A multi-sensor high-precision fusion measurement method for occlusion evaluation environment

Abstract

The present invention discloses a multi-sensor high-precision fusion measurement method for an occlusion evaluation environment, which solves the reliable and continuous positioning of vehicles when GNSS signals are blocked by a multi-sensor fusion solution. Active features are arranged on the roadside to increase the observation amount of the laser radar, so as to improve the positioning accuracy of laser SLAM in the case of sparse point clouds; at the same time, UWB distance observation is introduced to identify the active feature number scanned by the laser radar, and the positioning frequency is improved by combining the vehicle-mounted inertial sensor; finally, the factor graph algorithm is used to accurately estimate the vehicle's position information in real time. It has the advantages of low cost, high precision and good real-time performance.

Images