基于AGA的焊接机器人避障轨迹规划  

Obstacle Avoidance Trajectory Planning of Welding Robot Based on AGA

作　　者：张宏 汤小红[1,2] 龚永健 任垒垒 ZHANG Hong;TANG Xiao-hong;GONG Yong-jian;REN Lei-lei(School of Mechanical and Electrical Engineering,Central South University of Forestry and Technology,Changsha 410004,China;School of Electrical Mechanical Engineering,Hunan Institute of Science and Technology,Yueyang 414000,China)

机构地区：[1]中南林业科技大学机电工程学院,长沙410004 [2]湖南理工学院机电工程学院,岳阳414000

出　　处：《组合机床与自动化加工技术》2022年第5期19-23,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：长沙市重点研发计划(Kq2004094)。

摘　　要：针对焊接机器人在焊接过程中运动耗时长,稳定性系数低,避障精度差的问题,采用自适应遗传算法来搜索任务空间中轨迹的最优解。以ABB IRB 120焊接机器人为研究对象,首先,建立机器人D-H运动学模型,采用位姿分离的方法进行逆运动学分析;然后,通过自适应遗传算法对焊接机器人进行避障优化,使其能够快速地找到焊接机器人在焊接运动过程中的最优路径;同时,采用五次多项式插值法逼近任务空间中的轨迹行程。仿真结果表明,与经典遗传算法相比,自适应遗传算法通过自适应调节交叉概率Pc和变异概率Pm的值,能更好地产生新的个体摆脱局部极值,快速地搜索到全局最优解,获得平稳且连续变化的机器人末端点运动轨迹,在一定程度上提高收敛速度与求解精度。Aiming at the problems of long movement time,low stability coefficient and poor obstacle-avoiding accuracy of welding robot in welding process,the adaptive genetic algorithm was used to search the optimal solution of trajectory in task space.Taking ABB IRB 120 welding robot as the research object,the D-H kinematics model of the robot was established firstly,and the inverse kinematics analysis was carried out by using the method of position and pose separation.Then an adaptive genetic algorithm was used to optimize the obstacle avoidance of the welding robot so that it could quickly find the optimal path of the welding robot in the process of welding movement.At the same time,a quintic polynomial interpolation method is used to approximate the trajectory travel in the task space.Simulation results show that compared with the classical genetic algorithm,adaptive genetic algorithm with adaptive adjusting the value of the probability of crossover and mutation probability Pc Pm,better able to generate new individuals out of local minima,search to the global optimal solution quickly and get a smooth and continuous change of the robot end point trajectory,to a certain extent,improve the convergence speed and precision.

关 键 词：焊接机器人 D-H法 自适应遗传算法 位姿分离 五次多项式 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]