EUVIMEDEUVIMED entdecken
Crossref

Application of an Improved Swarm Optimization in Robot Autonomous Navigation System

Yi Zhang, Haoran Li, Yifei Cai, Yue Zhao, Tianshu You, Yong Xu

Concurrency and Computation: Practice and Experience · 2026-07 · 38 (14)

DOI: 10.1002/cpe.70740 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 12.07.2026. Verfasst von Yi Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aiming at the problems of slow convergence speed and low computational efficiency in robot path planning in dynamic environments, a combination of swarm intelligence optimization algorithm is proposed to solve the above problems. Swarm intelligence optimization algorithms have garnered significant attention for addressing complex engineering challenges, owing to their inherent robustness and flexibility. Among these, the Painted Kingfisher Optimization (PKO) is a recently developed metaheuristic recognized for its structural simplicity and rapid convergence. However, when tackling high‐dimensional or non‐linear tasks, the original PKO often suffers from stagnation in population diversity and a tendency to become trapped in local optima, which limits its optimization precision in complex landscapes. To surmount these deficiencies, this paper proposes a multi‐strategy Improved Painted Kingfisher Optimization (IPKO) algorithm. The proposed framework incorporates a multi‐dimensional initialization strategy based on quantum computing to enhance population diversity and utilizes a dynamic mutation mechanism of quantum gates to refine population quality. Furthermore, an attenuation factor E and a joiner strategy derived from the Sparrow Search Algorithm (SSA) are integrated into the symbiotic phase to accelerate convergence toward optimal regions. The performance of IPKO was rigorously evaluated against multiple state‐of‐the‐art algorithms using the CEC2021 (10 functions) and CEC2022 (12 functions) test suites. Experimental results demonstrate that IPKO significantly outperforms its competitors across the majority of benchmark cases. Finally, the practical utility of IPKO is validated through its application to autonomous robot navigation and multi‐robot dynamic path planning. Compared to the original PKO, IPKO consistently yields superior optimal and average path lengths in both simple and complex scenarios. Notably, in multi‐robot dynamic tasks, the maximum single‐step time of IPKO decreased by approximately 15% and 20% in Scenarios 1 and 3, respectively. In Scenario 2, the average decision time was reduced from 0.1269 s/step (PKO) to 0.0891 s/step (IPKO), representing a significant enhancement of 29.8%.

Zitieren

APA

Zhang, Y., Li, H., Cai, Y., Zhao, Y., You, T., & Xu, Y. (2026). Application of an Improved Swarm Optimization in Robot Autonomous Navigation System. Concurrency and Computation: Practice and Experience, 38(14). https://doi.org/10.1002/cpe.70740

Vancouver

Zhang Y, Li H, Cai Y, Zhao Y, You T, Xu Y. Application of an Improved Swarm Optimization in Robot Autonomous Navigation System. Concurrency and Computation: Practice and Experience. 2026;38(14). doi:10.1002/cpe.70740

BibTeX
@article{Zhang2026,
  author = {Zhang, Yi and Li, Haoran and Cai, Yifei and Zhao, Yue and You, Tianshu and Xu, Yong},
  title = {Application of an Improved Swarm Optimization in Robot Autonomous Navigation System},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2026},
  volume = {38},
  number = {14},
  doi = {10.1002/cpe.70740}
}
Kostenlos starten →