A Research of Trajectory Tracking of Robot Manipulator Using the Compensator of Neural Network Based on Dynamics

Abstract:

In this paper, a new trajectory control approach of robot manipulator based on dynamics model was proposed. The method was a combination of the torque control and a compensator of neural network. The torque profile was updated by the previous torque profile. Errors were inevitable while the modeling for dynamics of robot manipulator, but they could be compensated by the compensation structure of ANN. As such, the trajectory tracking converged very fast and the new algorithm achieved the asymptotical convergence based on the Lyapunov’s method. Furthermore, it could enhance the performance of the adaptability. The result of simulations and experiments show that the controller can get the performance of trajectory well.

• Periodical: Applied Mechanics and Materials (Volumes 66-68)
• Pages: 1802-1807
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.66-68.1802
• Online since: July 2011
• Authors: Zhen Yang, Fang Wang
• Keywords: Dynamic, Neural Network (NN), Robot Manipulator, Trajectory Control

References

[1] Chen QJ, Chen HT, Wang YJ and Woo PY: J Robot Syst. 18(2001), pp.69-75.

[2] Tomei P: IEEE Trans Robot Automation. 7(1991), pp.565-570.

[3] Yang Shengyue, Luo An and Fan Xiaoping: Chinese Journal of Control Theory & Applications. 20(2003), pp.707-712.

[4] Tayebi A: Automatic. 40(2004), pp.1195-1203.

[5] Ouyang P R, Zhang W J, and Gupta M M: Mechatronics. 16(2006), pp.51-61.

[6] Gopinath S, Kar I N: Mechanism and Machine Theory. 39(2004), pp.1367-1384.

[7] Mezouar Y, Chaumette F: International Journal of Robotics Research. 22(2003), pp.781-803.

[8] Xu Jianxin, Xu Jing and Cao Wenjun: ACTA Automatica SINICA. 27(2001), pp.434-446.

[9] WANG Fang: Journal of Computational Information Systems. 5(2009), pp.1067-1073.

[10] Tayebi A: Proceedings of the American control conference (2003), pp.4518-4523.