摘要
为了标定一般7R冗余度串联机器人的所有几何参数,提出了一种实效的算法.首先,使用D-H矩阵对机器人建立了运动学模型和几何参数识别模型,对雅可比矩阵进行奇异值分解并对分解后的正交阵的最后5行进行初等行变换,以确定需要补偿的几何参数.通过机器人关节角和末端手爪位置的测量数据,计算雅可比矩阵以及手爪位置理论值和实测值的误差,采用最小二乘法对机器人的尺寸参数进行补偿量的计算.仿真过程表明,在有测量扰动的情况下,算法是稳定的和可靠的.最后,对机器人进行了实际的测量和标定,取得了满意的结果.
A practical algorithm is presented to calibrate all the geometric parameters of general 7R redundant serial robots. First of all, D-H matrix is used to construct a kinematics model and a geometric parameter identification model for the robot, singular value decomposition （SVD） for Jacobian matrix is given, and elementary row operations are applied to the last 5 rows of the matrix to find the geometric parameters to be compensated. According to the measured values of the joint angles and the end-effector positions, Jacobian matrix is calculated, and errors between the desired and the measured positions of the end-effector are exported to the least square method to determine the compensation for the dimensional parameters of the robot. The simulation shows that the algorithm is stable and reliable in the presence of small measurement disturbance. At last, an experiment of measurement and calibration is made on the robot, and the results obtained are effective and satisfactory.
出处
《机器人》
EI
CSCD
北大核心
2006年第5期483-487,494,共6页
Robot
基金
国家973计划资助项目(2004CB318000)
国家自然科学基金资助项目(50475161)
2004年教育部科学技术研究重点项目(104043)
高等学校博士学科点专项科研基金资助项目(20050013006)
关键词
标定
仿真
最小二乘法
奇异值分解
运动学模型
calibration
simulation
least squares method
singular value decomposition （SVD）
kinematics model
