EUVIMEDEUVIMED entdecken
Crossref

End-to-End Autonomous Navigation: A Deep Unfolding and Reinforcement Learning-Based Approach

Xudong Wang, Guanghui Wen, Han Shen

IEEE Transactions on Industrial Electronics · 2026-09 · 73 (9) · 13776-13787

DOI: 10.1109/tie.2026.3679837 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Industrial Electronics, 2026-09. Verfasst von Xudong Wang und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic Research Program of Jiangsu, Key Research and Development Program of Zhejiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autonomous navigation demands the ability to operate in unknown and unstructured environments using only onboard, limited-range sensor data, without reliance on prior maps or global information. To address this challenge, this article introduces a novel end-to-end navigation framework composed of perception and planning modules. By adopting a modular end-to-end paradigm, the framework avoids the compounding errors inherent in traditional, decoupled pipelines. The perception component, Perception Net, is an interpretable deep unfolding network that efficiently processes raw point clouds into a compact feature representation of arbitrary obstacles, exhibiting significant advantages in both efficiency and accuracy. The planning component is a reinforcement learning planner featuring a velocity-adaptive Bézier action space, which learns a smooth and kinematically feasible navigation policy endowed with a forward-looking capability to handle nonconvex environments. The agent’s decisions are based solely on its own state, goal coordinates, and real-time perception features. Extensive simulations demonstrate the framework’s high success rate and robust generalization to complex scenarios. The effectiveness of this end-to-end framework is further validated through real-world field tests on an autonomous surface vehicle platform, demonstrating its capability to operate as a map-less and forward-looking system for autonomous navigation in complex environments.

Förderung

  • National Natural Science Foundation of China
  • Basic Research Program of Jiangsu
  • Key Research and Development Program of Zhejiang Province
  • Jiangsu Provincial Scientific Research Center of Applied Mathematics

Zitieren

APA

Wang, X., Wen, G., & Shen, H. (2026). End-to-End Autonomous Navigation: A Deep Unfolding and Reinforcement Learning-Based Approach. IEEE Transactions on Industrial Electronics, 73(9), 13776-13787. https://doi.org/10.1109/tie.2026.3679837

Vancouver

Wang X, Wen G, Shen H. End-to-End Autonomous Navigation: A Deep Unfolding and Reinforcement Learning-Based Approach. IEEE Transactions on Industrial Electronics. 2026;73(9):13776-13787. doi:10.1109/tie.2026.3679837

BibTeX
@article{Wang2026,
  author = {Wang, Xudong and Wen, Guanghui and Shen, Han},
  title = {End-to-End Autonomous Navigation: A Deep Unfolding and Reinforcement Learning-Based Approach},
  journal = {IEEE Transactions on Industrial Electronics},
  year = {2026},
  volume = {73},
  number = {9},
  pages = {13776--13787},
  doi = {10.1109/tie.2026.3679837}
}
Kostenlos starten →