The invention relates to an unmanned aerial vehicle searching method for an underground multi-
branch cave. The method comprises the steps that the current state configuration of an unmanned aerial vehicle is acquired, and the current
configuration space of the unmanned aerial vehicle is acquired through a
laser radar sensor; sampling is carried out in the
configuration space by using a path sampling
algorithm to obtain a plurality of paths of the unmanned aerial vehicle in the
configuration space, and a collision-free path are reserved; the future safety of each path is calculated according to the state configuration and configuration space of the unmanned aerial vehicle at the path end point, and the future
safe path is reserved; the exploration income of each path is calculated, and the unmanned aerial vehicle executes the path with the maximum exploration income. Compared with the prior art, the method has the advantages that a plurality of paths are firstly acquired, the collision-free path and the future
safe path are reserved in combination with obstacle information of the configuration space, and then the path with the highest income is selected, so that autonomous exploration of the unmanned aerial vehicle in an unknown multi-
branch tunnel environment can be realized at a relatively high speed, and the unmanned aerial vehicle with limited cruising ability can carry out exploration in a larger range and a farther path.