[1]封 澳,杨锦宇,谢玉阳,等.基于改进 PRM 算法的机器人路径规划[J].计算机技术与发展,2024,34(02):127-133.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 019]
　FENG Ao,YANG Jin-yu,XIE Yu-yang,et al.Robot Path Planning Based on Improved PRM Algorithm[J].,2024,34(02):127-133.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 019]

点击复制

基于改进 PRM 算法的机器人路径规划()

分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

34

期数:

2024年02期

页码:

127-133

栏目:

人工智能

出版日期:

2024-02-10

文章信息/Info

Title:

Robot Path Planning Based on Improved PRM Algorithm

文章编号:

1673-629X(2024)02-0127-07

作者:

封 澳¹ ; 杨锦宇² ; 谢玉阳³ ; 孙延康¹ ; 王璇之³ ; 肖 建^1*

1. 南京邮电大学 集成电路科学与工程学院,江苏 南京 210023;

2. 金陵中学 中美班,江苏 南京 210041;

3. 南京邮电大学 电子与光学工程学院、柔性电子(未来技术)学院,江苏 南京 210023

Author(s):

FENG Ao1 ; YANG Jin-yu2 ; XIE Yu-yang3 ; SUN Yan-kang1 ; WANG Xuan-zhi3 ; XIAO Jian1*

1. School of Integrated Circuit Science and Engineering,Nanjing University of Posts and Telecommunications, Nanjing 210023,China;

2. Sino American Class,Jinling High School,Nanjing 210041,China;

3. School of Electronic and Optical Engineering and School of Flexible Electronics ( Future Technology) , Nanjing University of Posts and Telecommunications,Nanjing 210023,China

关键词:

概率路线图; 路径规划; 路径优化策略; Sobol 序列; 贝塞尔曲线

Keywords:

probability roadmap; path planning; path optimization strategy; Sobol sequence; Bessel curve

分类号:

TP242

DOI:

10. 3969 / j. issn. 1673-629X. 2024. 02. 019

摘要:

概率路线图( Probabilistic Roadmap,PRM)算法是移动机器人领域常用的路径规划算法。 针对传统 PRM 算法存在采样点分布不均匀、路线图构建效率低以及路径冗余不平滑等问题,提出了一种改进 PRM 算法。 使用二维 Sobol 序列优化采样策略,保证采样点全局均匀分布,优化采样点的覆盖面积,提高了采样点的质量;其次,对采样点进行邻域分类并施加连接约束,使相邻邻域采样点进行连接,减少路线图的大小,提高了路线图的构图和搜索效率;接着,使用节点平移优化算法优化节点位置,使优化路径符合实际空间中的最优路径;最后,使用贝塞尔曲线平滑路径拐点,使生成的路径更符合机器人的实际运动约束。 大量仿真实验结果表明,改进 PRM 算法可以有效提升规划路径的质量且受采样点数量的影响较小。 相比于传统 PRM 算法和其他改进 PRM 算法,提出的 PRM 算法在路径长度、运行时间和成功率上具有明显优势。

Abstract:

Probabilistic Roadmap ( PRM) is a commonly used path planning algorithm in the field of mobile robots. Aiming at theproblems of uneven distribution of sampling points,low efficiency of road map construction and unsmooth path redundancy in traditionalPRM,an improved PRM is proposed. The two-dimensional Sobol sequence is used to optimize the sampling strategy to ensure the globaluniform distribution of sampling points, optimize the coverage area of sampling points, and improve the quality of sampling points.Secondly,the sampling points are classified by neighborhood and the connection constraint is applied to connect the sampling points in theadjacent domain,which reduces the size of the roadmap and improves the composition and search efficiency of the roadmap. Then,thenode translation optimization algorithm is used to optimize the node position,so that the optimized path conforms to the optimal path inthe actual space. Finally,the Bessel curve is used to smooth the path inflection point,so that the generated path is more in line with theactual motion constraints of the robot. A large number of simulation results show that the improved PRM can effectively improve thequality of the planning path and is less affected by the number of sampling points. Compared with the traditional PRM and otherimproved PRM,the proposed PRM has obvious advantages in path length,running time and success rate.

常用功能