row1
Abstract
Construction materials account for a significant percentage of the resources on a construction site and plays a vital role in the success of the project. By utilizing an experimental methodology, the goal of this research was to execute a proof of concept for autonomous inventory management of construction materials using Ultra-High Frequency passive RFID and a terrestrial autonomous robot. An experiment was administered to identify the reliability (tags read vs. tags placed) of the proposed system in a dynamic environment in autonomous mode. According to the results, the robot was largely able to navigate around and between smaller objects versus larger obstacles. Using Bootstrap simulation, the successful read rate (percent) was found to be [67,88] [LL, UL] at a 95 percent confidence interval. Based on the results, using a Boston Dynamics SPOT with UHF Passive RFID to control building material inventories could be a viable route with additional research. Future research will improve material management through RFID, computer vision, and Bayes Filters for localization.
Summary
Autonomous tracking is the next logical step in inventory management, but how can automatic solutions deal with rough terrain and changing worksites? Enter Mac, a combination of Boston Dynamics’ Spot and the RFID inventory tracking system Okapi. This collaboration between Auburn University’s College of Building Sciences and the RFID Lab has produced a robust system which utilizes Spot’s ability to traverse rough areas and Okapi's ability to take inventory at the same time, with minimal manual intervention.
Spot can be controlled manually or be given a set path to walk. On its routines, it uses Okapi, which consists of an RFID scanner and two depth cameras. It builds a map of its surroundings, reads all RFID tags in the area, and shows the position of all RFID tags within the map. The tags are represented with red dots. This kind of system is perfect for construction sites, especially for tool tracking.
