EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Swarm Intelligence for Obstacle Avoidance with Multi-Strategy and Improved Dung Beetle Optimization Algorithm in Mobile Robot Navigation

Longhai Li, Lili Liu, Yuxuan Shao, Xu Zhang, Yue Chen, Ce Guo, Heng Nian

Electronics · 30.10.2023 · 12 (21) · 4462

DOI: 10.3390/electronics12214462 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 30.10.2023. Verfasst von Longhai Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of the Jiangsu Higher Education Institutions of China, Xuzhou University of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Dung Beetle Optimization (DBO) algorithm is a powerful metaheuristic algorithm that is widely used for optimization problems. However, the DBO algorithm has limitations in balancing global exploration and local exploitation capabilities, often leading to getting stuck in local optima. To overcome these limitations and address global optimization problems, this study introduces the Multi-Strategy and Improved DBO (MSIDBO) Algorithm. The MSIDBO algorithm incorporates several advanced computational techniques to enhance its performance. Firstly, it introduces a random reverse learning strategy to improve population diversity and mitigate early convergence or local stagnation issues present in the DBO algorithm. Additionally, a fitness-distance balancing strategy is employed to better manage the trade-off between diversity and convergence within the population. Furthermore, the algorithm utilizes a spiral foraging strategy to enhance precision, promote strong exploratory capabilities, and prevent being trapped in local optima. To further enhance the global search ability and particle utilization of the MSIDBO algorithm, it combines the Optimal Dimension-Wise Gaussian Mutation strategy. By minimizing premature convergence, population diversity is increased, and the convergence of the algorithm is accelerated. This expansion of the search space reduces the likelihood of being trapped in local optima during the evolutionary process. To demonstrate the effectiveness of the MSIDBO algorithm, extensive experiments are conducted using benchmark test functions, comparing its performance against other well-known metaheuristic algorithms. The results highlight the feasibility and superiority of MSIDBO in solving optimization problems. Moreover, the MSIDBO algorithm is applied to path planning simulation experiments to showcase its practical application potential. A comparison with the DBO algorithm shows that MSIDBO generates shorter and faster paths, effectively addressing real-world application problems.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of the Jiangsu Higher Education Institutions of China
  • Xuzhou University of Technology
  • Jiangsu Industry University
  • National Defense Basic Scientific Research Project

Zitieren

APA

Li, L., Liu, L., Shao, Y., Zhang, X., Chen, Y., Guo, C., & Nian, H. (2023). Enhancing Swarm Intelligence for Obstacle Avoidance with Multi-Strategy and Improved Dung Beetle Optimization Algorithm in Mobile Robot Navigation. Electronics, 12(21), 4462. https://doi.org/10.3390/electronics12214462

Vancouver

Li L, Liu L, Shao Y, Zhang X, Chen Y, Guo C, et al. Enhancing Swarm Intelligence for Obstacle Avoidance with Multi-Strategy and Improved Dung Beetle Optimization Algorithm in Mobile Robot Navigation. Electronics. 2023;12(21):4462. doi:10.3390/electronics12214462

BibTeX
@article{Li2023,
  author = {Li, Longhai and Liu, Lili and Shao, Yuxuan and Zhang, Xu and Chen, Yue and Guo, Ce and Nian, Heng},
  title = {Enhancing Swarm Intelligence for Obstacle Avoidance with Multi-Strategy and Improved Dung Beetle Optimization Algorithm in Mobile Robot Navigation},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {21},
  pages = {4462},
  doi = {10.3390/electronics12214462}
}
Kostenlos starten →