A high-precision road network construction method based on deep learning for unmanned vehicles in openpit mines

Updating the openpit vehicle transportation network has the problem of being time consuming and low precision. To address this problem, a high-precision road network model construction method for unmanned vehicles in openpit mines is proposed. This method can be divided into two steps. In the first step, an improved deep learning image processing model named DeepLabv3+C (DeepLabv3+Concat) is presented, and the road information extracted by the DeepLabv3+C network is used to construct a three-dimensional model of the openpit mine road network. In the second step, aiming at the time-consuming problem of unmanned vehicles meeting in openpit mines, a vehicle meeting strategy is proposed. This strategy is used to guide the navigation of unmanned vehicles in openpit mines. At the end of the study, vehicle running simulation was carried out on the road network model using Unity, a 3D visualization simulation software. The high-precision unmanned road network model of openpit mines studied in this work can further promote the construction and development of smart mines by acting as a high-precision map for unmanned vehicles.