Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Crowd evacuation simulation method and system based on deep reinforcement learning algorithm

A technology of reinforcement learning and simulation methods, applied in neural learning methods, design optimization/simulation, computing, etc., can solve the problems of high algorithm complexity, slow algorithm convergence speed, and algorithm difficulty in obtaining results, etc., to improve the convergence speed, The effect of optimizing the results and reducing the amount of calculation

Pending Publication Date: 2021-01-15
SHANDONG NORMAL UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The most typical one is the Multi-Agent Deep Deterministic Policy Gradient algorithm (Multi-Agent Deep Deterministic Policy Gradient), but due to the complexity of the algorithm is too high, the convergence speed of the algorithm is slow, and due to the complexity of the environment, the algorithm is difficult get a good result

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
  • Crowd evacuation simulation method and system based on deep reinforcement learning algorithm
  • Crowd evacuation simulation method and system based on deep reinforcement learning algorithm
  • Crowd evacuation simulation method and system based on deep reinforcement learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] In this embodiment, a crowd evacuation simulation method based on a deep reinforcement learning algorithm is disclosed, including:

[0045] Perform initial setting of parameters in the evacuation scene simulation model according to the scene information and crowd parameter information;

[0046] Group the crowd and divide the leaders within the group;

[0047] Each leader selects the best exit as the evacuation target, and uses the improved multi-agent depth deterministic strategy gradient algorithm for global path planning to obtain the optimal evacuation path;

[0048] Ordinary pedestrians in the group follow the movement of the leader in the group.

[0049] Further, each group of leaders is regarded as an agent, and the improved multi-agent deep deterministic policy gradient algorithm is used for global path planning, including:

[0050] Set the movable direction and current position of the agent;

[0051] Set the reward and return mechanism of the Critic network, an...

Embodiment 2

[0115] In this embodiment, a crowd evacuation simulation system based on a strategy-optimized deep reinforcement learning algorithm is disclosed, including:

[0116] The initialization setting module performs initialization setting of parameters in the evacuation scene simulation model according to the scene information and crowd parameter information;

[0117] The leader selection module in the group realizes the grouping of people and selects the leader in the group;

[0118] In the evacuation simulation module, each leader selects the best exit as the evacuation target, uses the improved multi-agent depth deterministic strategy gradient algorithm to perform global path planning, and obtains the optimal evacuation path. Ordinary pedestrians in the group follow the movement of the leader in the group .

Embodiment 3

[0120] An electronic device, comprising a memory, a processor, and computer instructions stored in the memory and run on the processor, when the computer instructions are run by the processor, the crowd evacuation simulation based on the deep reinforcement learning algorithm disclosed in Embodiment 1 is completed steps described in the method.

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 crowd evacuation simulation method and system based on a deep reinforcement learning algorithm, and the method comprises the steps: setting initialization of parameters in anevacuation scene simulation model according to scene information and crowd parameter information; grouping crowds, and dividing leaders in the groups; selecting an optimal exit as an evacuation target by each leader, and performing global path planning by utilizing an improved multi-agent depth deterministic strategy gradient algorithm to obtain an optimal evacuation path; wherein ordinary pedestrians in the group move along with the leaders in the group. A cross entropy method for optimizing a strategy and a data pruning algorithm for optimizing a sample are introduced on the basis of an original multi-agent depth deterministic strategy gradient algorithm, the result of the algorithm is optimized, the convergence speed of the algorithm is increased, crowds can be better guided to evacuate, and the evacuation efficiency is improved.

Description

technical field [0001] The present disclosure relates to a crowd evacuation simulation method and system based on a deep reinforcement learning algorithm. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] With the continuous improvement of the level of economic development, people's safety requirements for daily life are also increasing. Crowd evacuation in emergency situations has always been a topic that cannot be ignored. Because a small disturbance in the crowd will have a great impact on the rapid evacuation of the crowd, the safety hazard is relatively large. If the crowd cannot be effectively controlled, it will easily lead to crowd crowding and stampede incidents. For this reason, it is of great significance to simulate the real crowd evacuation situation, provide reasonable evacuation plan for pedestrians, formulate the best evac...

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): G06F30/27G06Q10/04G06Q50/26G06N3/04G06N3/08
CPCG06F30/27G06Q10/047G06Q50/265G06N3/084G06N3/045
Inventor 刘弘孟祥栋李信金赵缘
Owner SHANDONG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com