EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Efficient path planning for autonomous vehicles based on RRT* with variable probability strategy and artificial potential field approach

Fazhan Tao, Zhaowei Ding, Zhigao Fu, Mengyang Li, Baofeng Ji

Scientific Reports · 21.10.2024 · 14 (1)

DOI: 10.1038/s41598-024-76299-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Reports, online erschienen am 21.10.2024. Verfasst von Fazhan Tao und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, China. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Program for Science and Technology Innovation Talents in the University of Henan Province under Grant, Major Science and Technology Projects of Longmen Laboratory under Grant, National Natural Science Foundation of China under Grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of autonomous driving technology, path planning has gained significant attention as it holds great potential for improving safety. The Rapidly-exploring Random Tree star(RRT*) algorithm has attracted much attention because of its good adaptability and expansibility. However, how solving problems in the RRT* algorithm such as slow convergence time, significant search range randomness, and unpredictability is a challenge. Therefore, an RRT* enhancement algorithm combining variable probability goal-bias strategy and artificial potential field(APF) method(Improved A-RRT*) is proposed in this paper. Firstly, the variable probability goal-bias strategy is introduced in the sampling process to make random tree expand towards the target direction and improve the directional searchability of the random tree. Secondly, the potential field function in APF is improved to prevent falling into local optimum problems during path generation. Thirdly, improved APF is combined with RRT*, the target generates a gravitational field on random tree, and the obstacle generates a repulsive force on it, leading random tree to grow toward the target region. Finally, the proposed algorithm is compared with RRT* algorithm and its derivative algorithm. The experimental results demonstrate that the proposed algorithm has obvious optimizations in convergence speed and path quality.

Autor:innen und Institutionen

  • School of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, China.
  • Longmen Laboratory, Luoyang, 471000, China.
  • Institute of Physics, Henan Academy of Sciences, Zhengzhou, 450046, China.
  • Faculty of Science and Technology, University of Macau, Macau, China.
  • School of Physics and Electronic Information, Luoyang Normal University, Luoyang, 471934, China.
  • Longmen Laboratory, Luoyang, 471000, China. baofengjihkd@163.com.

Förderung

  • Program for Science and Technology Innovation Talents in the University of Henan Province under Grant
  • Major Science and Technology Projects of Longmen Laboratory under Grant
  • National Natural Science Foundation of China under Grant

Zitieren

APA

Tao, F., Ding, Z., Fu, Z., Li, M., & Ji, B. (2024). Efficient path planning for autonomous vehicles based on RRT* with variable probability strategy and artificial potential field approach. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-76299-9

Vancouver

Tao F, Ding Z, Fu Z, Li M, Ji B. Efficient path planning for autonomous vehicles based on RRT* with variable probability strategy and artificial potential field approach. Scientific Reports. 2024;14(1). doi:10.1038/s41598-024-76299-9

BibTeX
@article{Tao2024,
  author = {Tao, Fazhan and Ding, Zhaowei and Fu, Zhigao and Li, Mengyang and Ji, Baofeng},
  title = {Efficient path planning for autonomous vehicles based on RRT* with variable probability strategy and artificial potential field approach},
  journal = {Scientific Reports},
  year = {2024},
  volume = {14},
  number = {1},
  doi = {10.1038/s41598-024-76299-9}
}
Kostenlos starten →