 In this paper, the authors propose a novel radio environment map, REM, update methodology based on clustering and machine learning for indoor coverage. The authors use real measurements collected by a Turtlebot 3 mobile robot to measure the received signal strength indicator, RSSI, as a measure of link quality between transmitter and receiver. They then use the historical dataset to determine the number of clusters via the K-means algorithm. The authors then divide the samples from the historical dataset into clusters, and they train one random forest, RF, model with the corresponding historical data from each cluster. When new data measurements are collected, these new samples are assigned to one cluster for a timely update of the RF model. Simulation results show that the proposed scheme outperforms other ML algorithms and a baseline scheme without clustering. This article was authored by Mario Arcamana, Carla E. Garcia, Taiwum Huang, and others. We are article.tv, links in the description below.