EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Bio-Inspired Geomagnetic Navigation Method Based on Hybrid Reinforcement Learning and Greedy Descent

Jiaojiao Guo, Binfeng Yang, Xiaolin Ji, Jiazheng Liu, Min Yang, Hanbing Wang, Yukun Li

Geomatics · 19.11.2026 · 6 (6) · 147

DOI: 10.3390/geomatics6060147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geomatics, online erschienen am 19.11.2026. Verfasst von Jiaojiao Guo und 6 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Basic Research Program of Shaanxi — General Program — Youth Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Geomagnetic navigation offers geospatial positioning in GNSS-denied environments, using the global geomagnetic reference field as a continuously available reference. Traditional map-free bio-inspired navigation, however, relies on random search, which limits experience accumulation and search efficiency. To overcome this, this paper proposes a hybrid reinforcement learning and greedy descent (RL-GD) method. A state–action value table (Q-table) is trained offline in a simulation environment with randomly sampled start and target points using the 14th generation International Geomagnetic Reference Field (IGRF-14) model. In the online navigation stage, Q-table-based heading suggestions are fused with local trial candidates to form hybrid decisions that minimize normalized geomagnetic costs, while pure greedy descent is automatically activated for untrained states. In 50 paired Monte Carlo trials, RL-GD reduces the mean number of iterations from 3572 (EAS) to 1949 (a 45.4% reduction), lowers the path ratio from 2.15 to 1.16, and decreases the terminal positioning error from 0.078% to 0.037% of the straight-line distance. Ablation tests showed that removing greedy descent reduced success from 100% to 0% across all 50 tasks, while the Q-table prior reduced iterations by 17.3%. Under measurement noise of 2.5–10 nT, RL-GD maintained a 100% success rate, whereas EAS decreased from 100% (≤5 nT) to 28% (10 nT).

Förderung

  • Natural Science Basic Research Program of Shaanxi — General Program — Youth Project

Zitieren

APA

Guo, J., Yang, B., Ji, X., Liu, J., Yang, M., Wang, H., & Li, Y. (2026). A Bio-Inspired Geomagnetic Navigation Method Based on Hybrid Reinforcement Learning and Greedy Descent. Geomatics, 6(6), 147. https://doi.org/10.3390/geomatics6060147

Vancouver

Guo J, Yang B, Ji X, Liu J, Yang M, Wang H, et al. A Bio-Inspired Geomagnetic Navigation Method Based on Hybrid Reinforcement Learning and Greedy Descent. Geomatics. 2026;6(6):147. doi:10.3390/geomatics6060147

BibTeX
@article{Guo2026,
  author = {Guo, Jiaojiao and Yang, Binfeng and Ji, Xiaolin and Liu, Jiazheng and Yang, Min and Wang, Hanbing and Li, Yukun},
  title = {A Bio-Inspired Geomagnetic Navigation Method Based on Hybrid Reinforcement Learning and Greedy Descent},
  journal = {Geomatics},
  year = {2026},
  volume = {6},
  number = {6},
  pages = {147},
  doi = {10.3390/geomatics6060147}
}
Kostenlos starten →