The invention provides a robot path planning method based on an improved genetic algorithm. The robot path planning method comprises the following steps: when an optimal path exists, a robot executes an inspection task according to the optimal path, or else, the task is executed according to an approximate optimal path. At the same time, the robot path planning method provided by the invention is used for calculating a shortest path between two random inspection points, then taking the shortest path as basic data of the genetic algorithm to calculate the optimal path for the robot to do the inspection task next time, and continuously iterating like this, so that the path planned by the robot is more and more intelligent, and the reliability and the navigation accuracy of the system are maximized; since the path planning adopts the specially optimized genetic algorithm, as time goes on, the number of robot inspection times is increased, the planned path may become more and more excellent.