RSSI-Based Distance Triangulation Using A Low-Cost Transceiver: Towards Robust Localization in Agrorobotics

Radio-based tracking systems are highly desired in various asset tracking and autonomous systems. The goal of this research report is to evaluate and validate the regression models that are implemented. Smartphone and ESP32 embedded system devices are used to capture the Received Signal Strength Indicator (RSSI), or radio signal strength, and subsequently use it for regression to acquire the distance. The objective of the research is to evaluate the suitability of such devices for distance triangulation. Results indicate a high correlation when used in the short range (10-20 m). The dataset is sampled using several intervals and ranges at two separate locations, i.e., green field and pavement, in view of possible multipath propagation. Results indicate that there does not seem to be multipath propagation despite the sampling of RSSI at the pavement. The R2 of about 0.9 is acquired when range of 1-10 meters is considered. This implies that almost 90% of variance can be explained by the RSSI variation. This research validates some of the findings by other researchers.