Method and system for vehicle route planning

Abstract

The invention belongs to the technical field of vehicle path planning, and discloses a vehicle path planning method and system. By initializing N random paths as antibodies and putting them into antibody candidate sets, the distance of each vehicle path is calculated as the distance between each antibody and the antigen. Affinity, initialize and mark each antibody; select the top n antibodies with the highest affinity, perform a cloning operation on each antibody, and update the label at the same time; re-label the mutated antibody; recalculate the affinity of the mutated antibody, and select a For the N antibodies with the highest affinity between antigens, update the antibody labeling of the antibodies in the antibody candidate set; when the antibody meets the antibody forgetting threshold, forget; when the number of evaluation function calls is satisfied, the calculation is terminated, and the optimal vehicle route is obtained. The invention carries out population marking and updating on the antibodies in the antibody concentration through the replacement process, so as to achieve the effect of improving the convergence speed and convergence stability of the algorithm.

Description

technical field [0001] The invention belongs to the technical field of vehicle route planning, and in particular relates to a vehicle route planning method and system. Background technique [0002] At present, the clonal selection algorithm is a new type of intelligent optimization algorithm inspired by the clonal selection principle of the biological immune system; Ag (antigen) antigen: the present invention specifically refers to the vehicle route planning problem requirements; Ab (antibody) antibody: the present invention specifically refers to The sorting sequence of each city route; Forgetting mechanism: Forgetting is a phenomenon of information loss. In a specific environment, the loss of information is meaningful. [0003] The vehicle routing problem (Vehicle Routing Problem, VRP) was first proposed by Dantzig and Ramser in 1959. It refers to a certain number of customers, each of whom has a different quantity of goods demand. The distribution center provides goods to...

AI Technical Summary

Problems solved by technology

[0005] 1. Simulated annealing algorithm: slow convergence speed, long execution time, and large parameter dependence;

[0006] 2. Genetic Algorithm: It is easy to fall into local prematurity, poor convergence performance, and the solution is reduced from continuous problems to combination problems, which greatly affects the accuracy;

[0007] 3. Clone selection algorithm: belongs to the evolutionary algorithm cluster, the convergence speed is too fast, and it is easy to fall into local optimum; there are two problems in the clone selection algorithm in solving the vehicle route planning problem: first, the existence of intermediate antibodies that cannot be eliminated in time affects the efficiency of the algorithm, Second, there is a problem of insufficient competitiveness of newly generated antibodies when ensuring the diversity of antibodies

[0008] 4. Ant colony algorithm: the calculation overhead is too large, and the solution efficiency is not high

[0010] Existing vehicle path planning methods have inaccurate results, low precision, low efficiency and long time-consuming

For example, when simulated annealing is used as the core algorithm to solve the vehicle planning route in the logistics vehicle route planning system, due to the slow convergence speed of this method, the user needs to wait for a long time to get the solution, which is not user-friendly and the system efficiency is low

Another example is when the genetic algorithm or the original clone selection algorithm is used as the core algorithm of the logistics vehicle route planning system, because this type of method is prone to local prematurity, the result is often not the optimal path, resulting in a lot of manpower and material resources in the actual logistics distribution. , reducing the efficiency of logistics distribution

Images