thumbnail

Topic

Transport in agriculture

Volume

Volume 71 / No. 3 / 2023

Pages : 548-557

Metrics

Volume viewed 0 times

Volume downloaded 0 times

ANALYSIS ON PATH OPTIMIZATION OF AGRICULTURAL HANDLING ROBOTS BASED ON ANT COLONY-IMPROVED ARTIFICIAL POTENTIAL FIELD METHOD

基于蚁群-改进人工势场法的农业搬运机器人路径规划分析

DOI : https://doi.org/10.35633/inmateh-71-47

Authors

(*) Hexia Chu

Zhumadian Preschool Education College

(*) Corresponding authors:

[email protected] |

Hexia Chu

Abstract

Aiming at the problems of low efficiency and slow function convergence of the ant colony algorithm in path planning of agricultural transport robots, a fusion algorithm combined with the artificial potential field method was proposed. Firstly, the function of each parameter was analyzed according to the mathematical model of the traditional ant colony algorithm, followed by the simulation analysis of the optimal parameters through grid map modeling in MATLAB and data recording. Secondly, the deficiency of the classical artificial potential field method in agriculture, i.e., it could not arrive at the endpoint or realize local locking, was improved by introducing the intermediate point and the relative distance of the target. Finally, the features of the two algorithms were combined and the improved artificial potential field method was integrated with the traditional ant colony algorithm so that the improved artificial potential field method could play a dominant role in the initial path planning stage of agricultural transport robots while the ant colony algorithm exerted the main effect in the later stage with the increase in the pheromone concentration. It was verified through simulation analysis, it was verified that the fusion algorithm of ant colony algorithm and improved artificial potential field method outperforms traditional ant colony algorithm in terms of farthest path, optimal path, running time, and iteration number.

Abstract in Chinese

针对蚁群算法在农业运输机器人路径规划中效率低、函数收敛慢等问题,提出了一种与人工势场法相结合的融合算法。首先,根据传统蚁群算法数学模型对各参数的函数进行分析,并在MATLAB中通过栅格图建模对最优参数进行仿真分析,并记录数据。其次,通过引入中间点和目标相对距离的方法,改善了经典人工势场法在农业中无法到达终点和无法进行局部锁定的问题;最后,结合两种算法的特点,将改进的人工势场法与传统的蚁群算法相结合,使改进的人工势场法在农业运输机器人路径规划的初始阶段发挥主要作用,蚁群算法在后期随着信息素浓度的增加发挥主要作用。通过仿真分析验证了将蚁群算法与改进的人工势场法相融合算法在最远路径、最优路径、运行时间、迭代次数各项数据都优于传统蚁群算法。

Indexed in

Clarivate Analytics.
 Emerging Sources Citation Index
Scopus/Elsevier
Google Scholar
Crossref
Road