Robot path planning based on obstacle avoidance optimization and improved ant colony algorithm

Aimed at the problems of slow convergence speed and redundant planning paths in the processing of path planning by ant colony algorithm, an improved ant colony algorithm based on obstacle avoidance information and fast optimization search strategy was proposed. In order to improve the first search e...

Full description

Saved in:
Bibliographic Details
Main Authors: HE Xingshi, CHEN Huiyuan
Format: Article
Language:zho
Published: Editorial Office of Journal of XPU 2024-06-01
Series:Xi'an Gongcheng Daxue xuebao
Subjects:
Online Access:http://journal.xpu.edu.cn/en/#/digest?ArticleID=1474
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321830771326976
author HE Xingshi
CHEN Huiyuan
author_facet HE Xingshi
CHEN Huiyuan
author_sort HE Xingshi
collection DOAJ
description Aimed at the problems of slow convergence speed and redundant planning paths in the processing of path planning by ant colony algorithm, an improved ant colony algorithm based on obstacle avoidance information and fast optimization search strategy was proposed. In order to improve the first search efficiency and accuracy of the ant colony, the Chebyshev distance was introduced to improve the distance heuristic function, and the guidance of the target point to the robot was enhanced in the transfer probability. The adaptive transfer probability was used to adjust the selection method of nodes during path planning and the setting of initial pheromones based on the distribution of obstacles around the nodes, and the percentage that the ants generate effective paths for the first time increased from 60% to 92%. The garbage information of the generated paths was removed, increasing the pheromone concentration of the optimal path nodes, balancing the local and global searching ability of the ant colony, and speeding up the optimal path. By smoothing the generated paths, the number of robot turns was reduced and the path distance was shortened. The algorithms SSA, ACO, IACO, and I-ACO were selected for performance testing on three grid environments. The results show that the improved ACO algorithm outperforms the other algorithms on path optimization.
format Article
id doaj-art-18f6df0ab25841dc9174ca541ee9d5c9
institution Kabale University
issn 1674-649X
language zho
publishDate 2024-06-01
publisher Editorial Office of Journal of XPU
record_format Article
series Xi'an Gongcheng Daxue xuebao
spelling doaj-art-18f6df0ab25841dc9174ca541ee9d5c92025-08-20T03:49:37ZzhoEditorial Office of Journal of XPUXi'an Gongcheng Daxue xuebao1674-649X2024-06-0138310010810.13338/j.issn.1674-649x.2024.03.014Robot path planning based on obstacle avoidance optimization and improved ant colony algorithmHE Xingshi0CHEN Huiyuan1School of Science, Xi’an Polytechnic University, Xi’an 710048, ChinaSchool of Science, Xi’an Polytechnic University, Xi’an 710048, ChinaAimed at the problems of slow convergence speed and redundant planning paths in the processing of path planning by ant colony algorithm, an improved ant colony algorithm based on obstacle avoidance information and fast optimization search strategy was proposed. In order to improve the first search efficiency and accuracy of the ant colony, the Chebyshev distance was introduced to improve the distance heuristic function, and the guidance of the target point to the robot was enhanced in the transfer probability. The adaptive transfer probability was used to adjust the selection method of nodes during path planning and the setting of initial pheromones based on the distribution of obstacles around the nodes, and the percentage that the ants generate effective paths for the first time increased from 60% to 92%. The garbage information of the generated paths was removed, increasing the pheromone concentration of the optimal path nodes, balancing the local and global searching ability of the ant colony, and speeding up the optimal path. By smoothing the generated paths, the number of robot turns was reduced and the path distance was shortened. The algorithms SSA, ACO, IACO, and I-ACO were selected for performance testing on three grid environments. The results show that the improved ACO algorithm outperforms the other algorithms on path optimization.http://journal.xpu.edu.cn/en/#/digest?ArticleID=1474robot path planningobstacle avoidance optimizationant colony optimization algorithmgrid mappath smoothing
spellingShingle HE Xingshi
CHEN Huiyuan
Robot path planning based on obstacle avoidance optimization and improved ant colony algorithm
Xi'an Gongcheng Daxue xuebao
robot path planning
obstacle avoidance optimization
ant colony optimization algorithm
grid map
path smoothing
title Robot path planning based on obstacle avoidance optimization and improved ant colony algorithm
title_full Robot path planning based on obstacle avoidance optimization and improved ant colony algorithm
title_fullStr Robot path planning based on obstacle avoidance optimization and improved ant colony algorithm
title_full_unstemmed Robot path planning based on obstacle avoidance optimization and improved ant colony algorithm
title_short Robot path planning based on obstacle avoidance optimization and improved ant colony algorithm
title_sort robot path planning based on obstacle avoidance optimization and improved ant colony algorithm
topic robot path planning
obstacle avoidance optimization
ant colony optimization algorithm
grid map
path smoothing
url http://journal.xpu.edu.cn/en/#/digest?ArticleID=1474
work_keys_str_mv AT hexingshi robotpathplanningbasedonobstacleavoidanceoptimizationandimprovedantcolonyalgorithm
AT chenhuiyuan robotpathplanningbasedonobstacleavoidanceoptimizationandimprovedantcolonyalgorithm