基于改进遗传算法的机械臂时间最优轨迹优化  

Time-optimal Trajectory Optimization of Collaborative Manipulator Based on Improved Genetic Algorithm

作　　者：李甚霖 曾庆生[1] 冯栋彦[1] 夏广健 LI Shenling;ZENG Qingsheng;FENG Dongyan;XIA Guangjian(School of Mechanical Engineering,University of South China,Hengyang 421001,China)

机构地区：[1]南华大学机械工程学院,衡阳421001

出　　处：《自动化与仪表》2024年第10期60-65,共6页Automation & Instrumentation

摘　　要：针对传统遗传算法在优化机械臂轨迹时间时存在易陷入局部最优、后期局部搜索精度不高等问题,提出了一种改进型遗传算法。使用Tent映射初始化种群,增强遗传算法全局搜索能力。引入模拟退火算法对每一代子代种群进行局部退火操作,提升算法跳出局部最优的能力,在算法后期使用萤火虫算法替代常规变异算子,提高算法后期局部搜索精度。以aubo-i10协作机械臂为对象进行时间优化仿真,结果表明,改进后的遗传算法优化时间相比传统遗传算法减少了约1.2 s,并使机械臂各关节的角速度、角加速度曲线光滑连续,且满足最大约束条件,证明了算法的可行性和有效性。Aiming at the problems of traditional genetic algorithm in optimizing the trajectory time of manipulator,such as easy to fall into the local optimum and low precision of local search at the later stage,an improved genetic algorithm is proposed.Tent mapping is used to initialize the population to enhance the global search ability of the genetic algorithm.The simulated annealing algorithm is introduced to carry out local annealing operation for each generation of the offspring population to enhance the ability of the algorithm to jump out of the local optimum,and the firefly algorithm is used to replace the conventional variational operator at the later stage of the algorithm to improve the local search accuracy of the algorithm at the later stage of the algorithm.The aubo-i10 collaborative manipulator is used as the object for time optimization simulation,and the results show that the optimization time of the improved genetic algorithm is reduced by about 1.2 s compared with the traditional genetic algorithm,and the angular velocity and angular acceleration curves of the joints of the manipulator are smooth and continuous and satisfy the maximum constraints,which proves the feasibility and effectiveness of the algorithm.

关 键 词：轨迹规划 轨迹优化 改进遗传算法 模拟退火算法 萤火虫算法 协作机械臂 

分 类 号：TH-39[机械工程] TP241[自动化与计算机技术—检测技术与自动化装置]