Underground location algorithm based on random forest and environmental factor compensation

Abstract

Abstract Aiming at the poor location accuracy caused by the harsh and complex underground environment, long strip roadway, limited wireless transmission and sparse anchor nodes, an underground location algorithm based on random forest and compensation for environmental factors was proposed. Firstly, the underground wireless access point (AP) network model and tunnel environment were analyzed, and the fingerprint location algorithm was built. And then the Received Signal Strength (RSS) was analyzed by Kalman Filter algorithm in the offline sampling and real-time positioning stage. Meanwhile, the target speed constraint condition was introduced to reduce the error caused by environmental factors. The experimental results show that the proposed algorithm solves the problem of insufficient location accuracy and large fluctuation affected by environment when the anchor nodes are sparse. At the same time, the average location accuracy reaches three meters, which can satisfy the application of underground rescue, activity track playback, disaster monitoring and positioning. It has high application value in complex underground environment.