Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem

Chao Xu; Jianjun Tan; Jie Jiao; Yang Long; Mahmoud S. Abouomar

doi:10.3233/ATDE240500

Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem

Chao Xu
, Jianjun Tan
, Jie Jiao
, Yang Long^*
, Mahmoud S. Abouomar

^*Corresponding author for this work

Interdisciplinary Research Center for Smart Mobility and Logistics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

To address the slow convergence speed of genetic algorithms (GAs) in solving the mobile robot path planning problem, this study proposes a genetic algorithm with quality of population evolution (QPEGA). In QPEGA, the population is divided into two subpopulations based on the quality of individuals, and the quality of each subpopulation is defined. The crossover and mutation probabilities of each subpopulation are dynamically adjusted to enhance the algorithm's solving quality. Additionally, the optimal parameter combination for the algorithm is determined using the orthogonal experimental method. To evaluate the performance of QPEGA, a comparison is made with standard GA and adaptive genetic algorithm (AGA). The planning results are subjected to Friedman test at a 95% confidence interval, and the experimental findings demonstrate that QPEGA outperforms the comparative algorithms and exhibits significant advantages in solving the path planning problem.

Original language	English
Title of host publication	Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024
Editors	Ljiljana Trajkovic, Sos S. Agaian, Yu-Dong Zhang, Danilo Pelusi, Qingsheng Feng, Jingsha He
Publisher	IOS Press BV
Pages	517-529
Number of pages	13
ISBN (Electronic)	9781643685243
DOIs	https://doi.org/10.3233/ATDE240500
State	Published - 1 Jul 2024
Event	5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024 - Dalian, China Duration: 12 Apr 2024 → 14 Apr 2024

Publication series

Name	Advances in Transdisciplinary Engineering
Volume	57
ISSN (Print)	2352-751X
ISSN (Electronic)	2352-7528

Conference

Conference	5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024
Country/Territory	China
City	Dalian
Period	12/04/24 → 14/04/24

Bibliographical note

Publisher Copyright:
© 2024 The Authors.

Keywords

Mobile robot
genetic algorithm
path planning
population evolution

ASJC Scopus subject areas

Computer Science Applications
Industrial and Manufacturing Engineering
Software
Algebra and Number Theory
Strategy and Management

Access to Document

10.3233/ATDE240500

Cite this

Xu, C., Tan, J., Jiao, J., Long, Y., & Abouomar, M. S. (2024). Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem. In L. Trajkovic, S. S. Agaian, Y.-D. Zhang, D. Pelusi, Q. Feng, & J. He (Eds.), Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024 (pp. 517-529). (Advances in Transdisciplinary Engineering; Vol. 57). IOS Press BV. https://doi.org/10.3233/ATDE240500

Xu, Chao ; Tan, Jianjun ; Jiao, Jie et al. / Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem. Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024. editor / Ljiljana Trajkovic ; Sos S. Agaian ; Yu-Dong Zhang ; Danilo Pelusi ; Qingsheng Feng ; Jingsha He. IOS Press BV, 2024. pp. 517-529 (Advances in Transdisciplinary Engineering).

@inproceedings{ee4f8482fc6a4ca4b64393572ffd0a3b,

title = "Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem",

abstract = "To address the slow convergence speed of genetic algorithms (GAs) in solving the mobile robot path planning problem, this study proposes a genetic algorithm with quality of population evolution (QPEGA). In QPEGA, the population is divided into two subpopulations based on the quality of individuals, and the quality of each subpopulation is defined. The crossover and mutation probabilities of each subpopulation are dynamically adjusted to enhance the algorithm's solving quality. Additionally, the optimal parameter combination for the algorithm is determined using the orthogonal experimental method. To evaluate the performance of QPEGA, a comparison is made with standard GA and adaptive genetic algorithm (AGA). The planning results are subjected to Friedman test at a 95\% confidence interval, and the experimental findings demonstrate that QPEGA outperforms the comparative algorithms and exhibits significant advantages in solving the path planning problem.",

keywords = "Mobile robot, genetic algorithm, path planning, population evolution",

author = "Chao Xu and Jianjun Tan and Jie Jiao and Yang Long and Abouomar, \{Mahmoud S.\}",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors.; 5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024 ; Conference date: 12-04-2024 Through 14-04-2024",

year = "2024",

month = jul,

day = "1",

doi = "10.3233/ATDE240500",

language = "English",

series = "Advances in Transdisciplinary Engineering",

publisher = "IOS Press BV",

pages = "517--529",

editor = "Ljiljana Trajkovic and Agaian, \{Sos S.\} and Yu-Dong Zhang and Danilo Pelusi and Qingsheng Feng and Jingsha He",

booktitle = "Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024",

address = "Netherlands",

}

Xu, C, Tan, J, Jiao, J, Long, Y & Abouomar, MS 2024, Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem. in L Trajkovic, SS Agaian, Y-D Zhang, D Pelusi, Q Feng & J He (eds), Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024. Advances in Transdisciplinary Engineering, vol. 57, IOS Press BV, pp. 517-529, 5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024, Dalian, China, 12/04/24. https://doi.org/10.3233/ATDE240500

Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem. / Xu, Chao; Tan, Jianjun; Jiao, Jie et al.
Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024. ed. / Ljiljana Trajkovic; Sos S. Agaian; Yu-Dong Zhang; Danilo Pelusi; Qingsheng Feng; Jingsha He. IOS Press BV, 2024. p. 517-529 (Advances in Transdisciplinary Engineering; Vol. 57).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem

AU - Xu, Chao

AU - Tan, Jianjun

AU - Jiao, Jie

AU - Long, Yang

AU - Abouomar, Mahmoud S.

PY - 2024/7/1

Y1 - 2024/7/1

N2 - To address the slow convergence speed of genetic algorithms (GAs) in solving the mobile robot path planning problem, this study proposes a genetic algorithm with quality of population evolution (QPEGA). In QPEGA, the population is divided into two subpopulations based on the quality of individuals, and the quality of each subpopulation is defined. The crossover and mutation probabilities of each subpopulation are dynamically adjusted to enhance the algorithm's solving quality. Additionally, the optimal parameter combination for the algorithm is determined using the orthogonal experimental method. To evaluate the performance of QPEGA, a comparison is made with standard GA and adaptive genetic algorithm (AGA). The planning results are subjected to Friedman test at a 95% confidence interval, and the experimental findings demonstrate that QPEGA outperforms the comparative algorithms and exhibits significant advantages in solving the path planning problem.

AB - To address the slow convergence speed of genetic algorithms (GAs) in solving the mobile robot path planning problem, this study proposes a genetic algorithm with quality of population evolution (QPEGA). In QPEGA, the population is divided into two subpopulations based on the quality of individuals, and the quality of each subpopulation is defined. The crossover and mutation probabilities of each subpopulation are dynamically adjusted to enhance the algorithm's solving quality. Additionally, the optimal parameter combination for the algorithm is determined using the orthogonal experimental method. To evaluate the performance of QPEGA, a comparison is made with standard GA and adaptive genetic algorithm (AGA). The planning results are subjected to Friedman test at a 95% confidence interval, and the experimental findings demonstrate that QPEGA outperforms the comparative algorithms and exhibits significant advantages in solving the path planning problem.

KW - Mobile robot

KW - genetic algorithm

KW - path planning

KW - population evolution

UR - https://www.scopus.com/pages/publications/85198525851

U2 - 10.3233/ATDE240500

DO - 10.3233/ATDE240500

M3 - Conference contribution

AN - SCOPUS:85198525851

T3 - Advances in Transdisciplinary Engineering

SP - 517

EP - 529

BT - Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024

A2 - Trajkovic, Ljiljana

A2 - Agaian, Sos S.

A2 - Zhang, Yu-Dong

A2 - Pelusi, Danilo

A2 - Feng, Qingsheng

A2 - He, Jingsha

PB - IOS Press BV

T2 - 5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024

Y2 - 12 April 2024 through 14 April 2024

ER -

Xu C, Tan J, Jiao J, Long Y, Abouomar MS. Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem. In Trajkovic L, Agaian SS, Zhang YD, Pelusi D, Feng Q, He J, editors, Image Processing, Electronics and Computers - Proceedings of the 5th Asia-Pacific Conference, IPEC 2024. IOS Press BV. 2024. p. 517-529. (Advances in Transdisciplinary Engineering). doi: 10.3233/ATDE240500

Genetic Algorithm with Quality of Population Evolution for Mobile Robot Path Planning Problem

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this