GPS-less indoor construction location sensing

Abstract

Abstract Location aware computing in construction is an emerging area where the location of materials, workforce, and equipment can be used to derive knowledge about the state of the project. This paper aims to provide a low-cost location sensing solution for indoor construction and underground facilities, where satellite navigation systems cannot be used. In this solution a set of low-cost passive Radio Frequency Identification (RFID) tags is deployed using a predefined topology to provide a good spatial coverage of the project-active area. The locations are estimated and represented by zones and coordinates. The zone detection approach uses K-Nearest Neighbor classification method to assign a zone to the target. The coordinates of the target's location are also acquired by weighted average method using the Received Signal Strength Indicator (RSSI) as weight. The approach has been experimented on a construction project in Montreal as well as in a controlled lab environment. The experimental results show an average of 0.17 as error rate for detecting the target's zone and an average of 1.3 m accuracy in detecting the coordinates. The promising results presented in this paper demonstrate the potential for a high-accuracy and low-lost location estimation method for indoor construction job sites.