John R. Spletzer, Sean Kelly, David Stolfo, Mooi Choo Chuah, Thomas Miller
This study develops a automated system applicable to inventory and asset management, a no human-in-loop system, a proof-of-concept demontration in a representative environment and Matlab RFID toolbox and proof-of-concept hardware tech specs.
We will merge radio-frequency identification (RFID) and mobile robotics technologies to develop an Automated Asset Locating System (AALS). Such a system will enhance inventory management by automatically updating on-hand inventory, and by locating misplaced assets in factories, warehouses, etc. – all without human interaction. For proof of concept validation, we will demonstrate a working AALS prototype that integrates computing, a LIDAR system, and RFID reader on a mobile robot base. This prototype will autonomously navigate in its environment while simultaneously locating tagged assets.
Failed to achieve 100% detection rates on the highest boxes. Average localization errors increased to >1 meter on the x-y plane. Conditional density functions helped asset mapping accuracy. Power stepping hurt asset mapping accuracy