Unlock instant, AI-driven research and patent intelligence for your innovation.

Large-scale public place people flow guiding path planning method based on differential evolution algorithm

A differential evolution algorithm and technology in public places, applied in computing models, computing, artificial life, etc., to achieve the effect of reducing path intersections, taking into account safety and efficiency, and overcoming the singleness of evaluation criteria

Active Publication Date: 2021-06-01
CHINA-SINGAPORE INT JOINT RES INST
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The path planning method proposed by the present invention uses differential evolution algorithm combined with multi-objective optimization technology to solve the path planning problem, effectively overcomes the shortage of single evaluation criteria in prior art optimization, reduces path crossing, takes into account safety and efficiency, and improves practicality

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Large-scale public place people flow guiding path planning method based on differential evolution algorithm
  • Large-scale public place people flow guiding path planning method based on differential evolution algorithm
  • Large-scale public place people flow guiding path planning method based on differential evolution algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0047] For a large-scale public scene, suppose there are M different paths that need to be planned. M depends on how many main flow directions the flow of people has. Group exits and entrances. There is a path between each group of entrances and each group of exits. Where you are and the exit you want to reach, determine the route guidance you want to follow. Due to the grouping operation, a path may correspond to multiple entrances and exits, and each planned path includes the selection of the exit and the route in the middle. Our goal is to effectively guide the crowd to reach the destination quickly while minimizing the intersection of crowds on different routes in the scene to improve safety. Therefore, efficiency and safety are the multi-objective differential evolution algorithms used in this invention The two objectives in correspond to two objective function values, that is, fitness. The objective function value is calculated as follows:

[0048] f 1 =∑H(C)

[0049...

specific Embodiment approach

[0062] S1. Execute the initialization operation:

[0063] According to the walkable area in the scene, a population Q of size N is randomly generated. During the generation process, if the current point is found not in the walkable area, the point is regenerated until it falls into the walkable area. Make sure that every keypoint on the planned path falls within a walkable area of ​​the scene. For the scene of Tiyu Xilu subway station, the population size N is set to 30. The target vector is constructed for each population individual by the encoding method of the correlation between the front and back genes, and the target vector contains the route information and the end point information. Subsequently, the objective function value of the population individual objective vector is calculated by using the method for calculating the objective function value described above. The target vector is encoded as an M×(D+1)-dimensional real number vector as follows:

[0064] P i，k =...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a large-scale public place people flow guiding path planning method based on a differential evolution algorithm. According to the method, a path planning problem is represented as a continuous optimization problem, a differential evolution algorithm is combined with a multi-objective optimization technology to solve a people flow guiding path planning problem in a large public place, a path scheme is encoded into a group of gene sequences which are related and interconnected front and back, and in the differential evolution process, fitness evaluation is performed on a path scheme based on a crowd behavior simulation result, a population is guided to perform individual selection, security and efficiency are taken as two targets of multi-target selection operation, population individual selection is performed by applying a classic NSGA-II algorithm, and the obtained path scheme has relatively good security, can guide crowds to efficiently pass through a scene, the defect that in the prior art, the evaluation criterion is too single during optimization is effectively overcome, path crossing is reduced, and safety and efficiency are both considered.

Description

technical field [0001] The invention relates to the technical field of route planning and intelligent computing, in particular to a method for guiding route planning of people flow in large public places based on differential evolution algorithm. Background technique [0002] The problem of guiding the flow of people in large public places is an important issue of public safety. It requires road signs or route instructions to be provided in a given scenario, so that pedestrians can reach their destinations quickly and safely, while avoiding congestion caused by intersections between different routes as much as possible. [0003] Path planning methods mainly include global path planning based on scene information and local path planning based on real-time information. Traditional path planning methods include Dijkstra algorithm and A* algorithm, etc. In recent years, bionic methods have also been applied to path planning, such as ant colony algorithm, genetic algorithm, etc....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06F30/27G06N3/00G06F111/06
CPCG06Q10/047G06F30/27G06N3/006G06F2111/06
Inventor 钟竞辉李东芮蔡文桐
Owner CHINA-SINGAPORE INT JOINT RES INST