Method for searching a path by using a three-dimensional reconstructed map

A method for searching a path by using a three-dimensional reconstructed map comprising:

• using a point-cloud map-retrieving device to emit lidar signals to environment, detect distance data points according to the lidar signals, and combine the distance data points into three-dimensional point-cloud map information according to actual coordinates of the distance data points;
• using a processor to perform the following steps:
• receiving the three-dimensional point-cloud map information and three-dimensional material map information;
• clustering the three-dimensional point-cloud map information with a clustering algorithm to obtain clustering information, and identifying material attributes of objects in the three-dimensional point-cloud map information with a material neural network model to obtain material attribute information;
• retrieving coordinate information of the three-dimensional point-cloud map information and the three-dimensional material map information, and fusing the three-dimensional point-cloud map information and the three-dimensional material map information based on the coordinate information, thereby outputting fused map information;
• identifying obstacle areas and non-obstacle areas in the fused map information based on an obstacle neural network model, the clustering information, and the material attribute information;
• generating three-dimensional path information according to the non-obstacle areas, wherein the three-dimensional path information comprises path points connected with each other, and the path points keep a distance where an obstacle-avoidance circle is formed from the obstacle areas, the distance is used as the radius of the obstacle-avoidance circle;
• and
• inputting wind information and determining whether the wind information is greater than a wind-level threshold or determining whether a headwind occurs based on the wind information, wherein a wind sensor is coupled to the processor generating the wind information:
• if yes, decreasing the radius of the obstacle-avoidance circle and a position in a z axis of the three-dimensional path information to generate first three-dimensional path information, wherein the position is unmanned aerial vehicle's position in the z axis of the three-dimensional path information;
• and
• if no, increasing the radius of the obstacle-avoidance circle to generate second three-dimensional path information.