基于神经网络的空间7R机器人模型辨识及其实验研究

Theoretical and Experimental Study on Model Identification of Spatial 7R Robots Based on Neural Networks

针对空间冗余机器人建模中不确定因素的影响 ,采用神经网络辨识空间 7R机器人输入输出间的非线性关系 ,建立机器人的运动学模型。对Elman动态递归网络结构作了改进 ,提出一种状态延迟输入动态递归神经网络 ,提高了网络的学习速度。将该网络应用到机器人系统模型的辨识问题上 ,以德国PowerCubeTM模块化机器人为研究对象 ,根据机器人返回的关节位置信息及利用OPTOTRAK 30 2 0三维运动测量系统测得的机器人末端位置信息作为神经网络的学习样本 ,对包含各种影响因素的机器人运动模型进行了辨识 ,得到了满意的结果 。

Neural network is used in this paper to identify the model of spatial redundant robot systems with unpredictable disturbances. A new neural network named State Delay Input Dynamical Recurrent Neural Network (SDIDRNN) is presented on the basis of Elman network to increase the learning ability. This new neural network is applied to the experimental study of the model identification for the PowerCube TM modular robot system. The data of joint positions retrieved from the robot and the position data of the end effector measured by the OPTOTRAK 3020 are used as learning sets for neural network. Simulation results are satisfactory and the learning superiority of the new neural network is illustrated.