Crowd evacuation path planning method considering panic diffusion

Abstract

The invention provides a crowd evacuation path planning method considering panic diffusion. The method comprises the following steps: determining an initial individual panic degree of each individual in a crowd of a target scene; adjacent individuals of each individual are determined, the initial individual panic degree of each individual is updated, and the individual panic degree of each individual under panic propagation is obtained; performing panic attenuation processing on the individual panic degree of each individual under panic propagation to obtain the final individual panic degree at the current moment; the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment is determined, and the final individual panic degree is obtained to update the final obstacle avoidance speed at the next moment; and determining a crowd evacuation planning path based on the final obstacle avoidance speed at each moment. According to the method, the crowd evacuation path planning is completed under the condition that the influence of the panic emotion of the crowd is considered, the authenticity of crowd evacuation path planning simulation is improved, and then the evacuation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of path planning, and in particular to a crowd evacuation path planning method taking into account the spread of panic. Background Art

[0002] The existing crowd evacuation path planning methods focus on improving evacuation efficiency, such as the classic RVO obstacle avoidance algorithm and particle swarm algorithm. They simulate obstacle avoidance trajectories, but due to the lack of consideration of the personalized movement of the crowd, the crowd evacuation effect is usually inconsistent with the actual situation. At the same time, the focus of crowd evacuation path planning is mostly on path planning, and it is often ignored that the object of evacuation is the crowd, thereby ignoring the impact of panic on crowd evacuation. Therefore, the evacuation efficiency of the existing crowd evacuation path planning methods is low.

[0003] Therefore, the prior art has defects and needs to be improved and developed. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a crowd evacuation path planning method taking into account the spread of panic in view of the above-mentioned defects of the prior art, aiming to solve the problem of low evacuation efficiency of the crowd evacuation path planning method in the prior art.

[0005] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0006] A method for planning a crowd evacuation route taking into account the spread of panic, wherein the method comprises:

[0007] Determine the initial individual panic level of each individual in the crowd of the target scene;

[0008] Determine the adjacent individuals of each individual, and update the initial individual panic level of each individual based on the initial individual panic levels of the adjacent individuals to obtain the individual panic level of each individual under panic propagation;

[0009] Perform panic attenuation processing on the individual panic level of each individual under panic propagation to obtain the final individual panic level at the current moment;

[0010] Determine the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, update the predicted obstacle avoidance speed at the next moment according to the final individual panic degree, and obtain the final obstacle avoidance speed of each individual at the next moment;

[0011] The crowd evacuation planning path is determined based on the final obstacle avoidance speed at each moment.

[0012] In one embodiment of the present application, determining the initial individual panic level of each individual in a crowd of a target scene includes:

[0013] Obtain the health status, sensitivity, average rate of adjacent individuals and preset individual maximum rate of each individual in the crowd of the target scene;

[0014] The initial individual panic level is determined based on each individual's health level, sensitivity level, average rate of neighboring individuals, and a preset individual maximum rate.

[0015] In one embodiment of the present application, the neighboring individuals of each individual are determined, and the initial individual panic level of each individual is updated based on the initial individual panic levels of the neighboring individuals to obtain the individual panic level of each individual under panic propagation, including:

[0016] Determine the adjacent individuals of each individual, and calculate the first distance between the centroid of each individual and the centroid of each adjacent individual;

[0017] Calculate the sum of the panic levels of each individual and the initial individual panic levels of all corresponding adjacent individuals;

[0018] The individual panic degree of each individual under panic propagation is calculated based on the total panic degree, the number of adjacent individuals and the first distance.

[0019] In one embodiment of the present application, panic attenuation processing is performed on the individual panic level of each individual under panic propagation to obtain the final individual panic level at the current moment, including:

[0020] Obtaining a preset distance for generating panic attenuation, a second distance between each individual and an exit of a target scene, and a sensitivity level of each individual;

[0021] Calculate the panic attenuation coefficient of each individual at the current moment using a pre-constructed panic attenuation model based on the individual panic degree of each individual under panic propagation, the second distance, and the sensitivity;

[0022] The final individual panic level at the current moment is calculated based on the individual panic level of each individual under panic propagation and the corresponding panic attenuation coefficient.

[0023] In one embodiment of the present application, the panic decay model is constructed based on the Heaviside step function.

[0024] In one embodiment of the present application, determining the predicted obstacle avoidance speed of each individual in a crowd of target scenes at the next moment includes:

[0025] The social force model is used to calculate the first obstacle avoidance speed of each individual in the crowd of the target scene at the current moment, and the ORCA obstacle avoidance algorithm is used to calculate the second obstacle avoidance speed of each individual in the crowd of the target scene at the current moment;

[0026] The predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment is calculated based on the first obstacle avoidance speed and the second obstacle avoidance speed.

[0027] In one embodiment of the present application, the predicted obstacle avoidance speed at the next moment is updated according to the final individual panic level to obtain the final obstacle avoidance speed of each individual at the next moment, including:

[0028] Calculating the final obstacle avoidance speed of each individual at the next moment according to the predicted obstacle avoidance speed at the next moment, the final individual panic level and the preset individual maximum speed;

[0029] Obtain the direction vector of the average obstacle avoidance speed of all adjacent individuals of each individual at the current moment, and calculate the final obstacle avoidance speed direction of each individual at the next moment according to the final individual panic degree, the direction vector of the predicted obstacle avoidance speed of each individual at the next moment, and the direction vector of the average obstacle avoidance speed;

[0030] The final obstacle avoidance speed of each individual at the next moment is obtained according to the final obstacle avoidance speed magnitude and the final obstacle avoidance speed direction.

[0031] The present application also provides a crowd evacuation path planning device taking into account the spread of panic, wherein the device comprises:

[0032] A determination module, used to determine the initial individual panic level of each individual in the crowd of the target scene;

[0033] A first updating module is used to determine the neighboring individuals of each individual, and update the initial individual panic level of each individual based on the initial individual panic levels of the neighboring individuals to obtain the individual panic level of each individual under panic propagation;

[0034] Attenuation module, used to perform panic attenuation processing on the individual panic level of each individual under panic propagation to obtain the final individual panic level at the current moment;

[0035] The second updating module is used to determine the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, and update the predicted obstacle avoidance speed at the next moment according to the final individual panic degree to obtain the final obstacle avoidance speed of each individual at the next moment;

[0036] The path planning module is used to determine the crowd evacuation planning path based on the final obstacle avoidance speed at each moment.

[0037] The present application also provides a terminal, which includes: a memory, a processor, and a crowd evacuation path planning program considering the spread of panic stored in the memory and executable on the processor, wherein the crowd evacuation path planning program considering the spread of panic, when executed by the processor, implements the steps of the crowd evacuation path planning method considering the spread of panic as described above.

[0038] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program can be executed to implement the steps of the crowd evacuation path planning method considering panic spread as described above.

[0039] The present invention provides a crowd evacuation path planning method considering panic spread, the method comprising: determining the initial individual panic degree of each individual in the crowd of the target scene; determining the adjacent individuals of each individual, and updating the initial individual panic degree of each individual based on the initial individual panic degree of the adjacent individuals, to obtain the individual panic degree of each individual under panic spread; performing panic attenuation processing on the individual panic degree of each individual under panic spread, to obtain the final individual panic degree at the current moment; determining the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, updating the predicted obstacle avoidance speed at the next moment according to the final individual panic degree, to obtain the final obstacle avoidance speed of each individual at the next moment; determining the crowd evacuation planning path based on the final obstacle avoidance speed at each moment. The present invention completes the crowd evacuation path planning while considering the influence of the crowd's panic emotions, improves the authenticity of the crowd evacuation path planning simulation, and thus improves the evacuation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of a preferred embodiment of a crowd evacuation path planning method considering the spread of panic in the present invention;

[0041] Figure 2 is a schematic diagram of the social force model in the present invention;

[0042] Figure 3 It is a functional principle block diagram of a preferred embodiment of a crowd evacuation path planning device considering panic spread in the present invention;

[0043] Figure 4 It is a functional principle block diagram of a preferred embodiment of the terminal in the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0045] The embodiments of the present application are based on a computer simulation model, and the methods involved are implemented through simulation. Crowd evacuation is a complex process, and large-scale crowd evacuation drills are difficult to implement due to problems such as difficulty in organization, high cost, and low personnel safety. The development of computer simulation technology provides a way to simulate crowd evacuation. The use of crowd evacuation simulation technology can simulate the crowd evacuation process and provide guidance for crowd evacuation in safety accidents.

[0046] In order to improve the authenticity of crowd evacuation path planning in the simulation model, the embodiment of the present application takes into account the interactive effects brought by multiple individuals in the group, the panic emotions of the crowd, and the spread of panic emotions, and combines the social force model and obstacle avoidance algorithm to simulate the evacuation process. The purpose is to simulate the evacuation process of the crowd through simulation and deduction, and provide decision-making reference for urban public safety emergency management personnel.

[0047] See also Figure 1 , Figure 1 is a flow chart of the crowd evacuation path planning method considering the spread of panic in the present invention. Figure 1 As shown, the crowd evacuation path planning method considering panic spread according to the embodiment of the present invention includes:

[0048] Step S100: determining the initial individual panic level of each individual in the crowd of the target scene.

[0049] Specifically, during the simulation, the crowd (i.e., agents) that need to be evacuated in the scene are given personalized attributes such as age, reaction time, and sensitivity. The initial panic level is calculated based on these personalized attributes and the speed and number of the surrounding crowds. According to the panic propagation radius, it is determined whether an agent will be affected by other agents around it. If there is an impact, the panic will be superimposed, and if there is no impact, the panic will gradually decrease. At the same time, considering that the panic level of the crowd tends to gradually decrease as the evacuation process proceeds, an exponential decay model is used to simulate this situation to obtain the final panic level.

[0050] When applied in actual scenarios, the number of individual pedestrians in the crowd in the target scene, location information and the initial panic level of the crowd are obtained through video cameras, Bluetooth, mobile phones and other devices, and then the evacuation path is obtained through simulation to provide decision-making reference for emergency management personnel. The management personnel then use mobile phones and other devices to provide evacuation guidance to the crowd.

[0051] In the embodiment of the present application, the step S100 specifically includes:

[0052] Step S110, obtaining the health level, sensitivity level, average rate of adjacent individuals and preset individual maximum rate of each individual in the crowd of the target scene;

[0053] Step S120: determining an initial individual panic level based on each individual's health level, sensitivity level, average rate of neighboring individuals, and a preset individual maximum rate.

[0054] Specifically, in actual scenarios, health and sensitivity can be obtained through a dedicated target APP; that is, the target APP is installed on the mobile terminals of the people in the target scenario, and the target APP records the health and sensitivity of the users. As in simulation, different parameter intervals can be set for people of different age groups, and random values ​​are taken within the corresponding intervals according to the age of each individual in the crowd of the target scenario.

[0055] When simulating, set personalized parameters for each agent i: health level h i , sensitivity i , reaction time τ i , where h i ,τ i ∈(0,1),s i ∈(0.2,0.8). In the application scenario, the health level, sensitivity level, average rate of adjacent individuals and preset individual maximum rate of each individual in the crowd of the target scene are obtained, and each individual is simulated as an intelligent agent.

[0056] Specifically, when setting the values ​​of health and sensitivity, the values ​​can be set based on the assessment of personality traits in the Big Five Personality Traits Model (OCEAN). Health is an intuitive reflection of a person's physical condition. For example, children are in better physical condition than the elderly, and their health will be appropriately higher. Sensitivity refers to the degree of impact of an emergency on a person. People with high sensitivity will have a higher degree of panic, and the panic attenuation coefficient will be smaller. Reaction time refers to the time required to take the next action, that is, how fast a person reacts, which mainly affects the size of the target force in social force.

[0057] The range of health level can be set from low to high. For example, low health level, with a range of 1-3, means that the individual is in poor physical condition, may suffer from chronic diseases or be in a sub-healthy state, and is prone to fatigue and discomfort. Medium health level, with a range of 4-6, means that the individual is in general physical condition, has no obvious diseases, but may occasionally have minor illnesses or feel physically tired. High health level, with a range of 7-9, means that the individual is in good physical condition, has strong immunity and recovery ability, and can cope with various challenges in daily life. The individual's health level can also be comprehensively assessed based on factors such as age, gender, living habits, and physical examination results, and the corresponding values ​​are given and recorded in the target APP.

[0058] The sensitivity value range can also be set from low to high. For example, low sensitivity: the value range is between 1-3, which means that the individual can remain calm and rational when facing an emergency, and is not prone to panic and anxiety. Medium sensitivity: the value range is between 4-6, which means that the individual will have a certain reaction and panic when facing an emergency, but can gradually calm down and take countermeasures. High sensitivity: the value range is between 7-9, which means that the individual is prone to strong panic and anxiety when facing an emergency, and the panic attenuation coefficient is small, and it is difficult to calm down quickly. The sensitivity of the individual can be comprehensively evaluated based on factors such as the individual's personality traits, past experiences, and psychological tolerance, and the corresponding value is given and recorded in the target APP.

[0059] The calculation formula for the initial individual panic level is:

[0060]

[0061] Among them, P i (t) represents the initial individual panic level of agent i at time t, N(i) represents the set of neighboring agents of agent i, represents the average rate of neighboring agents, v j represents the speed of agent j, ∥v j ∥ represents the speed v of agent j j Size, V max represents the maximum rate of the agent, σ(x) is the Sigmoid function, μ is a smoothing parameter, μ is set to 0.5, so that the value of σ(x) The change of is smoother. The individual panic level is defined by the agent's own attributes (health level, sensitivity level) and the movement speed of the surrounding neighboring agents. The average speed of the neighboring agents is obtained by calculating the average of the sum of the speeds of all neighboring agents.

[0062] like Figure 1 As shown, the crowd evacuation path planning method considering panic spread according to the embodiment of the present invention also includes:

[0063] Step S200: determine the neighboring individuals of each individual, and update the initial individual panic level of each individual based on the initial individual panic levels of the neighboring individuals to obtain the individual panic level of each individual under panic propagation.

[0064] In one embodiment of the present application, step S200 specifically includes:

[0065] Step S210: determine the adjacent individuals of each individual, and calculate the first distance between the centroid of each individual and the centroid of each adjacent individual;

[0066] Step S220, calculating the sum of panic levels of each individual and the initial individual panic levels of all corresponding adjacent individuals;

[0067] Step S230: Calculate the individual panic degree of each individual under panic propagation based on the total panic degree, the number of adjacent individuals and the first distance.

[0068] Specifically, when individuals are simulated as intelligent agents, the calculation formula for the individual panic degree after panic spread is:

[0069]

[0070] represents the individual panic level of agent i at time t after panic propagation, N i represents the number of neighboring agents of agent i, d ij Represents the distance between the centroids of agent i and agent j. The panic level of agent i after updating at time t The panic level P at time t i (t) and the panic level P of the neighboring agents j (t) The distance between the agent and the adjacent agent is determined by the mean of the sum of the two. At the same time, considering that the farther the distance between the agent and the adjacent agent is, the less panic spreads, so the distance d ij Inversely proportional.

[0071] The embodiment of the present application takes into account the influence of the degree of panic on the magnitude of the psychological repulsion between people, the magnitude and direction of the obstacle avoidance speed, and while improving the collision avoidance performance, increases the speed of going to the exit and increases the conformity of the individual evacuation direction, thereby improving the overall evacuation efficiency.

[0072] like Figure 1 As shown, the crowd evacuation path planning method considering panic spread according to the embodiment of the present invention also includes:

[0073] Step S300: Perform panic attenuation processing on the individual panic level of each individual under panic propagation to obtain the final individual panic level at the current moment.

[0074] In the embodiment of the present application, the step S300 specifically includes:

[0075] Step S310, obtaining a preset distance for generating panic attenuation, a second distance between each individual and the exit of the target scene, and a sensitivity level of each individual;

[0076] Step S320: Calculate the panic attenuation coefficient of each individual at the current moment using a pre-constructed panic attenuation model based on the individual panic degree of each individual under panic propagation, the second distance, and the sensitivity degree;

[0077] Step S330: Calculate the final individual panic level at the current moment according to the individual panic level of each individual under panic propagation and the corresponding panic attenuation coefficient.

[0078] Specifically, when individuals are simulated as intelligent agents, the calculation formula of the panic attenuation model is:

[0079]

[0080] represents the panic attenuation coefficient of agent i at time t, D represents the preset distance for panic decay. represents the second distance between agent i and exit g, h(x) is the Heaviside step function, An exponential model is used to simulate panic decay, according to the panic degree of agent i after panic propagation at time t Dynamically calculate the panic attenuation coefficient. The greater the panic level, the greater the panic attenuation coefficient and the smaller the panic attenuation amplitude. The value of determines whether panic decay will occur. This means that the higher the individual's sensitivity, the closer he is to the exit, and the more panic will decay.

[0081] The calculation formula for the final individual panic level at the current moment is:

[0082]

[0083] represents the final individual panic level of agent i at time t, which is the panic level P of agent i after panic propagation at time t. i (t) and the panic attenuation coefficient of agent i at time t to decide.

[0084] The embodiment of the present application superimposes the panic levels of individuals in the crowd to achieve panic emotion propagation, performs a certain panic attenuation near the exit, improves the authenticity of the simulation, and thereby obtains a crowd evacuation planning path with better evacuation effect.

[0085] In the embodiment of the present application, the panic decay model is constructed based on the Heaviside step function.

[0086] The embodiment of the present application constructs a panic decay model by using the Heaviside step function, so that the panic decay model can accurately describe the mutation phenomenon, simplify the model complexity, and enhance the model flexibility, thereby enabling the panic decay model to cope with the problem of group panic propagation.

[0087] like Figure 1 As shown, the crowd evacuation path planning method considering panic spread according to the embodiment of the present invention also includes:

[0088] Step S400: determining a predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, updating the predicted obstacle avoidance speed at the next moment according to the final individual panic degree, and obtaining a final obstacle avoidance speed of each individual at the next moment.

[0089] In the embodiment of the present application, the step S400 of “determining the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment” specifically includes:

[0090] Step S410, using the social force model to calculate the first obstacle avoidance speed of each individual in the crowd of the target scene at the current moment, and using the ORCA obstacle avoidance algorithm to calculate the second obstacle avoidance speed of each individual in the crowd of the target scene at the current moment;

[0091] Step S420: Calculate the obstacle avoidance speed of each individual in the crowd of the target scene at the next moment based on the first obstacle avoidance speed and the second obstacle avoidance speed.

[0092] Specifically, although ORCA can provide intelligent agents with strong obstacle avoidance capabilities, it lacks certain target-orientedness and the characterization of human behavior characteristics, which makes it very different from the actual situation when used in fields with a large number of intelligent agents such as crowd evacuation. Therefore, the social force model is used to improve it and make it more suitable for the obstacle avoidance function in crowd evacuation. Considering that the obstacle avoidance process should be close to human behavior without affecting the obstacle avoidance capability of the ORCA algorithm, the embodiment of the present application chooses to use the social force model composed of the improved target force, interaction force, and environmental force for adjustment.

[0093] like Figure 2 As shown in the figure, when the social force model is used to calculate the first obstacle avoidance speed of each individual in the crowd of the target scene at the current moment, the social force model is:

[0094]

[0095] m i represents the quality of agent i, represents the first obstacle avoidance speed of the agent at time t under the social force model, Δt represents a time step, and F goal 、F int、F env They represent target force, interaction force and environmental force respectively.

[0096] Target force F goal The expression is:

[0097]

[0098]

[0099] F goal The mass m of agent i i , expected speed v desired , current speed v i and the reaction time τ i The decision is made by both parties. desired The maximum rate V of the agent max and the vector of agent i pointing to the target exit g In addition to the reaction time τ i , the mass m of agent i i and the maximum rate V max It is also defined according to age groups to express individual differences among people. In the application scenario, the quality m i The acquisition of video can estimate the mass of a person by collecting images of each individual in the crowd. The expected speed is set by the maximum speed of ordinary people, and the maximum speed of the elderly is usually slower. Therefore, the correspondence between different age ranges and expected speeds is pre-stored. In the application scenario, the age range of a person can be determined based on the image after video collection, and the corresponding expected speed can be found based on the age range.

[0100] Interaction force F int The expression is:

[0101]

[0102] in, and Represent the psychological repulsion and physical repulsion between individuals respectively, and the expressions are as follows:

[0103]

[0104] A and B represent psychological repulsion The two parameters, R i and R j is the radius of agent i and agent j, that is, the agent is abstracted into a circle, such as Figure 2 As shown, the radius of the agent is the radius of the circle, d ijis the distance between the centroids of agent i and agent j, and ω represents the relative position of the crowd in the field of view of the agent. The degree of influence, 0≤ω≤1, is the direction vector of agent j pointing to the center of mass of agent i, φ ij represents the speed direction and k and l are the physical repulsive forces The two parameters of is the tangential force direction vector, ΔV ij is the speed difference between agent i and agent j, ΔV ij =∥v j -v i ∥, By R i +R j -d ij The value of determines the positional relationship between the two agents, and then determines whether physical repulsion is required at the critical point of collision. Make emergency evasive adjustments.

[0105] Environmental force F env The expression is as follows:

[0106]

[0107] in, and Represent the psychological repulsion and physical repulsion between the individual and the obstacle, respectively, and the expressions are as follows:

[0108]

[0109] F env represents the environmental force, W(i) represents the set of wall obstacles w around agent i, and d iw represents the distance between agent i and wall obstacle w, is the unit vector from obstacle w to agent i, is the direction of the tangential force.

[0110] The ORCA obstacle avoidance algorithm is used to calculate the second obstacle avoidance speed of each individual in the crowd of the target scene at the current moment. Then, using the first obstacle avoidance speed To make up for the shortcomings of the ORCA algorithm, the obstacle avoidance speed of the agent at time t+1 is obtained as follows:

[0111]

[0112] represents the predicted obstacle avoidance speed of agent i at time t+1, and α is the combination of and A coupling value of , α is taken as 0.5.

[0113] The embodiment of the present application combines the social force model and the ORCA obstacle avoidance algorithm to act together on the behavior of the intelligent agent. The social force model defines three forces possessed by the intelligent agent, namely target force, interaction force, and environmental force. Through these three forces, the speed of the intelligent agent under the social force model is calculated according to Newton's third law. The embodiment of the present application adds reaction time to the target force, and adds panic level and visual impact parameters to the interaction force to better simulate the impact of panic on evacuation in reality. After obtaining the obstacle avoidance speeds under the social force model and the ORCA obstacle avoidance algorithm respectively, the two speeds are combined through a weight to obtain the obstacle avoidance speed of each individual.

[0114] In one embodiment of the present application, the step S400 of “updating the predicted obstacle avoidance speed at the next moment according to the final individual panic level to obtain the final obstacle avoidance speed of each individual at the next moment” specifically includes:

[0115] Step S430, calculating the final obstacle avoidance speed of each individual at the next moment according to the predicted obstacle avoidance speed at the next moment, the final individual panic level and the preset individual maximum speed;

[0116] Step S440, obtaining the direction vector of the average obstacle avoidance speed of all adjacent individuals of each individual at the current moment, and calculating the final obstacle avoidance speed direction of each individual at the next moment according to the final individual panic degree, the direction vector of the predicted obstacle avoidance speed of each individual at the next moment, and the direction vector of the average obstacle avoidance speed;

[0117] Step S450: Obtain the final obstacle avoidance speed of each individual at the next moment according to the final obstacle avoidance speed magnitude and the final obstacle avoidance speed direction.

[0118] Specifically, the final obstacle avoidance speed of each individual at the next moment is calculated according to the predicted obstacle avoidance speed at the next moment, the final individual panic degree and the preset individual maximum speed, and the formula is as follows:

[0119]

[0120] in, Represents the final panic level of agent i at time t at time t+1 The final obstacle avoidance speed under the influence. yes The size of V max is the maximum rate of the agent (i.e. the preset individual maximum rate), and the two are combined through the degree of panic.

[0121] When evacuating people in a panic state, there will be a following phenomenon, so the speed direction is expressed as follows:

[0122]

[0123] in, The direction vector representing the average obstacle avoidance speed of the evacuated people at time t, is the predicted obstacle avoidance speed of agent i at time t+1 The direction vector of the two vectors is the final panic level at time t. Combined and normalized, we get the final obstacle avoidance speed direction under the influence of panic

[0124] Average obstacle avoidance speed The calculation formula is:

[0125]

[0126] is the obstacle avoidance speed of the adjacent individuals at the current moment, It is the average obstacle avoidance speed of adjacent individuals at the current moment.

[0127] Get the final obstacle avoidance speed under panic process The formula is:

[0128] The embodiment of the present application has the ability to cope with complex environments, simulates human motion performance, and also incorporates the degree of panic into the obstacle avoidance algorithm to improve the authenticity of the simulation.

[0129] like Figure 1 As shown, the crowd evacuation path planning method considering panic spread according to the embodiment of the present invention also includes:

[0130] Step S500: determining a crowd evacuation planning path based on the final obstacle avoidance speed at each moment.

[0131] Specifically, the embodiment of the present application calculates the final obstacle avoidance speed, that is, the movement rate and direction of the intelligent agent at the next moment, by taking into account the influence of the panic level. This process is repeated until the exit is reached, thereby completing the path planning.

[0132] The embodiment of the present application completes the obstacle avoidance work of crowd evacuation while taking into account the influence of crowd panic emotions, which can improve the authenticity of crowd evacuation path planning simulation while improving evacuation efficiency.

[0133] In one embodiment, if Figure 3As shown, based on the above-mentioned crowd evacuation path planning method considering the spread of panic, the present invention also provides a crowd evacuation path planning device considering the spread of panic, including:

[0134] A determination module 100 is used to determine the initial individual panic level of each individual in the crowd of the target scene;

[0135] A first updating module 200 is used to determine the neighboring individuals of each individual, and update the initial individual panic level of each individual based on the initial individual panic levels of the neighboring individuals to obtain the individual panic level of each individual under panic propagation;

[0136] Attenuation module 300, used to perform panic attenuation processing on the individual panic level of each individual under panic propagation, and obtain the final individual panic level at the current moment;

[0137] The second updating module 400 is used to determine the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, and update the predicted obstacle avoidance speed at the next moment according to the final individual panic level to obtain the final obstacle avoidance speed of each individual at the next moment;

[0138] The path planning module 500 is used to determine the crowd evacuation planning path based on the final obstacle avoidance speed at each moment.

[0139] Figure 4 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. The terminal may include:

[0140] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0141] When the processor 502 executes the program, the crowd evacuation path planning method considering the spread of panic provided in the above embodiment is implemented.

[0142] Furthermore, the terminal further includes:

[0143] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0144] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0145] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0146] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0147] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0148] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0149] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for planning a crowd evacuation route taking into account the spread of panic is implemented as described above.

[0150] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0151] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0152] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations, in which the order shown or discussed may not be followed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0153] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can read instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary and then storing it in a computer memory.

[0154] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0155] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0156] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0157] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

[0158] In summary, the present invention discloses a method for planning a crowd evacuation path considering panic spread, the method comprising: determining the initial individual panic level of each individual in the crowd of the target scene; determining the adjacent individuals of each individual, and updating the initial individual panic level of each individual based on the initial individual panic level of the adjacent individuals, to obtain the individual panic level of each individual under panic spread; performing panic attenuation processing on the individual panic level of each individual under panic spread, to obtain the final individual panic level at the current moment; determining the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, updating the predicted obstacle avoidance speed at the next moment according to the final individual panic level, to obtain the final obstacle avoidance speed of each individual at the next moment; determining the crowd evacuation planning path based on the final obstacle avoidance speed at each moment. The present invention completes the crowd evacuation path planning while considering the influence of the crowd's panic emotions, improves the authenticity of the crowd evacuation path planning simulation, and thus improves the evacuation efficiency.

[0159] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A crowd evacuation path planning method considering panic spread, characterized in that: The method comprises: Determine the initial individual panic level of each individual in the crowd of the target scene; Determine the adjacent individuals of each individual, and update the initial individual panic level of each individual based on the initial individual panic levels of the adjacent individuals to obtain the individual panic level of each individual under panic propagation; Perform panic attenuation processing on the individual panic level of each individual under panic propagation to obtain the final individual panic level at the current moment; Determine the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, update the predicted obstacle avoidance speed at the next moment according to the final individual panic degree, and obtain the final obstacle avoidance speed of each individual at the next moment; The crowd evacuation planning path is determined based on the final obstacle avoidance speed at each moment.

2. The crowd evacuation route planning method considering panic spread according to claim 1, characterized in that: Determine the initial individual panic level of each individual in the crowd of the target scene, including: Obtain the health status, sensitivity, average rate of adjacent individuals and preset individual maximum rate of each individual in the crowd of the target scene; The initial individual panic level is determined based on each individual's health level, sensitivity level, average rate of neighboring individuals, and a preset individual maximum rate.

3. The crowd evacuation route planning method considering panic spread according to claim 1, characterized in that: Determine the adjacent individuals of each individual, and update the initial individual panic level of each individual based on the initial individual panic levels of the adjacent individuals, and obtain the individual panic level of each individual under panic propagation, including: Determine the adjacent individuals of each individual, and calculate the first distance between the centroid of each individual and the centroid of each adjacent individual; Calculate the sum of the panic levels of each individual and the initial individual panic levels of all corresponding adjacent individuals; The individual panic degree of each individual under panic propagation is calculated based on the total panic degree, the number of adjacent individuals and the first distance.

4. The crowd evacuation path planning method considering panic spread according to claim 1, characterized in that: Perform panic attenuation processing on the individual panic level of each individual under panic propagation to obtain the final individual panic level at the current moment, including: Obtaining a preset distance for generating panic attenuation, a second distance between each individual and an exit of a target scene, and a sensitivity level of each individual; Calculate the panic attenuation coefficient of each individual at the current moment using a pre-constructed panic attenuation model based on the individual panic degree of each individual under panic propagation, the second distance, and the sensitivity; The final individual panic level at the current moment is calculated based on the individual panic level of each individual under panic propagation and the corresponding panic attenuation coefficient.

5. The crowd evacuation route planning method considering panic spread according to claim 4 is characterized in that: The panic decay model is constructed based on the Heaviside step function.

6. The method for planning a crowd evacuation path considering the spread of panic according to claim 1, characterized in that: Determine the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, including: The social force model is used to calculate the first obstacle avoidance speed of each individual in the crowd of the target scene at the current moment, and the ORCA obstacle avoidance algorithm is used to calculate the second obstacle avoidance speed of each individual in the crowd of the target scene at the current moment; The predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment is calculated based on the first obstacle avoidance speed and the second obstacle avoidance speed.

7. The crowd evacuation route planning method considering panic spread according to claim 1, characterized in that: The predicted obstacle avoidance speed at the next moment is updated according to the final individual panic level to obtain the final obstacle avoidance speed of each individual at the next moment, including: Calculating the final obstacle avoidance speed of each individual at the next moment according to the predicted obstacle avoidance speed at the next moment, the final individual panic level and the preset individual maximum speed; Obtain the direction vector of the average obstacle avoidance speed of all adjacent individuals of each individual at the current moment, and calculate the final obstacle avoidance speed direction of each individual at the next moment according to the final individual panic degree, the direction vector of the predicted obstacle avoidance speed of each individual at the next moment, and the direction vector of the average obstacle avoidance speed; The final obstacle avoidance speed of each individual at the next moment is obtained according to the final obstacle avoidance speed magnitude and the final obstacle avoidance speed direction.

8. A crowd evacuation route planning device considering the spread of panic, characterized in that: The device comprises: A determination module, used to determine the initial individual panic level of each individual in the crowd of the target scene; A first updating module is used to determine the neighboring individuals of each individual, and update the initial individual panic level of each individual based on the initial individual panic levels of the neighboring individuals to obtain the individual panic level of each individual under panic propagation; Attenuation module, used to perform panic attenuation processing on the individual panic level of each individual under panic propagation to obtain the final individual panic level at the current moment; The second updating module is used to determine the predicted obstacle avoidance speed of each individual in the crowd of the target scene at the next moment, and update the predicted obstacle avoidance speed at the next moment according to the final individual panic degree to obtain the final obstacle avoidance speed of each individual at the next moment; The path planning module is used to determine the crowd evacuation planning path based on the final obstacle avoidance speed at each moment.

9. A terminal, characterized in that: include: A memory, a processor, and a crowd evacuation path planning program considering the spread of panic stored in the memory and executable on the processor, wherein the crowd evacuation path planning program considering the spread of panic, when executed by the processor, implements the steps of the crowd evacuation path planning method considering the spread of panic as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program can be executed to implement the steps of the crowd evacuation route planning method considering panic spread as described in any one of claims 1 to 7.

Images