Integrated PID-type Learning and Fuzzy Control for Flexible-joint Manipulators |
| |
Authors: | Lih-Chang Lin Tzong-En Lee |
| |
Affiliation: | (1) Department of Mechanical Engineering, National Chung Hsing University, Taichung, 402, Taiwan R.O.C |
| |
Abstract: | The increased complexity of the dynamics of robots considering joint elasticity makes conventional model-based control strategies complex and difficult to synthesize. In this paper, a model-free control using integrated PID-type learning and fuzzy control for flexible-joint manipulators is proposed. Optimal PID gains can be learned by a neural network learning algorithm and then a simple standard fuzzy control could be incorporated in the overall control strategy, if needed, for enhancing the system responses. A modified recursive least squares algorithm is suggested for faster learning of the connection weights representing the PID-like gains. Simulation results show that the suggested simple model-free approach can control a complex flexible-joint manipulator to meet stringent requirements for both transient and steady-state performances. |
| |
Keywords: | flexible-joint robot model-free control PID-type learning fuzzy control |
本文献已被 SpringerLink 等数据库收录! |