EUVIMEDEUVIMED entdecken
Crossref

Selective Densification for Rapid Motion Planning in High Dimensions With Narrow Passages

Lu Huang, Lingxiao Meng, Xingjian Jing, Jiankun Wang

IEEE Transactions on Automation Science and Engineering · 2025 · 22 · 21443-21455

DOI: 10.1109/tase.2025.3606845 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Automation Science and Engineering, 2025. Verfasst von Lu Huang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: Shenzhen-Hong Kong-Macao Scheme-C, Innovation and Technology Fund of Hong Kong, Booster Fund of City University of Hong Kong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sampling-based algorithms are widely used for motion planning in high-dimensional configuration spaces. However, due to low sampling efficiency, their performance often diminishes in complex configuration spaces with narrow corridors. Existing approaches address this issue using handcrafted or learned heuristics to guide sampling toward useful regions. Unfortunately, these strategies often lack generalizability to various problems or require extensive prior training. In this paper, we propose a simple yet efficient sampling-based planning framework along with its bidirectional version that overcomes these issues by integrating different levels of planning granularity. Our approach probes configuration spaces with uniform random samples at varying resolutions and explores these multi-resolution samples online with a bias towards sparse samples when traveling large free configuration spaces. By seamlessly transitioning between sparse and dense samples, our approach can navigate complex configuration spaces while maintaining planning speed and completeness. The simulation results demonstrate that our approach outperforms several state-of-the-art sampling-based planners in $\mathbb {SE}(2)$ , $\mathbb {SE}(3)$ , and $\mathbb {R}^{14}$ with challenging terrains. Furthermore, experiments conducted with the Franka Emika Panda robot operating in a constrained workspace provide additional evidence of the superiority of the proposed method. Note to Practitioners—Motion planning for robots with a high degree of freedom (DoF), such as humanoid robots and robotic arms, presents significant challenges due to the vast configuration space involved. Each joint adds a dimension, leading to an exponentially larger and more complex configuration space that is difficult to navigate. To address these challenges, sampling-based techniques are commonly employed. These methods sample points in the configuration space to construct a graph or tree of potential motion paths. However, their computational complexity increases dramatically with environmental complexity. Obstacles can create narrow passages in the configuration space, requiring a large number of samples to ensure the connectivity of the underlying graph or tree and, therefore, the existence of solutions. This paper proposes a novel sampling-based planner along with its bidirectional version that reduces search complexity by simultaneously exploring samples at various resolutions. The proposed planners efficiently find solutions in large free configuration spaces by utilizing sparse random samples. When navigating narrow passages, they transition to denser random samples to locate viable paths. By integrating samples of different resolutions, the proposed planners effectively navigate high-dimensional configuration spaces with narrow passages. Simulation results demonstrate that our approach outperforms several state-of-the-art sampling-based planners across various scenarios. The proposed planners, with their adaptability, can be easily implemented as a plug-and-play solution for diverse robotic systems, enabling them to perform autonomous navigation tasks in unstructured environments.

Förderung

  • Shenzhen-Hong Kong-Macao Scheme-C
  • Innovation and Technology Fund of Hong Kong
  • Booster Fund of City University of Hong Kong
  • CityU Internal Funds for External Grant Schemes
  • City University of Hong Kong
  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • High Level of Special Funds from Southern University of Science and Technology

Zitieren

APA

Huang, L., Meng, L., Jing, X., & Wang, J. (2025). Selective Densification for Rapid Motion Planning in High Dimensions With Narrow Passages. IEEE Transactions on Automation Science and Engineering, 22, 21443-21455. https://doi.org/10.1109/tase.2025.3606845

Vancouver

Huang L, Meng L, Jing X, Wang J. Selective Densification for Rapid Motion Planning in High Dimensions With Narrow Passages. IEEE Transactions on Automation Science and Engineering. 2025;22:21443-21455. doi:10.1109/tase.2025.3606845

BibTeX
@article{Huang2025,
  author = {Huang, Lu and Meng, Lingxiao and Jing, Xingjian and Wang, Jiankun},
  title = {Selective Densification for Rapid Motion Planning in High Dimensions With Narrow Passages},
  journal = {IEEE Transactions on Automation Science and Engineering},
  year = {2025},
  volume = {22},
  pages = {21443--21455},
  doi = {10.1109/tase.2025.3606845}
}
Kostenlos starten →