《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 人工智能 > 設(shè)計(jì)應(yīng)用 > 基于改進(jìn)PSO算法的機(jī)器人路徑規(guī)劃研究
基于改進(jìn)PSO算法的機(jī)器人路徑規(guī)劃研究
電子技術(shù)應(yīng)用
王友運(yùn)1,,徐堅(jiān)磊2,胡燕海1,陳海輝2,,張行2
1.寧波大學(xué) 機(jī)械工程與力學(xué)學(xué)院;2.寧波航工智能裝備有限公司
摘要: 傳統(tǒng)粒子群算法(PSO)容易早熟收斂,,陷入局部最優(yōu),,為此提出混沌動(dòng)態(tài)多種群粒子群算法(CDMPSO),并將其應(yīng)用在機(jī)器人三維路徑規(guī)劃中,。通過(guò)引入混沌映射理論來(lái)提高粒子種群初始解的質(zhì)量和分布均勻性,,同時(shí)引入分組并行優(yōu)化策略,依據(jù)適應(yīng)度值采用中位數(shù)聚類的方法,,將種群分為3個(gè)子種群并迭代進(jìn)行實(shí)時(shí)動(dòng)態(tài)調(diào)整,,根據(jù)不同子種群的特點(diǎn)采用不同的方法來(lái)進(jìn)行種群更新。在MATLAB軟件中與傳統(tǒng)PSO算法和自適應(yīng)粒子群(APSO)算法進(jìn)行對(duì)比實(shí)驗(yàn),,發(fā)現(xiàn)改進(jìn)后的CDMPSO算法全局搜索范圍更大,,陷入局部最優(yōu)次數(shù)更少,最終路徑更短,,從而驗(yàn)證了該改進(jìn)算法是切實(shí)可行的,。
中圖分類號(hào):TP242 文獻(xiàn)標(biāo)志碼:A DOI: 10.16157/j.issn.0258-7998.234609
中文引用格式: 王友運(yùn),徐堅(jiān)磊,,胡燕海,,等. 基于改進(jìn)PSO算法的機(jī)器人路徑規(guī)劃研究[J]. 電子技術(shù)應(yīng)用,2024,,50(4):75-80.
英文引用格式: Wang Youyun,,Xu Jianlei,Hu Yanhai,,et al. Research on robot path planning based on improved PSO algorithm[J]. Application of Electronic Technique,,2024,50(4):75-80.
Research on robot path planning based on improved PSO algorithm
Wang Youyun1,,Xu Jianlei2,,Hu Yanhai1,Chen Haihui2,,Zhang Xing2
1.School of Mechanical Engineering and Mechanics,, Ningbo University; 2.Ningbo Hanggong Intelligent Equipment Co.,, Ltd.
Abstract: Traditional particle swarm optimization (PSO) is easy to premature convergence and fall into local optimum. Therefore, chaotic dynamic multi swarm particle swarm optimization (CDMPSO) is proposed and applied to robot three-dimensional path planning. The chaotic mapping theory is introduced to improve the quality and distribution uniformity of the initial solution of the particle population. At the same time, the grouping parallel optimization strategy is introduced to divide the population into three sub populations by using the median clustering method according to the fitness value and iterate for real-time dynamic adjustment. Different methods are used to update the population according to the characteristics of different sub populations. Compared with traditional PSO algorithm and adaptive particle swarm optimization (APSO) algorithm in MATLAB software, the improved CDMPSO algorithm has larger global search range, fewer times of falling into local optimum and shorter final path, which verifies that the improved algorithm is feasible.
Key words : path planning,;chaotic mapping;Levy flight;Gaussian variation,;dynamic multigroup parallelism

引言

機(jī)器人路徑規(guī)劃即機(jī)器人依據(jù)某些指標(biāo)在運(yùn)動(dòng)空間中從起點(diǎn)到終點(diǎn)找到一條最優(yōu)的路徑[1],。目前,現(xiàn)實(shí)生活中常見(jiàn)的可用于路徑規(guī)劃的算法包括A-star算法[2],、D-star算法[3],、粒子群(Particle Swarm Optimization,PSO)算法[4],、蟻群優(yōu)化(Ant Colony Optimization,,ACO)算法[5]等。其中粒子群算法用個(gè)體和社會(huì)兩種屬性疊加進(jìn)行搜索,,以其參數(shù)簡(jiǎn)潔,、收斂速度快、搜索效率高等優(yōu)點(diǎn)被廣泛應(yīng)用于機(jī)器人路徑規(guī)劃及優(yōu)化過(guò)程中,。

雖然粒子群算法在機(jī)器人領(lǐng)域的應(yīng)用很廣泛,,但傳統(tǒng)粒子群算法主要是通過(guò)跟蹤粒子個(gè)體極值和全局極值進(jìn)行搜索,這樣粒子就容易在某一極值點(diǎn)上聚集,,從而使算法早熟收斂,,陷入局部最優(yōu)[6]。針對(duì)這一問(wèn)題,,徐福強(qiáng)等人[7]提出引入Circle映射和正弦余弦因子的改進(jìn)粒子群算法,,使用Circle映射來(lái)豐富種群多樣性,采用正余弦因子來(lái)平衡全局探索與局部開(kāi)發(fā)能力,;汪雅文等人[8]提出了融合吸引排斥和雙向?qū)W習(xí)的改進(jìn)粒子群算法,,通過(guò)雙向?qū)W習(xí)策略擴(kuò)大粒子搜索范圍,利用吸引排斥策略提高算法的局部尋優(yōu)和收斂性能,;Yuan等人[9]提出了一種基于差分進(jìn)化的改進(jìn)粒子群算法,,研究出了一種“高強(qiáng)度訓(xùn)練”模式,利用改進(jìn)的差分進(jìn)化算法對(duì)粒子群算法的全局最優(yōu)位置進(jìn)行密集訓(xùn)練,,提高了算法的搜索精度,;陳天培等人[10]提出基于模糊邏輯的改進(jìn)粒子群算法,通過(guò)模糊處理控制路徑規(guī)劃的輸入量,,防止系統(tǒng)陷入局部最優(yōu),;封建湖等人[11]提出了一種聚類融合交叉粒子群算法,,通過(guò)K均值聚類來(lái)保存良性群體的極值位置,,利用交叉和變異算子來(lái)增加粒子多樣性,避免算法在早期就陷入早熟收斂,。

基于以上研究,,本文提出在粒子種群初始化階段引入混沌映射理論,同時(shí)采用動(dòng)態(tài)多種群并行策略來(lái)進(jìn)行改進(jìn),從而得到混沌動(dòng)態(tài)多種群粒子群(Chaotic Dynamic Multi population Particle Swarm Optimization,,CDMPSO)算法,,最后通過(guò)進(jìn)行大量的仿真實(shí)驗(yàn)來(lái)驗(yàn)證改進(jìn)算法的可行性。


本文詳細(xì)內(nèi)容請(qǐng)下載:

http://forexkbc.com/resource/share/2000005952


作者信息:

王友運(yùn)1,,徐堅(jiān)磊2,,胡燕海1,陳海輝2,,張行2

(1.寧波大學(xué) 機(jī)械工程與力學(xué)學(xué)院,,浙江 寧波 315211;2.寧波航工智能裝備有限公司,,浙江 寧波 315311)


Magazine.Subscription.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。