Crowd motion simulation method fused with walking aid equipment and computer equipment

Abstract

The invention is suitable for the field of crowd motion simulation, and provides a crowd motion simulation method fused with walking aid equipment, a computer readable storage medium and computer equipment. Comprising the following steps: constructing a building scene model, and configuring crowd parameters in the building scene model; according to the crowd parameters in the building scene model, calling and instantiating a corresponding number of intelligent agents, corresponding types and corresponding initial positions in the building scene model from a preset multi-mode intelligent agent model library, and endowing each intelligent agent with a corresponding parameter; and according to the intelligent agent at the corresponding initial position in the building scene model, based on a time stepping simulation cycle mechanism, dynamically simulating and deducing all the intelligent agents in the building scene model to carry out motion and interaction in the building scene model to obtain a simulation result. Compared with a traditional simplified model, the obtained crowd motion simulation result is closer to reality, the accuracy is greatly improved, and the crowd simulation precision is improved.

Description

Technical Field

[0001] This application belongs to the field of crowd movement simulation, and particularly relates to a crowd movement simulation method integrating walking aids, a computer-readable storage medium, and a computer device. Background Technology

[0002] Against the backdrop of rapid global population aging and urbanization, the safety and accessibility design of public places such as hospitals, senior living communities, and transportation hubs have become crucial. Pedestrian simulation technology, as an advanced quantitative analysis tool, is widely used in building design evaluation and emergency evacuation plan development, aiming to improve space utilization efficiency and safety by simulating and predicting crowd flow patterns. With increasing societal attention to vulnerable groups, realistically reproducing the complex movement behaviors of people using assistive devices, including those with disabilities and the elderly, in computer simulation environments has become a cutting-edge technology urgently needing breakthroughs in pedestrian traffic and public safety.

[0003] However, current mainstream crowd movement simulation technologies have serious shortcomings when simulating people using assistive devices. Existing crowd movement simulation models (such as cellular automata models and social force models) typically simplify all pedestrians into individuals with uniform size and behavioral patterns. For those with mobility impairments, they often use a crude approach of simply reducing their movement speed, completely ignoring the fundamental changes brought about by assistive devices (such as wheelchairs and canes). This results in crowd movement simulation models failing to reflect the physical constraints of assistive devices in terms of space occupation, turning radius, and gait rhythm, leading to severely distorted simulation results. Summary of the Invention

[0004] The purpose of this application is to provide a method for simulating crowd movement by integrating mobility aids, a computer-readable storage medium, and a computer device. It aims to solve the problem that existing crowd movement simulation models often use a crude approach of simply reducing the movement speed of people with mobility impairments, while completely ignoring the fundamental changes brought about by mobility aids, thus resulting in seriously distorted simulation results.

[0005] Firstly, this application provides a method for simulating crowd movement by integrating mobility aids, comprising the following steps: S101. Construct an architectural scene model and configure crowd parameters in the architectural scene model. The crowd includes at least people using walking aids and people with mobility impairments. The crowd parameters include the number of people using walking aids, the number of people with mobility impairments, and the initial position of each person in the architectural scene model. S102. Based on the crowd parameters located in the building scene model, call and instantiate a corresponding number of intelligent agents of the corresponding type and initial position in the building scene model from the preset multimodal intelligent agent model library, and assign corresponding parameters to each intelligent agent. The multimodal intelligent agent model library includes pedestrian intelligent agent models with convenient mobility and human intelligent agent models using mobility aids. S103. Based on the agents at their respective initial positions in the building scene model, and using a time-stepping simulation loop mechanism, dynamically simulate and deduce the movement and interaction of all agents in the building scene model to obtain the simulation results.

[0006] Furthermore, step S101 further includes the following steps: Receive user markings of accessible facilities in the building scene model, the accessible facilities including accessible elevators, accessible emergency exits and / or accessible ramps; S101 also includes the following steps: Receive user markings of physical elements in the building scene model, including walls, doors, corridors, normal exits and / or emergency evacuation exits.

[0007] Furthermore, the person using the mobility aid is either a person using crutches or a person using a wheelchair; The human agent model using mobility aids includes a human agent model using crutches and a human agent model using a wheelchair; The human agent model using a cane is defined with dynamic physical boundaries and velocity fluctuation functions. The dynamic physical boundary refers to the physical space occupied by the human agent using a cane, which is defined as a dynamically changing envelope. The size and shape of the envelope will change periodically according to the walking rhythm to simulate the extra space required when the cane is extended. The human agent model using a cane is also defined with environment-dependent behavior, which means that in high-density crowds or when walking long distances, the human agent using a cane is given a higher probability of finding and moving along the support. The intelligent agent model of the wheelchair user is defined with constraints on the length and width of the wheelchair, speed, acceleration, and linear and angular velocities. The speed and acceleration of the wheelchairs include those of electric wheelchairs and those of manual wheelchairs.

[0008] Furthermore, the group also includes caregivers of people using wheelchairs; The population parameter also includes the number of a person using a wheelchair and the number of caregivers accompanying the person using the wheelchair as a group; The multimodal agent model library also includes a combined agent model of a person using a wheelchair and a caregiver accompanying the person using the wheelchair as a combined entity; In the combined intelligent agent model, the caregiver is defined as an individual unit responsible for environmental perception, path planning, and speed decision-making; the wheelchair and the person using the wheelchair are defined as the following unit, which inherits the definition of the intelligent agent model of the person using the wheelchair. The caregiver and the following unit always maintain a fixed relative position and posture in the simulation. The movement of the combined entity is driven by the caregiver's desired speed, but follows the constraint relationship between the linear velocity and angular velocity of the following unit.

[0009] Secondly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the crowd motion simulation method for the integrated mobility aid device as described above.

[0010] Thirdly, this application provides a computer device, comprising: One or more processors; Memory; and One or more computer programs, the processor and the memory being connected via a bus, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, wherein the processors, when executing the computer programs, implement the steps of the crowd motion simulation method for the integrated mobility aid device as described above.

[0011] In this application, since the configured crowd parameters located in the building scene model include the number of people using mobility aids and the initial position of each person in the building scene model, agents of the corresponding number, type, and initial position in the building scene model are called and instantiated from a preset multimodal agent model library that includes agent models of people using mobility aids, based on the crowd parameters located in the building scene model. Therefore, the obtained crowd motion simulation results are closer to reality than traditional simplified models, and the accuracy is greatly improved, thus enhancing the precision of crowd simulation.

[0012] Furthermore, since the crowd parameters configured in the building scene model include the number of wheelchair users and their caregivers as a combined entity; and the multimodal intelligent agent model library also includes a combined intelligent agent model of wheelchair users and their caregivers as a combined entity, the accuracy of the resulting crowd motion simulation results is greatly improved, thus enhancing the precision of the crowd simulation.

[0013] Furthermore, by receiving user markings of accessible facilities in the building scene model, including accessible elevators, accessible emergency exits, and / or accessible ramps; and by receiving user markings of physical elements in the building scene model, including walls, doors, corridors, normal exits, and / or emergency evacuation exits, the system can identify evacuation bottlenecks specific to users of mobility aids that traditional models cannot detect, achieving accurate identification of evacuation bottlenecks. It allows for quantitative assessment and optimization of accessible passage widths, ramp locations, elevator capacity, etc., in buildings such as hospitals and nursing homes during the design phase, improving building safety and user-friendliness from the outset. It also helps managers develop and rehearse more realistic and effective emergency plans, enhancing the scientific rigor and relevance of these plans. Attached Figure Description

[0014] Figure 1 This is a flowchart of a crowd movement simulation method integrating walking aids provided in an embodiment of this application.

[0015] Figure 2a This is a schematic diagram of a convenient pedestrian intelligent agent model provided in one embodiment of this application.

[0016] Figure 2b This is a schematic diagram of a human intelligent agent model using a cane provided in one embodiment of this application.

[0017] Figure 2c This is a schematic diagram of a human intelligent agent model using a cane provided in one embodiment of this application.

[0018] Figure 2d This is a schematic diagram of a combined intelligent agent model provided in an embodiment of this application.

[0019] Figure 3 This is an example image of a crowd evacuation scene in a senior living community.

[0020] Figure 4 This is a structural block diagram of a computer device provided in one embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and beneficial effects of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0022] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0023] Please see Figure 1This is a flowchart of a crowd motion simulation method for an integrated mobility aid device provided in an embodiment of this application. This embodiment mainly uses the application of the crowd motion simulation method of the integrated mobility aid device to a computer device as an example for illustration. The crowd motion simulation method for an integrated mobility aid device provided in an embodiment of this application includes the following steps: S101. Construct an architectural scene model and configure the crowd parameters in the architectural scene model. The crowd includes at least people using walking aids and people with mobility impairments (i.e., people who do not need to use walking aids). The crowd parameters include the number of people using walking aids, the number of people with mobility impairments, and the initial position of each person in the architectural scene model.

[0024] In one embodiment of this application, the construction of the building scene model includes importing two-dimensional CAD drawings or three-dimensional BIM building layout drawings of the building to be evaluated.

[0025] In one embodiment of this application, S101 may further include the following steps: Receive user markings of accessibility facilities in the building scene model.

[0026] Accessible facilities include accessible elevators, accessible emergency exits, and accessible ramps.

[0027] S101 may also include the following steps: It receives user markings of physical elements such as walls, doors, corridors, normal exits, and emergency evacuation exits in the building scene model.

[0028] In one embodiment of this application, the person using the mobility aid may be a person using crutches or a person using a wheelchair.

[0029] The population may also include caregivers who accompany a person using a wheelchair. The population parameter may also include the number of individuals using a wheelchair and their caregivers as a single entity.

[0030] S102. Based on the crowd parameters located in the building scene model, call and instantiate a corresponding number of intelligent agents of the corresponding type and initial position in the building scene model from the preset multimodal intelligent agent model library, and assign corresponding parameters to each intelligent agent. The multimodal intelligent agent model library includes pedestrian intelligent agent models with convenient mobility and human intelligent agent models using mobility aids.

[0031] Using S102, a highly heterogeneous digital twin population with configurable population parameters is constructed before the simulation begins.

[0032] In one embodiment of this application, the human agent model using mobility aids includes a human agent model using crutches and a human agent model using a wheelchair.

[0033] The multimodal agent model library may also include a combined agent model consisting of a person using a wheelchair and a caregiver accompanying the person using the wheelchair.

[0034] Please see Figure 2a A mobile pedestrian intelligent agent model is defined as a social force model representing a person with a fixed radius. The movement of the pedestrian agent is determined by a desired velocity, following a social force model for obstacle avoidance and following; or it can be defined as a fixed-length, fixed-width cellular rectangle represented by a cellular automaton model, also following a cellular automaton model for obstacle avoidance and following. drive.

[0035] Please see Figure 2b The agent model of a person using a cane was defined with dynamic physical boundaries and velocity fluctuation functions. Among them, The dynamic physical boundary refers to the physical space occupied by a human agent using a cane, defined as a dynamically changing envelope. The size and shape of this envelope periodically change according to the walking rhythm to simulate the extra space required when the cane is extended. Typically, the size of the envelope changes periodically, and its radius... The minimum value is The maximum value is 150% of =

[0036] in, It is a circle with a fixed radius. It is the rhythm and frequency of a person using a cane walking. It refers to the phase difference of pedestrian gait in a simulated scenario. This is the amplitude of the change in the envelope, and it is recommended to set it to 1 / 4.

[0037] Due to the expected speed of people using canes It is not a constant, so it is defined by a velocity fluctuation function that includes random perturbations to reflect the instability and fatigue susceptibility of its gait.

[0038] Instantaneous speed of a person using a cane The expression is =

[0039] in, It is the average speed. It is the velocity amplitude. It is random noise, and its value is related to the differences in heterogeneous characteristics of pedestrians.

[0040] In one embodiment of this application, the human agent model using a cane is further defined with environment-dependent behavior, which means that in high-density crowds or when walking long distances, the human agent using a cane is given a higher probability of finding and moving along supports such as walls and handrails.

[0041] Please see Figure 2c The intelligent agent model of a wheelchair user was defined by the length of the wheelchair. Hekuan Velocity, acceleration, and linear velocity and angular velocity The constraints between them.

[0042] In one embodiment of this application, the speed and acceleration of the wheelchair include the speed and acceleration of an electric wheelchair and the speed and acceleration of a manual wheelchair.

[0043] Because wheelchairs cannot move laterally, their linear velocity... and angular velocity There are constraints between them.

[0044] The linear velocity and angular velocity The specific constraints between them are: ,in, It is the turning radius of the wheelchair. It is the minimum turning radius of the wheelchair.

[0045] Please see Figure 2d In the combined agent model, the caregiver is defined as an individual unit responsible for environmental perception, path planning, and speed decision-making; the wheelchair and the person using the wheelchair are defined as following units, inheriting the definition of the wheelchair user's agent model. The caregiver and following units maintain a fixed relative position and posture throughout the simulation, and the combined agent's movement is determined by the caregiver's desired speed. Driven, but adhering to the linear velocity of the follower unit. and angular velocity The constraints between them.

[0046] S103. Based on the agents at their respective initial positions in the building scene model, and using a time-stepping simulation loop mechanism, dynamically simulate and deduce the movement and interaction of all agents in the building scene model to obtain the simulation results.

[0047] In one embodiment of this application, S103 specifically includes the following steps: Based on the agents at their respective initial positions in the building scene model, a simulation loop mechanism based on time steps is used to calculate the next movement speed, direction, and position for each agent in the building scene model within each time step, according to its own model characteristics and the surrounding environment, until all agents reach the designated exit or reach the preset simulation deadline.

[0048] In one embodiment of this application, the dynamic simulation simulation of all intelligent agents in the architectural scene model moving and interacting within the architectural scene model specifically includes the following steps: S1031. Invoke the path planning algorithm that integrates accessibility costs to update or generate a path to the target for the agent that needs to make a decision.

[0049] The path planning algorithm that integrates accessibility costs specifically involves: making evacuation path planning decisions for each agent; integrating a path planning algorithm that incorporates accessibility facility preferences; assigning different weights to ordinary paths, stairs, accessible ramps, accessible elevators, etc.; setting accessibility type attributes for each discrete grid for discrete models such as cellular automata; and setting accessibility type attributes for each grid for continuous models such as social force models.

[0050] Path selection cost: People using canes, wheelchairs, and combinations thereof have different weights and path calculation costs for different area types, guiding each group to choose the appropriate route. For example, the path cost function for wheelchair users and combinations thereof will assign infinite cost to stairs, while assigning lower cost to accessible ramps and accessible elevators, and people using canes will have a higher path cost for stairs.

[0051] Local path adjustment: At each time step, the agent dynamically fine-tunes its desired speed and direction based on the local environment (other agents, obstacles) within its field of vision to avoid immediate collisions.

[0052] S1032, invoke the behavioral interaction rules based on the social force model or cellular automaton model to calculate the interaction and action rules between each agent and other agents and environmental obstacles.

[0053] For the social force model, the driving force from the target point, the repulsive force from other agents and walls, and the contact force between agents are calculated. For the composite entity, the whole is treated as a single object with greater mass and volume to calculate the resultant force. For the cellular automaton model, the state of each cell is updated according to predefined rules (such as prioritizing movement towards the exit, avoiding collisions, following, etc.). The set of movement rules differs for different types of agents; for example, a person using a wheelchair occupies multiple cells, and their movement must satisfy a cell sequence with a turning radius.

[0054] S1033, the rules governing the action of the integrated social force model or cellular automaton model, update the speed and position of the agent.

[0055] By combining the agent's path to the target with the interaction and action rules between the agent and other agents and environmental obstacles, the agent's acceleration, velocity, and spatial position at the current time step are updated according to the social force model or cellular automata model.

[0056] For human agents and combined agents using wheelchairs, kinematic constraint checks are also required to ensure that the relationship between linear velocity and angular velocity meets the minimum turning radius limit. If the calculated next movement violates the minimum turning radius limit, the speed is reduced or the movement is paused within a time step.

[0057] In one embodiment of this application, the crowd motion simulation method integrating mobility aids may further include the following steps: S104. Analyze and evaluate the simulation results.

[0058] In one embodiment of this application, S104 specifically involves: calculating evacuation assessment indicators based on the simulation results, generating visualized simulation results, and integrating the evacuation assessment indicators and visualized simulation results into a comprehensive evacuation safety assessment report for users to review and make decisions.

[0059] In one embodiment of this application, the evacuation assessment indicators include total evacuation time, evacuation time distribution of different groups of people, utilization efficiency of each exit, maximum personnel density in the scene, and bottleneck location of the scene.

[0060] Total evacuation time refers to the time from when the first person notices and begins to evacuate after an emergency evacuation alert is issued until the last person reaches a safe area.

[0061] The utilization efficiency of the exit is calculated as follows: the instantaneous flow and cumulative number of people passing through the safety exit passage of the building scene are calculated, and the passage efficiency and evacuation efficiency per unit width of the exit are quantified.

[0062] The maximum population density within the scene is calculated as follows: by analyzing population distribution data, the area with the largest instantaneous population density in the scene is identified and located.

[0063] The bottleneck locations in a scene are identified by analyzing congested areas with consistently high population density, identifying these areas as bottleneck locations, analyzing the center and radius of the bottleneck location, and analyzing the percentage of people using accessible facilities at the bottleneck location.

[0064] In one embodiment of this application, the visualized simulation results include an animation replay of the evacuation process, a heat map of population density, and a highlighted display of congested areas.

[0065] The evacuation process can be replayed in two or three dimensions, visually demonstrating the flow of people, the formation and dissipation of congestion points, and the path selection of different agents.

[0066] The following example illustrates this concept.

[0067] Scenario setting: An evacuation diagram of a senior living community building. The building has three floors and is equipped with two elevators and two evacuation staircases. Figure 3 This is a schematic diagram of the first-floor layout of a senior living community as an example. The floor area is 800 square meters, with one main staircase exit, two elevators, and a ramp connecting to an outdoor safety area. The first floor contains 16 apartments, with the following occupancy parameters: 10 people with good mobility, 10 people using canes, 5 people using wheelchairs, and 5 groups consisting of one wheelchair user and their caregiver. Assume that at a certain moment, a fire alarm sounds at one end of the floor, and all personnel must urgently evacuate to a safe area.

[0068] Implementation process and results analysis: The operator performs a simulation according to the crowd movement simulation method of the integrated mobility aid device provided in one embodiment of this application. During the dynamic simulation derivation (S103) on a single-level plane, the following key phenomena are observed: (1) Pedestrian agents with good mobility and some human agents using canes quickly choose the nearest exit steps for evacuation.

[0069] (2) All human agents and combined agents using wheelchairs planned paths to the accessible ramps due to their built-in path planning algorithms.

[0070] (3) Due to their large physical size and turning radius constraints, the human agent and the combined agent using wheelchairs move slowly at the narrow corners leading to the gentle slope passage and have obvious conflicts with other agents, creating a second congestion point.

[0071] (4) The simulation results show that the total evacuation time of the building is 4 minutes and 30 seconds. The assessment report clearly points out that the non-first-floor staircase entrance and the corner passage leading to the gentle slope are the two main bottlenecks in this evacuation.

[0072] One embodiment of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the crowd motion simulation method for integrated mobility aids provided in one embodiment of this application.

[0073] Figure 4 This diagram illustrates a specific structural block diagram of a computer device according to an embodiment of this application. The computer device 100 includes one or more processors 101, a memory 102, and one or more computer programs. The processors 101 and the memory 102 are connected via a bus. The one or more computer programs are stored in the memory 102 and configured to be executed by the one or more processors 101. When the processors 101 execute the computer programs, they implement the steps of the crowd movement simulation method for an integrated mobility aid device as provided in an embodiment of this application. The computer device includes servers and terminals, etc.

[0074] In this application, since the configured crowd parameters located in the building scene model include the number of people using mobility aids and the initial position of each person in the building scene model, agents of the corresponding number, type, and initial position in the building scene model are called and instantiated from a preset multimodal agent model library that includes agent models of people using mobility aids, based on the crowd parameters located in the building scene model. Therefore, the obtained crowd motion simulation results are closer to reality than traditional simplified models, and the accuracy is greatly improved, thus enhancing the precision of crowd simulation.

[0075] Furthermore, since the crowd parameters configured in the building scene model include the number of wheelchair users and their caregivers as a combined entity; and the multimodal intelligent agent model library also includes a combined intelligent agent model of wheelchair users and their caregivers as a combined entity, the accuracy of the resulting crowd motion simulation results is greatly improved, thus enhancing the precision of the crowd simulation.

[0076] Furthermore, by receiving user markings of accessible facilities in the building scene model, including accessible elevators, accessible emergency exits, and / or accessible ramps; and by receiving user markings of physical elements in the building scene model, including walls, doors, corridors, normal exits, and / or emergency evacuation exits, the system can identify evacuation bottlenecks specific to users of mobility aids that traditional models cannot detect, achieving accurate identification of evacuation bottlenecks. It allows for quantitative assessment and optimization of accessible passage widths, ramp locations, elevator capacity, etc., in buildings such as hospitals and nursing homes during the design phase, improving building safety and user-friendliness from the outset. It also helps managers develop and rehearse more realistic and effective emergency plans, enhancing the scientific rigor and relevance of these plans.

[0077] It should be understood that the steps in the various embodiments of this application are not necessarily executed sequentially according to the order indicated by the step numbers. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0078] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0079] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method of simulating a crowd motion with a walking aid, characterized by, The method comprises the following steps: S101, constructing a building scene model, configuring a crowd parameter in the building scene model, the crowd at least comprising a person using a walking aid device and a person with free movement, the crowd parameter comprising a number of persons using a walking aid device, a number of persons with free movement, and an initial position of each person in the building scene model; S102, calling and instantiating a corresponding number, a corresponding type, and a corresponding initial position in the building scene model from a preset multi-modal agent model library according to the crowd parameter in the building scene model, and giving each agent a corresponding parameter, the multi-modal agent model library comprising a person with free movement agent model and a person using a walking aid device agent model; S103, based on a time stepping simulation loop mechanism, dynamically simulating and deducing all agents in the building scene model to move and interact in the building scene model according to the agents in the corresponding initial position in the building scene model, and obtaining a simulation result.

2. The method of claim 1, wherein, The S101 further comprises the following steps: receiving a user's marking of barrier-free facilities in the building scene model, the barrier-free facilities comprising barrier-free elevators, barrier-free emergency exits, and / or barrier-free ramps; The S101 further comprises the following steps: receiving a user's marking of physical elements in the building scene model, the physical elements comprising walls, doors, corridors, normal exits, and / or emergency evacuation exits.

3. The method of claim 1, wherein, The person using a walking aid device is a person using a walking stick or a person using a wheelchair; The person using a walking aid device agent model comprises a person using a walking stick agent model and a person using a wheelchair agent model; The person using a walking stick agent model is defined with a dynamic physical boundary and a speed fluctuation function, the dynamic physical boundary refers to a physical occupation space of the person using a walking stick agent being defined as a dynamic changing envelope box, a size and a shape of the envelope box periodically change according to a walking rhythm to simulate an extra space required when the walking stick is extended; The person using a walking stick agent model is further defined with an environment-dependent behavior, the environment-dependent behavior refers to the person using a walking stick agent being given a higher probability to find and move along a support in a high-density crowd or a long-distance walking; The person using a wheelchair agent model is defined with a length and a width of a wheelchair, a speed, an acceleration, and a constraint relationship between a linear speed and an angular speed; The speed and the acceleration of the wheelchair comprise a speed and an acceleration of an electric wheelchair and a speed and an acceleration of a manual wheelchair.

4. The method of claim 3, wherein, The crowd further comprises a caregiver accompanying a person using a wheelchair; The crowd parameter further comprises a number of combinations of a person using a wheelchair and a caregiver accompanying the person using a wheelchair; The multi-modal agent model library further comprises a combination body agent model of a combination of a person using a wheelchair and a caregiver accompanying the person using a wheelchair; The companion in the combined agent model is defined as an individual unit, responsible for environment perception, path planning and speed decision; the wheelchair and the person using the wheelchair are defined as a following unit, the following unit inherits the definition of the agent model of the person using the wheelchair, the companion and the following unit always maintain a fixed relative position and posture in the simulation, the movement of the combined body is driven by the desired speed of the companion, but the constraint relationship between the linear speed and the angular speed of the following unit is obeyed.

5. The method of claim 1, wherein, S103 specifically comprises the following steps: According to the agent in the corresponding initial position in the building scene model, based on the time stepping simulation cycle mechanism, the movement speed, direction and position of each agent in the building scene model are calculated according to its own model characteristics and the surrounding environment at each time step, until all agents reach the specified exit or reach the preset simulation cutoff time.

6. The method of claim 1, wherein, The dynamic simulation deduction of all agents in the building scene model moving and interacting in the building scene model specifically comprises the following steps: S1031, calling a path planning algorithm that fuses barrier-free cost, updating or generating a path to the target for the agent that needs to make a decision; S1032, calling the behavior interaction rule based on the social force model or the cellular automaton model, calculating the interaction and action rule between each agent and other agents and environmental obstacles; S1033, updating the speed and position of the agent by integrating the action rules of the social force model or the cellular automaton model.

7. The method of claim 6, wherein, The path planning algorithm that fuses barrier-free cost is specifically: for each agent decision evacuation path planning, fuse the path planning algorithm preferred by barrier-free facilities, give different weights to ordinary path, stairs, barrier-free ramp and barrier-free elevator, for discrete model, set barrier-free type attribute for each discrete grid, for continuous model, set barrier-free type attribute for each grid.

8. The method of claim 1, wherein, The method further comprises the following steps: S104, analyzing and evaluating the results of the simulation.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to realize the steps of the crowd motion simulation method of the walking aid device fusion according to any one of claims 1 to 8.

10. A computer device comprising: one or more processors; a memory; and one or more computer programs, the processor and the memory are connected through the bus, wherein the one or more computer programs are stored in the memory and are configured to be executed by the one or more processors, characterized in that the processor executes the computer program to realize the steps of the crowd motion simulation method of the walking aid device fusion according to any one of claims 1 to 8.

Images