基于改进模拟退火遗传算法的机械臂轨迹优化  

Trajectory Optimization of Robotic Arm Based on Improved Simulated Annealing Genetic Algorithm

作　　者：徐强 徐坚磊 胡燕海[1] 陈海辉 张行 邢兆辉 Xu Qiang;Xu Jianlei;Hu Yanhai;Chen Haihui;Zhang Xing;Xing Zhaohui(College of Mechanical Engineering and Mechanics,Ningbo University,Ningbo 315211,China;Ningbo Hanggong Intelligent Equipment Co.,Ltd.,Ningbo 315311,China)

机构地区：[1]宁波大学机械工程与力学学院,浙江宁波315211 [2]宁波航工智能装备有限公司,浙江宁波315311

出　　处：《系统仿真学报》2025年第2期404-412,共9页Journal of System Simulation

基　　金：国家自然科学基金(51705263);宁波市重点研发计划(2023Z169)。

摘　　要：为了优化机械臂的工作轨迹,提出了一种改进模拟退火遗传算法。综合考虑机械臂的作业要求及性能特点,利用五次多项式插值的方法在关节空间内规划出一条平滑的运动轨迹。通过罚函数法处理不满足约束条件的个体,动态线性标定法对适应度函数进行重新标定。设置一种交叉概率和变异概率自适应调节机制改进遗传算法,并引入模拟退火算法的退火思想,有效避免了算法陷入局部最优。仿真结果表明:改进模拟退火遗传算法优化后的轨迹相比传统遗传算法有效缩短了机械臂的运动时间,进而提高了机械臂的工作效率。To optimize the working trajectory of the robotic arm,a modified simulated annealing genetic algorithm is proposed.Comprehensively considering the operating requirements and performance characteristics of the robotic arm,the five-order polynomial interpolation method is used to plan a smooth motion trajectory in the joint space.The penalty function method is used to handle the individuals that do not meet the constraint conditions,and the fitness function is recalibrated by the dynamic linear calibration method.An adaptive adjustment mechanism for crossover probability and variation probability is set to modify the genetic algorithm.The cooling idea of the simulated annealing algorithm is introduced,which effectively avoids the algorithm falling into locally optimal.The results show that the optimized trajectory of the improved simulated annealing genetic algorithm effectively shortens the movement time of the robotic arm compared with the traditional genetic algorithm,and then improves the working efficiency of the robotic arm.

关 键 词：机械臂 五次多项式插值 模拟退火遗传算法 轨迹优化 罚函数法 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] TP391.9[自动化与计算机技术—控制科学与工程]