Robot Path Planning Based on Improved Salp Swarm Algorithm

被引：0

作者：

Liu J. ^{[1
,2
]}

Yuan M. ^{[2
,3
]}

Li Y. ^{[4
]}

机构：

[1] Institute of Intelligent Networks System, Henan University, Kaifeng

[2] College of Software, Henan University, Kaifeng

[3] School of Information Engineering, Zhengzhou Institute of Science and Technology, Zhengzhou

[4] Institute of Management Science and Engineering, Henan University, Kaifeng

来源：

Jisuanji Yanjiu yu Fazhan/Computer Research and Development | 2022年 / 59卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Double populations; Hermite interpolation; Inertia weight; Robot path planning; Salp swarm algorithm;

D O I：

10.7544/issn1000-1239.20201016

中图分类号：

学科分类号：

摘要：

To find an improved method to solve the robot path planning problem, a parasitic salp swarm algorithm based on differential evolution strategy is proposed. The position of salp of the previous generation is added into the leader position update formula to enhance the adequacy of global search. At the same time, the inertia weight of nonlinear decreasing trend is introduced to reasonably adjust the balance between the breadth search and the depth mining of salp leaders in different iteration periods, to improve solution accuracy. The following are introduced into the evolutionary structure: 1) The parasitic and host double populations with different evolutionary mechanisms, 2) their parasitic behaviors, and 3) the idea of survival of the fittest, to increase the diversity of the population and improve the ability of the algorithm to jump out of the local extreme value. The theoretical analysis proves that the time complexity of the improved algorithm is the same as that of the basic algorithm, and the simulation experiment is conducted on 10 standard test functions with different characteristics through six representative comparison algorithms. The results show that the optimization accuracy and stability of the algorithm are significantly improved. Finally, the algorithm is combined with the hermite interpolation method to define the algorithm encoding mode based on the path node. The fitness function and constraint conditions are constructed to bypass obstacles and the shortest paths, to solve the robot path planning problem. Experimental results in different complex obstacle scenes and different interpolation methods for robot path planning show that the improved algorithm is superior to the other five comparison algorithms in terms of the best value, the average value and the variance of the solution results, which also proves the superiority and effectiveness of the fusion Hermite interpolation method in solving the robot path planning problem. © 2022, Science Press. All right reserved.

引用

页码：1297 / 1314

页数：17

共 37 条

[1]

Wang Hongwei, Ma Yong, Xie Yong, Et al., Mobile robot path planning based on smooth A<sup>*</sup>algorithm, Journal of Tongji University: Natural Science Edition, 38, 11, pp. 1647-1650, (2010)

[2]

Wang Xingce, Zhang Rubo, Gu Guochang, Global path planning for robots based on potential field grid method, Journal of Harbin Engineering University, 24, 2, pp. 170-174, (2003)

[3]

Yu Zhenzhong, Yan Jihong, Zhao Jie, Et al., Mobile robot path planning based on improved artificial potential field method, Journal of Harbin Institute of Technology, 43, 1, pp. 50-55, (2011)

[4]

Zimmermann M, Konig C., Integration of a visibility graph based path planning method in the ACT/FHS rotorcraft, CEAS Aeronautical Journal, 7, 3, pp. 391-403, (2016)

[5]

Masehian E, Amin-Naseri M R., A Voronoi diagram-visibility graph-potential field compound algorithm for robot path planning, Journal of Robotic Systems, 21, 6, pp. 275-300, (2004)

[6]

Li Baotong, Liu Honglei, Su Wenjun, Topology optimization techniques for mobile robot path planning, Applied Soft Computing Journal, 78, pp. 528-544, (2019)

[7]

Rodriguez-Fdez L, Mucientes M, Bugarin A., Learning fuzzy cotrollers in mobile robotics with embedded preprocessing, Applied Soft Computing, 26, pp. 123-142, (2015)

[8]

Li Weishuo, Sun Jian, Chen Wei, Real-time obstacle avoidance algorithm for robots based on BP neural network, Chinese Journal of Scientific Instrument, 40, 11, pp. 204-211, (2019)

[9]

Liu Zhibin, Zeng Xiaoqin, Liu Huiyi, Et al., A heuristic two-layer reinforcement learning algorithm based on BP neural networks, Journal of Computer Research and Development, 52, 3, pp. 579-587, (2015)

[10]

Zhang Fuhai, Li Ning, Yuan Rupeng, Et al., Robot path planning algorithm based on reinforcement learning, Journal of Huazhong University of Science and Technology: National Science Edition, 46, 12, pp. 65-70, (2018)

← 1 2 3 4 →