Application of RBF Neural Network in the Manipulator Trajectory Planning

Abstract:

In view of the high order, nonlinear characteristics of target trajectory, control strategy is proposed for a kind of RBF neural network and polynomial interpolation combining. According to the specific requirements of trajectory planning, the manipulator in joint space variables are expressed as one or two order derivative function by polynomial interpolation algorithm, then the RBF neural network is used for tracking the target trajectory. Finally, through MATLAB simulation, the accuracy of this method is verified.

• Periodical: Applied Mechanics and Materials (Volumes 651-653)
• Pages: 659-662
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.651-653.659
• Online since: September 2014
• Authors: Meng Meng Du, Hai Tao Zhang
• Keywords: Interpolation Algorithm, RBF Neural Network, Trajectory Planning

References

[1] Chuanlei Zhang, Weimin Ge, Bo Song. Manipulator trajectory planning of the BP neural network method and simulation [J]. Journal of design and research, 2007: 22-24.

[2] Hairong Zhang, Zhibing Shu. BP neural network application in robot trajectory planning [J]. Machinery and electronics, 2006 (11): 56-58.

[3] Jinkun Liu. The advanced robot control [M]. Beijing: higher education press, 2007. 5.

[4] Min Tan, De Xu, etc. The design of the robot control system and MATLAB simulation [M]. Beijing: Tsinghua university press, 2008. 6.

[5] Kaili Zhou, YaoHong Kang. Neural network model and MATLAB simulation program design [M]. Beijing: Tsinghua university press, 2005. 7.