Research on Visual Positioning of a Roadheader and Construction of an Environment Map

The autonomous positioning of tunneling equipment is the key to intellectualization and robotization a face. In this paper, method based on simultaneous localization mapping (SLAM) estimate body pose roadheader build navigation map roadway presented. terms estimation, an RGB-D camera used collect images, calculation model established random sample consensus (RANSAC) iterative closest point (ICP); constructing graph optimization with closed-loop constraints. An equation Levenberg–Marquadt derived, which can achieve optimal estimation pose. mapping, LiDAR experimentally construct grid open-source algorithms, such as Gmapping, Cartographer, Karto, Hector. A cloud map, octree compound are constructed library RTAB-MAP. By setting parameters, expansion radius obstacle updating frequency cost for established. Combined Dijskra timed-elastic-band, simulation experiments show that combination support global path planning local avoidance.