Integrated PID-type Learning and Fuzzy Control for Flexible-joint Manipulators

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.

[1]  Kevin M. Passino,et al.  Intelligent control for autonomous systems , 1995 .

[2]  P. Tomei.  A simple PD controller for robots with elastic joints , 1991 .

[3]  Mark W. Spong,et al.  Robot dynamics and control , 1989 .

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control - design and stability analysis , 1994 .

[6]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control , 1994 .

[7]  M. C. Readman,et al.  Stabilization of the Fast Modes of a Flexible-Joint Robot , 1992 .

[8]  Shaheen Ahmad,et al.  Adaptive control of flexible joint robots using position and velocity feedback , 1992 .

[9]  B. Pasik-Duncan,et al.  Adaptive Control , 1996, IEEE Control Systems.

[10]  Patrizio Tomei,et al.  A method to design adaptive controllers for flexible joint robots , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[11]  B. Armstrong-Hélouvry.  Stick slip and control in low-speed motion , 1993, IEEE Trans. Autom. Control..

[12]  R. Hecht-Nielsen,et al.  Theory of the Back Propagation Neural Network , 1989 .

[13]  Yoshiki Uchikawa,et al.  Trajectory control of robotic manipulators using neural networks , 1991 .

[14]  Rogelio Lozano,et al.  Adaptive control of robot manipulators with flexible joints , 1992 .

[15]  F. Ghorbel,et al.  Adaptive integral manifold control of flexible joint robot manipulators , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[16]  Lih-Chang Lin,et al.  Control of flexible joint robots via external linearization approach , 1990, J. Field Robotics.

[17]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[18]  Scott M. Babcock,et al.  Inverse dynamics position control of a compliant manipulator , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[19]  Ronald R. Yager,et al.  Essentials of fuzzy modeling and control , 1994 .

[20]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[21]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[22]  L. Wang,et al.  Fuzzy systems are universal approximators , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[23]  H. Tan,et al.  Indirect adaptive control of a two-link robot arm using regularization neural networks , 1991, Proceedings IECON '91: 1991 International Conference on Industrial Electronics, Control and Instrumentation.

[24]  Lih-Chang Lin.  STATE FEEDBACK H_ CONTROL OF MANIPULATORS WITH FLEXIBLE JOINTS AND LINKS , 1991 .

[25]  Lin Lih-Chang,et al.  Rigid model-based fuzzy control of flexible-joint manipulators , 1995, J. Intell. Robotic Syst..