EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development of Unmanned Aerial Vehicle Navigation and Warehouse Inventory System Based on Reinforcement Learning

Huei-Yung Lin, Kai-Lun Chang, Hsin-Ying Huang

Drones · 28.05.2024 · 8 (6) · 220

DOI: 10.3390/drones8060220 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 28.05.2024. Verfasst von Huei-Yung Lin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology of Taiwan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we present the exploration of indoor positioning technologies for UAVs, as well as navigation techniques for path planning and obstacle avoidance. The objective was to perform warehouse inventory tasks, using a drone to search for barcodes or markers to identify objects. For the indoor positioning techniques, we employed visual-inertial odometry (VIO), ultra-wideband (UWB), AprilTag fiducial markers, and simultaneous localization and mapping (SLAM). These algorithms included global positioning, local positioning, and pre-mapping positioning, comparing the merits and drawbacks of various techniques and trajectories. For UAV navigation, we combined the SLAM-based RTAB-map indoor mapping and navigation path planning of the ROS for indoor environments. This system enabled precise drone positioning indoors and utilized global and local path planners to generate flight paths that avoided dynamic, static, unknown, and known obstacles, demonstrating high practicality and feasibility. To achieve warehouse inventory inspection, a reinforcement learning approach was proposed, recognizing markers by adjusting the UAV’s viewpoint. We addressed several of the main problems in inventory management, including efficiently planning of paths, while ensuring a certain detection rate. Two reinforcement learning techniques, AC (actor–critic) and PPO (proximal policy optimization), were implemented based on AprilTag identification. Testing was performed in both simulated and real-world environments, and the effectiveness of the proposed method was validated.

Förderung

  • Ministry of Science and Technology of Taiwan

Zitieren

APA

Lin, H., Chang, K., & Huang, H. (2024). Development of Unmanned Aerial Vehicle Navigation and Warehouse Inventory System Based on Reinforcement Learning. Drones, 8(6), 220. https://doi.org/10.3390/drones8060220

Vancouver

Lin H, Chang K, Huang H. Development of Unmanned Aerial Vehicle Navigation and Warehouse Inventory System Based on Reinforcement Learning. Drones. 2024;8(6):220. doi:10.3390/drones8060220

BibTeX
@article{Lin2024,
  author = {Lin, Huei-Yung and Chang, Kai-Lun and Huang, Hsin-Ying},
  title = {Development of Unmanned Aerial Vehicle Navigation and Warehouse Inventory System Based on Reinforcement Learning},
  journal = {Drones},
  year = {2024},
  volume = {8},
  number = {6},
  pages = {220},
  doi = {10.3390/drones8060220}
}
Kostenlos starten →