Route planning method, device and equipment and storage medium

Abstract

The invention discloses a route planning method and device, equipment and a storage medium. The method comprises the following steps: acquiring environmental information of substation workers and spatial information of a substation; determining a target state of the substation worker according to the environment information of the substation worker and the spatial information of the substation; inputting the target state into a target deep recurrent neural network model to obtain walking direction information of the substation worker, wherein the target deep recurrent neural network model is obtained by iteratively training a first to-be-trained deep recurrent neural network model and a second to-be-trained deep recurrent neural network model through a training sample set, the training sample set comprises a first state sample, a first action corresponding to the first state sample, a return value of the first action, a second state sample, a second action corresponding to the second state sample and a return value of the second action, and the second state sample is a next state sample after the first action is executed.

Description

technical field [0001] Embodiments of the present invention relate to the field of communication technologies, and in particular, to a route planning method, device, equipment, and storage medium. Background technique [0002] A substation refers to a place in a power system that transforms voltage and current, receives and distributes power, and its operating status is closely related to the normal operation of the power system. Therefore, the safe operation of the staff in the substation and the fast and efficient avoidance of dangerous areas to the work place are of great significance to the stable and efficient operation of the power system. Due to the particularity of the working environment of the substation, the working area inside the substation has different permissions for different types of workers, and the restricted area will change due to the occurrence of different situations. Many restrictions. Therefore, how the substation staff can quickly plan the optima...

AI Technical Summary

Problems solved by technology

The advantage of the particle swarm optimization algorithm is that the algorithm is simple, easy to implement through computer language, has good robustness, and is not very sensitive to the size of the population, and can quickly converge to the solution, but the disadvantage is that it is easy to fall into a local optimal solution

[0004] However, the above mainstream methods have the following obvious defects: (1) In the artificial potential field method, when the object is far away from the target point, the gravitational force will become particularly large, and the relatively small repulsive force can even be ignored. There may be obstacles on the path of the object; when there are obstacles near the target point, the repulsive force will be very large, and the gravitational force will be relatively small, making it difficult for the object to reach the target point; If it is reversed, the object will easily fall into a local optimal solution or oscillate

If the grid is small, the environmental information represented by the grid map will be very clear, but due to the need to store more information, the storage overhead will increase, and the interference signal will increase accordingly, and the planning speed will decrease accordingly. Real-time performance cannot be guaranteed; on the contrary, due to the small amount of information storage, the anti-interference ability has been enhanced, and the planning speed has increased accordingly, but the division of environmental information will become more blurred, which is not conducive to the planning of effective paths

(3) Ant colony algorithm has slow convergence speed and is easy to fall into local optimum

The ant colony algorithm generally requires a long search time, and its complexity can reflect this; moreover, the method is prone to stagnation, that is, after the search reaches a certain level, the solutions found by all individuals are exactly the same, and the solution space cannot be further searched , which is not conducive to finding a better solution

(4) The main problems of the PSO algorithm are that it is prone to premature convergence (especially in dealing with complex multi-peak search problems), poor local optimization ability, etc.

Images