Artificial intelligence space people flow evacuation path planning method

Abstract

The invention discloses an artificial intelligence space people flow evacuation path planning method. The method comprises the steps of determining a space region, collecting space people flow data, establishing a path planning model, outputting an optimal evacuation path scheme and performing safety supervision. The invention belongs to the technical field of path planning, and particularly relates to an artificial intelligence space people flow evacuation path planning method. According to the scheme, a path traffic capacity model based on crowd density is adopted, and correction of the crowd density on traffic capacity is considered; the multi-target path fusion control model comprehensively balances safety, time and capacity factors to obtain a path comprehensive score, then the optimal evacuation direction trend is determined through dynamic path gradient field calculation, and a decision threshold is obtained through a fuzzy decision control equation to adapt to complex conditions; and a data processing technology and a visualization technology are adopted to organize optimal path scheme data of the evacuation planning model, and evaluation indexes are calculated and visually displayed to provide people evacuation navigation guidance.

Description

Technical Field

[0001] This invention belongs to the field of path planning technology, specifically an artificial intelligence-based spatial pedestrian evacuation path planning method. Background Technology

[0002] Spatial crowd evacuation path planning is a technology that uses multimodal perception, dynamic modeling, and intelligent decision-making to achieve efficient and safe crowd guidance in complex environments. Its core is to generate evacuation path schemes adapted to dynamic scenarios by integrating real-time data, behavior prediction, and optimization algorithms. However, existing spatial crowd evacuation path planning methods suffer from technical problems such as low evacuation efficiency, low safety, increased risk of stampedes, obstruction of rescue personnel and equipment access, and social panic. Furthermore, inaccurate crowd evacuation path assessment leads to increased evacuation time, delays in reaching safe areas, and makes it difficult for commanders to effectively control the situation. Summary of the Invention

[0003] To address the aforementioned issues and overcome the shortcomings of existing technologies, this invention provides an artificial intelligence-based spatial pedestrian evacuation path planning method. Addressing the technical problems of low evacuation efficiency and safety, which increase the risk of stampedes, hinder the access of rescue personnel and equipment, and cause social panic, this method employs a path capacity model based on crowd density to consider the impact of crowd density on capacity. A multi-objective path fusion control model comprehensively weighs safety, time, and capacity factors to obtain a comprehensive path score. Dynamic path gradient field calculations determine the optimal evacuation direction trend. Fuzzy decision control equations are used to derive decision thresholds to adapt to complex situations. Finally, an adaptive path optimization model adaptively adjusts the evacuation path based on zoning conditions and decision thresholds. Furthermore, to address the technical problem of inaccurate pedestrian evacuation path assessment, which increases evacuation time, delays reaching safe areas, and makes it difficult for commanders to effectively control the situation, this invention uses data processing and visualization technologies to organize the optimal path scheme data from the evacuation planning model, calculate evaluation indicators, and visualize the data to provide pedestrian evacuation navigation guidance.

[0004] The technical solution adopted by this invention is as follows: The spatial pedestrian evacuation path planning method provided by this invention includes the following steps:

[0005] Step S1: Determine the spatial area, classify the spatial types, and analyze the spatial layout;

[0006] Step S2: Collect spatial pedestrian flow data, and perform pedestrian quantity statistics and pedestrian flow characteristic collection;

[0007] Step S3: Establish a path planning model, set the optimal distribution of pedestrian route planning constraint parameters, establish a pedestrian route distribution fusion control model, obtain the best pedestrian evacuation route, calculate the gradient function of the shortest pedestrian evacuation route planning, and use adaptive path optimization to analyze route parameters to ensure safe pedestrian evacuation.

[0008] Step S4: Output the optimal evacuation route plan. Use data processing and visualization techniques to organize the optimal route plan data of the evacuation planning model, calculate evaluation indicators and visualize them to provide guidance for pedestrian evacuation.

[0009] Step S5: Safety supervision. During the evacuation of people, cameras are used to monitor the evacuation status in real time.

[0010] Further, in step S1, determining the spatial region includes the following steps:

[0011] Step S11: Space type classification. First, it is necessary to clarify whether the space is an indoor space or an outdoor space. Different types of spaces have different structures and characteristics. Indoor spaces have more passage restrictions and a limited number of entrances and exits, while outdoor spaces will face a larger area of ​​crowd dispersion and more interference factors.

[0012] Step S12: Spatial layout analysis, determine the layout of fixed facilities in the space, such as the location of buildings, obstacles, passages, and stairs. These fixed facilities are important reference elements for the evacuation of people. Their location and interrelationship will directly affect the planning of evacuation routes. Mark special areas, including danger areas and service areas. Danger areas are places that people need to avoid, and service areas are temporary gathering points and auxiliary points during the evacuation process.

[0013] Further, in step S2, the collection of spatial pedestrian flow data includes the following steps:

[0014] Step S21: People flow statistics. The access control system and camera intelligent recognition technology are used to obtain the number of people entering and leaving the space, so as to calculate the total number of people in the space in real time.

[0015] Step S22: Collect pedestrian flow characteristics. The demographic characteristics of pedestrian flow, such as age and gender distribution, have a certain impact on evacuation route planning. The elderly and children move more slowly and require safer and more convenient evacuation routes.

[0016] The behavioral characteristics of crowds, including their tendency to gather, their walking speed distribution, and their familiarity with the space, also influence evacuation decisions.

[0017] Further, in step S3, establishing the path planning model includes the following steps:

[0018] Step S31: Establish a path capacity model based on population density, using the following formula:

[0019] ;

[0020] In the formula, Here, Q is the path capacity correction coefficient at time t, and Q is the base capacity. Indicates the target evacuation time. Indicates the baseline evacuation time. This represents the real-time crowd density at location (x, y). Indicates the maximum permissible flow rate;

[0021] Step S32: Multi-objective path fusion control model, constructing an index function to comprehensively evaluate the quality of paths, using the following formula:

[0022] ;

[0023] In the formula, The overall score represents the path. Represents the safety force vector. and This represents the time and capacity weighting coefficient, where t represents the evacuation time already used.

[0024] Step S33: Calculate the dynamic path gradient field, calculating the path selection gradient value at each point in space. The formula used is as follows:

[0025] ;

[0026] In the formula, This represents the path gradient at position (x, y). This represents the normalized distance to the nearest exit. This represents the minimum path score for the current region;

[0027] Step S34: Establish the fuzzy decision control equation and the dynamic decision threshold for path selection. The formula used is as follows:

[0028] ;

[0029] In the formula, Indicates the path decision threshold. This represents the weight of the k-th influence factor. This represents the normalized value of the k-th environmental parameter. Indicates the standard deviation of population density. Indicates the system robustness adjustment parameters;

[0030] Step S35: Adaptive path optimization, generating final path adjustment parameters, using the following formula:

[0031] ;

[0032] In the formula, Indicates path adjustment parameters. This represents the average velocity vector of the nth partition. Represents the partition normal vector. This represents the vector from the partition center to the exit, and N represents the total number of spatial partitions.

[0033] Further, in step S4, the output of the optimal evacuation route scheme includes the following steps:

[0034] Step S41: Organize the data, including the optimal route plan data calculated by the evacuation planning model, including the starting point, ending point, route nodes and route length information, to obtain the optimal route plan;

[0035] Step S42: Calculate the path evaluation index to quantitatively evaluate the optimal path. The formula used is as follows:

[0036] ;

[0037] In the formula, This indicates the sum of Euclidean distances. This represents the total time taken, i.e., the actual evacuation time. This represents the safety margin, a key indicator used to quantify the safety risks of evacuation routes. This represents the congestion threshold, and m represents the number of nodes in the path. Indicates the traffic capacity along the route. Indicates the time when the path begins to be entered. Indicates the time of arrival at the destination;

[0038] Step S43: Visualization. The optimal evacuation route plan is displayed through maps and charts, generating a detailed report on the optimal evacuation route plan, including route overview, explanation of optimization parameters, route diagram and efficiency evaluation, providing clear navigation guidance for the evacuation of people and ensuring personal safety.

[0039] Furthermore, in step S5, the safety supervision specifically involves using cameras installed in the space to observe the evacuation of people in real time during the evacuation process, focusing on whether the people are evacuating along the planned optimal path and whether there is local congestion or deviation from the safe route.

[0040] The beneficial results achieved by the present invention using the above solution are as follows:

[0041] (1) To address the technical problems of low evacuation efficiency and low safety, which leads to increased risk of stampedes, hinders the entry of rescue personnel and equipment, and causes social panic, a path capacity model based on crowd density is adopted to consider the correction of the capacity by crowd density. The multi-objective path fusion control model comprehensively weighs safety, time and capacity factors to obtain a comprehensive path score. The optimal evacuation direction trend is determined by dynamic path gradient field calculation. The decision threshold is obtained through fuzzy decision control equation to adapt to complex situations. Finally, the adaptive path optimization model adaptively adjusts the evacuation path according to the zoning situation and decision threshold.

[0042] (2) In response to the technical problems that the inaccurate assessment of the evacuation route leads to increased evacuation time and delays in reaching the safe area, and that the inaccurate route assessment makes it difficult for the commanders to effectively control the situation, data processing and visualization technologies are used to organize the optimal route scheme data of the evacuation planning model, calculate the evaluation indicators and visualize them to provide guidance for the evacuation of people. Attached Figure Description

[0043] Figure 1 A flowchart illustrating the spatial pedestrian evacuation path planning method for artificial intelligence provided by the present invention;

[0044] Figure 2 This is a flowchart illustrating step S2;

[0045] Figure 3 This is a flowchart illustrating step S3;

[0046] Figure 4 This is a flowchart illustrating step S4.

[0047] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. Detailed Implementation

[0048] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0049] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0050] Example 1, see Figure 1 The present invention provides an artificial intelligence-based spatial pedestrian evacuation path planning method, which includes the following steps:

[0051] Step S1: Determine the spatial area, classify the spatial types, and analyze the spatial layout;

[0052] Step S2: Collect spatial pedestrian flow data, and perform pedestrian quantity statistics and pedestrian flow characteristic collection;

[0053] Step S3: Establish a path planning model, set the optimal distribution of pedestrian route planning constraint parameters, establish a pedestrian route distribution fusion control model, obtain the best pedestrian evacuation route, calculate the gradient function of the shortest pedestrian evacuation route planning, and use adaptive path optimization to analyze route parameters to ensure safe pedestrian evacuation.

[0054] Step S4: Output the optimal evacuation route plan. Use data processing and visualization techniques to organize the optimal route plan data of the evacuation planning model, calculate evaluation indicators and visualize them to provide guidance for pedestrian evacuation.

[0055] Step S5: Safety supervision. During the evacuation of people, cameras are used to monitor the evacuation status in real time.

[0056] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, determining the spatial region includes the following steps:

[0057] Step S11: Space type classification. First, it is necessary to clarify whether the space is an indoor space or an outdoor space. Different types of spaces have different structures and characteristics. Indoor spaces have more passage restrictions and a limited number of entrances and exits, while outdoor spaces will face a larger area of ​​crowd dispersion and more interference factors.

[0058] Step S12: Spatial layout analysis, determine the layout of fixed facilities in the space, such as the location of buildings, obstacles, passages, and stairs. These fixed facilities are important reference elements for the evacuation of people. Their location and interrelationship will directly affect the planning of evacuation routes. Mark special areas, including danger areas and service areas. Danger areas are places that people need to avoid, and service areas are temporary gathering points and auxiliary points during the evacuation process.

[0059] Example 3, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S2, the collection of spatial pedestrian flow data includes the following steps:

[0060] Step S21: People flow statistics. The access control system and camera intelligent recognition technology are used to obtain the number of people entering and leaving the space, so as to calculate the total number of people in the space in real time.

[0061] Step S22: Collect pedestrian flow characteristics. The demographic characteristics of pedestrian flow, such as age and gender distribution, have a certain impact on evacuation route planning. The elderly and children move more slowly and require safer and more convenient evacuation routes.

[0062] The behavioral characteristics of crowds, including their tendency to gather, their walking speed distribution, and their familiarity with the space, also influence evacuation decisions.

[0063] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, establishing the path planning model includes the following steps:

[0064] Step S31: Establish a path capacity model based on population density, using the following formula:

[0065] ;

[0066] In the formula, Here, Q is the path capacity correction coefficient at time t, and Q is the base capacity. Indicates the target evacuation time. Indicates the baseline evacuation time. This represents the real-time crowd density at location (x, y). Indicates the maximum permissible flow rate;

[0067] Step S32: Multi-objective path fusion control model, constructing an index function to comprehensively evaluate the quality of paths, using the following formula:

[0068] ;

[0069] In the formula, The overall score represents the path. Represents the safety force vector. and This represents the time and capacity weighting coefficient, where t represents the evacuation time already used.

[0070] Step S33: Calculate the dynamic path gradient field, calculating the path selection gradient value at each point in space. The formula used is as follows:

[0071] ;

[0072] In the formula, This represents the path gradient at position (x, y). This represents the normalized distance to the nearest exit. This represents the minimum path score for the current region;

[0073] Step S34: Establish the fuzzy decision control equation and the dynamic decision threshold for path selection. The formula used is as follows:

[0074] ;

[0075] In the formula, Indicates the path decision threshold. This represents the weight of the k-th influence factor. This represents the normalized value of the k-th environmental parameter. Indicates the standard deviation of population density. Indicates the system robustness adjustment parameters;

[0076] Step S35: Adaptive path optimization, generating final path adjustment parameters, using the following formula:

[0077] ;

[0078] In the formula, Indicates path adjustment parameters. This represents the average velocity vector of the nth partition. Represents the partition normal vector. This represents the vector from the partition center to the exit, and N represents the total number of spatial partitions.

[0079] By performing the above operations, a path capacity model based on crowd density is adopted to consider the correction of capacity by crowd density. A multi-objective path fusion control model comprehensively weighs safety, time and capacity factors to obtain a comprehensive path score. Then, the optimal evacuation direction trend is determined by dynamic path gradient field calculation. A decision threshold is obtained through fuzzy decision control equations to adapt to complex situations. Finally, an adaptive path optimization model adaptively adjusts the evacuation path according to the zoning situation and decision threshold. This solves the technical problems of low evacuation efficiency and low safety, which leads to an increased risk of stampedes, hinders the entry of rescue personnel and equipment, and causes social panic.

[0080] Example 5, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S4, the output of the optimal evacuation route scheme includes the following steps:

[0081] Step S41: Organize the data, including the optimal route plan data calculated by the evacuation planning model, including the starting point, ending point, route nodes and route length information, to obtain the optimal route plan;

[0082] Step S42: Calculate the path evaluation index to quantitatively evaluate the optimal path. The formula used is as follows:

[0083] ;

[0084] In the formula, This indicates the sum of Euclidean distances. This represents the total time taken, i.e., the actual evacuation time. This represents the safety margin, a key indicator used to quantify the safety risks of evacuation routes. This represents the congestion threshold, and m represents the number of nodes in the path. Indicates the traffic capacity along the route. Indicates the time when the path begins to be entered. Indicates the time of arrival at the destination;

[0085] Step S43: Visualization. The optimal evacuation route plan is displayed through maps and charts, generating a detailed report on the optimal evacuation route plan, including route overview, explanation of optimization parameters, route diagram and efficiency evaluation, providing clear navigation guidance for the evacuation of people and ensuring personal safety.

[0086] By performing the above operations, data processing and visualization technologies are used to organize the optimal route data of the evacuation planning model, calculate evaluation indicators, and visualize them to provide guidance for the evacuation of people. This solves the technical problem that inaccurate evacuation route evaluation leads to increased evacuation time and delays in reaching the safe area. Furthermore, for evacuees, inaccurate route evaluation makes it difficult for commanders to effectively control the situation.

[0087] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S5, the safety supervision specifically involves using cameras installed in the space to observe the evacuation of people in real time during the evacuation process, focusing on whether the people are evacuating along the planned optimal path and whether there is local congestion or deviation from the safe route.

[0088] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0089] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

[0090] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A spatial pedestrian evacuation path planning method based on artificial intelligence, characterized by: The method includes the following steps: Step S1: Determine the spatial region; Step S2: Collect spatial pedestrian flow data; Step S3: Establish a path planning model, set the optimal distribution of pedestrian route planning constraint parameters, establish a pedestrian route distribution fusion control model, obtain the best pedestrian evacuation route, calculate the gradient function of the shortest pedestrian evacuation route planning, and use adaptive path optimization to perform route parameter analysis. Step S4: Output the optimal evacuation route plan. Use data processing and visualization techniques to organize the optimal route plan data of the evacuation planning model, calculate the evaluation index, and visualize the results. Step S5: Safety supervision.

2. The spatial pedestrian evacuation path planning method of artificial intelligence according to claim 1, characterized in that: In step S3, establishing the path planning model includes the following steps: Step S31: Establish a path capacity model based on population density; Step S32: Construct a multi-objective path fusion control model to evaluate the overall quality of the paths; Step S33: Calculate the dynamic path gradient field, and calculate the path selection gradient value at each point in space; Step S34: Establish the fuzzy decision control equation and the dynamic decision threshold for path selection; Step S35: Adaptive path optimization, generating final path adjustment parameters.

3. The artificial intelligence-based spatial pedestrian evacuation path planning method according to claim 1, characterized in that: In step S4, the output of the optimal evacuation route scheme includes the following steps: Step S41: Organize the data, organize the optimal route scheme data calculated by the evacuation planning model; Step S42: Calculate the path evaluation index to quantitatively evaluate the optimal path; Step S43: Visualization: Display the optimal evacuation route plan through maps and charts, and generate a detailed report on the optimal evacuation route plan.

4. The artificial intelligence-based spatial pedestrian evacuation path planning method according to claim 1, characterized in that: In step S1, determining the spatial region includes the following steps: Step S11: Space type classification. First, it is necessary to clarify whether the space is an indoor space or an outdoor space. Different types of spaces have different structures and characteristics. Step S12: Spatial layout analysis, determine the layout of fixed facilities in the space. The fixed facilities are important reference elements for the evacuation of people. Mark special areas. The special areas include dangerous areas and service areas. Dangerous areas are places that people need to avoid. Service areas are temporary gathering points and auxiliary points during the evacuation process.

5. The spatial pedestrian evacuation path planning method of artificial intelligence according to claim 1, characterized in that: In step S2, the collection of spatial pedestrian flow data includes the following steps: Step S21: Count the number of people. Use access control system and camera intelligent recognition technology to obtain the number of people entering and leaving the space, and calculate the total number of people in the space in real time. Step S22: Collect pedestrian characteristics. The age and gender distribution of pedestrians has an impact on evacuation route planning. The elderly and children move slowly and require safer and more convenient evacuation routes. The behavioral characteristics of people, including their tendency to gather, their walking speed distribution, and their familiarity with the space, also influence evacuation decisions.

6. The artificial intelligence-based spatial pedestrian evacuation path planning method according to claim 1, characterized in that: In step S5, the safety supervision specifically involves using cameras installed in the space to observe the evacuation of people in real time during the evacuation process.

Images