jamshidi, Mo

Affiliations: CAD Laboratory for Intelligent and Robotics Systems, Department of Electrical and Computer Engineering, The University of New Mexico, Albuquerque, NM 87131

Abstract: This article describes the implementation of hierarchical control on a robotic manipulator using fuzzy logic. A decentralized control approach is implemented, i.e., individual controllers control the two links of the robot. The kinematic aspect of the control is treated as the supervisory mode at a higher level, and the joint control is treated as the lower level. Fuzzy logic based rules determine the inverse kinematic mapping, which maps the Cartesian coordinates to the individual joint angles. This scheme is implemented using Togai Infra Logic software and the entire simulation software is implemented using the “C” language. The results of the simulation are discussed. This experiment is a proof of the principle that the fuzzy controller can be used to map the nonlinear mapping, which can be implemented to more complex problems of inverse kinematics of higher degree of freedom robots. A fuzzy PD controller is implemented on a Rhino robot. The performance is compared with a traditional PD controller. The fuzzy controller, being an adaptive technique, gives better performance than a traditional linear PD controller over a typical operational range. The fuzzy controller reaches the desired position with no overshoot, which is unlikely with a PD controller.

DOI: 10.3233/IFS-1995-3103

Journal: Journal of Intelligent and Fuzzy Systems, vol. 3, no. 1, pp. 21-29, 1995