The invention discloses a universal gravitation search-based unmanned plane air route planning method, which comprises the following eight steps: 1, establishing an unmanned plane air route planning mathematical model; 2, setting initialization improved universal gravitation search algorithm parameters and battlefield environmental parameters; 3, randomly initializing N routes and initial positions and accelerated speeds of various particles, and establishing a rotating coordinate system; 4, calculating threat cost of each route according to threat information and the mathematical model; 5, updating inertial mass Mi(t) of the particles according to a weight-based rule; 6, calculating the sum of accelerated speeds of each particle in all directions according to a universal gravitation standard, and updating the speeds of the particles according to a group information speed updating rule; 7, updating the position of each particles according to the updated speed of each particle and the choice of survival of the fittest; and 8, if the number of iterations is greater than the maximum number of iterations, exiting a circulation, otherwise, returning to the step 4 for next iteration. The obtained optimal air route coordinate is subjected to coordinate inverse transformation and a result is output.