摘要
针对七自由度串联机器人Robai Cyton Gamma 300轨迹规划问题,采用改进遗传算法规划机器人各关节的运动轨迹。利用D-H表示法建立起机器人末端执行器的位姿与参考坐标系之间的齐次变换矩阵,采用遗传算法优化BP神经网络求解机器人的运动学求逆解。利用5次B样条曲线在关节空间构造机器人各关节随时间变化的运动轨迹。在满足运动学约束条件下,对传统遗传算法在编码方式、遗传算子、交叉概率和变异概率等方面进行改进,对机器人各关节运动轨迹进行时间最优规划。运用Matlab对研究进行了仿真实验。结果表明,经改进遗传算法优化后的机器人运动轨迹时间明显缩短,各关节的角速度、加速度和加加速度曲线连续无突变,从而验证了该方法的有效性。
To solve trajectory planning problem of seven degree of freedom serial robot called Robai Cyton Gamma 300,an improved genetic algorithm was applied to plan robot trajectory of each joint. First,D-H notation was used to establish homogeneous transformation matrix between the actuator ＇s posture at the end of the robot and the reference coordinate system. And genetic algorithm was used to optimize the BP neural network to solve the kinematics inverse solution of robot. Then,five B spline curve was applied in the joint space of each joint＇s motion trajectory. Finally,under the condition of kinematic constraint,traditional genetic algorithm was improved on mode of coding,genetic operators,crossover probability and mutation probability,etc,to realize the time optimal planning. By conducting the simulation experiment on Matlab,the results showed the trajectory time of robot was optimized obviously by improved genetic algorithm. Angle velocity and the acceleration and jerk of each joint were continuous,it proved the effectiveness of the proposed method.
作者
马丹妮
李传江
张自强
MA Dan-ni LI Chuan-jiang ZHANG Zi-qiang(Guangdong Planning and Designing Institute of Telecommunications CO. LTD, Guangzhou 528000, China College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China)
出处
《实验室研究与探索》
CAS
北大核心
2016年第9期33-37,共5页
Research and Exploration In Laboratory
基金
上海市科委基金资助项目(11510502400)
