论文信息 - Solving Inverse Kinematics of Industrial Robot Based on BP Neural Network

Solving Inverse Kinematics of Industrial Robot Based on BP Neural Network

Inverse kinematics of robot means solving the joint variables by the position and posture of robot end-effector, which is the basis of robot control. For the traditional method of inverse kinematics is more complex and not universally applicable, an algorithm based on BP neural network solving inverse kinematics of robot is proposed in this paper. Taking RS10N industrial Robot as the research object, a BP neural network is trained and improved to solve its inverse kinematics, which is simulated by MATLAB toolbox. The simulation results show that BP neural network trained by LM algorithm is precise and fast, which is a reliable method of solving inverse kinematics of robot.

Hui Li | Zhihong Jiang | Wencheng Ni | Yang Mo | Zhenzi Song

[1] Difei Liu,et al. Spraying robot kinematics analysis based on BP neural network , 2015, 2015 IEEE International Conference on Information and Automation.

[2] Hui Li,et al. Adaptive Impedance Controller for a Robot Astronaut to Climb Stably in a Space Station , 2016 .

[3] Cong Shuang. Comparative Study on Fast Learning Algorithms of BP Networks , 2001 .

[4] Xue Xiao-qin. Inverse kinematics analysis of robot based on neural networks , 2008 .

[5] John J. Craig Zhu,et al. Introduction to robotics mechanics and control , 1991 .

[6] Yi Feng,et al. A New Algorithm for Solving Inverse Kinematics of Robot Based on BP and RBF Neural Network , 2014, 2014 Fourth International Conference on Instrumentation and Measurement, Computer, Communication and Control.

[7] Qiang Huang,et al. Target-tools recognition method based on an image feature library for space station cabin service robots , 2016, Robotica.

[8] Zhu Xue-feng. On Improved Algorithm of LMBP Neural Networks , 2008 .

[9] Jianxun Zhang,et al. Algorithm for Multi-joint Redundant Robot Inverse Kinematics Based on the Bayesian - BP Neural Network , 2008, 2008 International Conference on Intelligent Computation Technology and Automation (ICICTA).