基于改进多目标粒子群算法的机器人轨迹规划研究  

The robot trajectory planning based on improved multi-objective particle swarm optimization

作　　者：黄婷婷[1] Huang Tingting(Sino German Institute of Engineering,Shanghai Technical Institute of Electronics and Information,Shanghai,201411,China)

机构地区：[1]上海电子信息职业技术学院中德工程学院,上海201411

出　　处：《机械设计与制造工程》2023年第11期37-42,共6页Machine Design and Manufacturing Engineering

基　　金：2021年度上海市教育科学研究项目(C20211078)。

摘　　要：针对传统机器人轨迹规划算法无法实现全局寻优的问题,提出一种基于改进多目标粒子群的机器人轨迹规划算法。首先对机器人的当前位置进行定位并确定偏转角度,在粒子寻优过程中引入一种外部机制形成非劣解容器,引入SA算法对种群内部的粒子位置进行重新排布,避免解集陷入局部最优;再根据多机器人拥塞概率进行分解和乘积表征,消解冲突,避免发生碰撞。实验结果显示:所提算法能够规划出一条最短的路径,并可以有效地避免机器人发生碰撞,且移动时间少于传统算法。Aiming at the problem that traditional robot trajectory planning algorithms cannot achieve global optimization,a robot trajectory planning scheme based on improved multi-objective particle swarm is proposed.First,the current position of the robot is located and the deflection angle is determined.In the particle optimization process,an external mechanism is introduced to form a non-inferior solution container,so as to realize the global path optimization better.The SA algorithm is introduced to rearrange the particle positions in the population to avoid the solution set falling into the local optimal.Then,according to the congestion probability of multiple robots,the decomposition and product characterization are carried out to resolve conflicts and avoid collisions.The experimental results show that the proposed algorithm can identify the shortest and most economical trajectory path,and can effectively avoid robot collision,and the moving time is lower than the traditional algorithm.

关 键 词：改进多目标粒子群 物流机器人 轨迹规划 乘积表征 冲突消解 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]