Multiagent-based warehouse inventory system (WareDrone)

Due to the exponential growth of ecommerce, the need for automated Inventory management is crucial to have, among others, up-to-date information. There have been recent developments in using drones equipped with RGB cameras for scanning and counting inventories in warehouse. Due to their unlimited reach, agility and speed, drones can speed up the inventory process and keep it actual.
To benefit from this drone technology, warehouse owners and inventory service providers are actively exploring ways for maximizing the utilization of this technology through extending its capability in long-term autonomy, collaboration and operation in night and weekends. This feasibility study is aimed at investigating the possibility of developing a robust, reliable and resilient group of aerial robots with long-term autonomy as part of effectively automating warehouse inventory system to have competitive advantage in highly dynamic and competitive market. To that end, the main research question is,
“Which technologies need to be further developed to enable collaborative drones with long-term autonomy to conduct warehouse inventory at night and in the weekends?”
This research focusses on user requirement analysis, complete system architecting including functional decomposition, concept development, technology selection, proof-of-concept demonstrator development and compiling a follow-up projects.

Eindrapportage

Wat zijn de uitkomsten van het project: verslag Jurre.
The project developed drones with certain requirments to fly indoor without GPS. The results are utilized to expand the consortium and plan a larger project to address additional critical aspects, aiming to create a comprehensive framework for navigations using sensors and image detection. This project contributed to strengthening the Netherlands' position as a strong knowledge economy, given the global trend and market potential of drones. The challenges were recognized as:
 GPS-Denied Area.
 Tight Space for Navigation.
 Low Cost System
The algorithm used fiducial markers (ArUco) for vision-based precision landing, combining an image filter and a Kalman filter to improve marker recognition under challenging conditions. We tested several algorithms and methods to navigate within the closed environment. A UAV-mounted camera detected markers and calculated landing guidance commands. Relative position and orientation data were used to compute velocity commands, with alignment achieved through proportional control gains. The Kalman filter smoothed position and orientation data, ensuring robust data continuity even with partial marker occlusion. Based on the conducted study it was understood that following topics needs to be further developed:
- Mobile station.
-Localization sensors.
-Drone image Detection.
-Inventory Scanning uisng Lidar.

Vervolg project:
The follow-up project are in preparation for incorporating the Active Dock station where Lidar on mobile dock station will be autonomously employed for multiple applications.