Sage Journals: Discover world-class research

Abstract

To swing up an acrobot, a two-link under-actuated robotic system, a fuzzy neural network (FNN) controller with limited torque based on genetic algorithm (GA) is presented and tested. The acrobot is composed of two links rotating in a same plane around two joints, only the second of which is actuated. The upswing process is a complex problem to rotate the two links from the low to the top balance position by single torque on the actuated joint. In a real application system, motor output is often limited. Therefore, an FNN controller is proposed to generate limited torque on the actuated joint according to different states of the two links. The antecedents and consequences of the FNN controller are determined with an improved GA. Simulation results on the acrobot system verify the feasibility and generalization of the proposed GA-based FNN control scheme.

Keywords

Acrobot fuzzy neural network genetic algorithm

Get full access to this article

View all access options for this article.

References

Bortoff, S. A. 1994: Advanced nonlinear robotic control using digital signal processing. IEEE Transactions on Industrial Electronics 41, 32-39.

Fantoni, I. , Lozano, R. and Spong, M. W. 2000: Energy based control of the pendubot. IEEE Transactions on Automatic Control 45, 725-729.

Lai, X. , She, J. H. Ohyama, Y. and Cai, Z. 1999: Fuzzy control strategy for acrobots combining model-free and model-based control. IEE Proceedings on Control Theory and Applications 146, 505-510.

Smith, M. H. , Zhang, T. and Gruver, W. A. 1998: Dynamic fuzzy control and system stability for the acrobot. IEEE International Conference on Fuzzy Systems. Anchorage, 286-291.

Spong, M. W. 1995: The swing up control problem for the acrobot. IEEE Control Systems Magazine 15, 49-55.

Topalov, A. V. , Kim, J. H. and Proychev, T. P. 1998: Fuzzy-net control of non-holonomic mobile robot using evolutionary feedback-error-learning. Robotics and Autonomous Systems 23, 187-200.

Xin, X. and Kaneda, M. 2001: A robust control approach to the swing up control problem for the acrobot. Proceedings of 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Hawaii, 1650-1655.

Xu, X. and He, H. G. 2002: Residual-gradient-based neural reinforcement learning for the optimal control of an acrobot. IEEE International Symposium on Intelligent Control. Vancouver, 758-763.

Yang, Y. P. , Xu, X. M. and Zhang, W. Y. 1998: Real-time stable self-learning FNN controller using genetic algorithm. Fuzzy Sets and Systems 100, 173-178.

10.

Yoshimoto, J. and Ishii, S. 1999: Application of reinforcement learning to balancing of Acrobot. IEEE International Conference on Systems, Man, and Cybernetics 5, 516-521.

11.

Zhang, M. J. and Tarn, T. J. 2002: Hybrid control of the pendubot. IEEE/ASME Transactions on Mechatronics 7, 79-86.

GA-based control to swing up an acrobot with limited torque

Abstract

Keywords

Get full access to this article

References