机器人逆标定方法研究

在分析传统机器人位姿标定方法的基础上，提出了一种新的机器人标定方法：基于神经网络的逆标定方法。这种标定方法把机器人实际位姿和相应的关节角误差分别作为前馈神经网络的输入和输出来训练网络，从而获得机器人任意位姿时的关节角误差值，通过修改关节值来提高机器人的位姿精度。这种标定方法把所有因素引起的误差均归结为关节角误差，无须求解机器人逆运动学方程，实现了误差的在线补偿。把标定结果与基于运动学模型的参数法的标定结果进行了比较分析。仿真和试验结果均证明了这种方法比传统方法标定效果更好，且更方便简单，避免了其他传统标定方法繁琐的建模及参数辨识过程。

Study on robot inverse calibration

An innovative robot calibration approach: inverse robot calibration based on neural network,was proposed in this paper,based on the analysis of traditional calibration approach.This method took the robot actual poses and corresponding joint errors as inputs and outputs of a feed-forward neural network respectively, so as to achieve the real-time joint errors in arbitrary pose through the neural network,and pose accuracy was improved only through correcting the joints angles.This calibration came down all error effects to joint errors and need not resolve the inverse kinematics model,and achieved arbitrary joint errors realtime compensation.Calibration results were compared with those obtained by traditional parametric methodologies.Simulation and experimental results show that this method is more effective compared with the traditional calibration methods, and avoids the complex modeling and parameters identification.