Super-large space pedestrian flow simulation system

Abstract

The invention relates to an ultra-large space pedestrian flow simulation system, and relates to the technical field of pedestrian flow management technologies, and the system comprises an autonomous decision behavior simulation module which simulates the behavior decision of pedestrians in a complex space, and the behavior decision comprises path selection, speed adjustment and avoidance behaviors; the environment sensing module is used for identifying obstacles, channel layout, exit positions and other environment characteristics in the space; the time period flow simulation module simulates pedestrian flow density and distribution in different time periods, and analyzes and optimizes configuration of various service facilities; and the visual display module is used for displaying a simulation result through a thermodynamic diagram, a traffic matrix and evacuation path tracking. According to the method, factors such as pedestrian behaviors, environmental perception and density are comprehensively considered, the optimal path is generated, pace is dynamically adjusted, congestion and collision are avoided, and meanwhile, the system senses environmental changes in real time and predicts the future flow trend through sensor data fusion and machine learning technologies.

Description

Technical Field

[0001] The present application relates to the technical field of pedestrian flow management, and in particular to a large-space pedestrian flow simulation system. Background Art

[0002] With the acceleration of urbanization and the increasing number of large venues, pedestrian flow management in ultra-large spaces has become a key issue. Effective pedestrian flow management can not only improve the efficiency of personnel passage, but also effectively ensure the safety of personnel in emergency situations. Therefore, how to accurately simulate the flow pattern of pedestrians in ultra-large spaces and make scientific decisions has become an important research direction in the fields of intelligent buildings and public safety. Existing pedestrian flow simulation systems usually focus on certain single factors, such as path planning or traffic prediction, and most simulation systems find it difficult to achieve comprehensive dynamic adaptation. In actual applications, pedestrian flow behavior is affected by multiple factors, including environmental layout, pedestrian density, targets, avoidance behavior, etc., and these factors often interact with each other, causing the system complexity to increase greatly.

[0003] In the existing technology, although there are some basic flow simulation systems, most of these systems are based on traditional rule settings or simple model derivation, and cannot effectively handle large-scale, highly complex environments and dynamic changes. Especially when encountering complex avoidance behaviors and uncertain environmental changes, they often cannot provide sufficiently accurate and efficient simulation results. Therefore, there is an urgent need for a very large space pedestrian flow simulation system that can perform comprehensive simulation and prediction from multiple dimensions and angles. It not only takes into account the autonomous decision-making behavior of pedestrians, but also perceives environmental changes in real time, and performs efficient optimization and adjustment through the simulation of time period flow. In order to better meet these challenges, the present invention proposes a very large space pedestrian flow simulation system, which integrates modules such as autonomous decision-making, environmental perception, and time period flow simulation. It can respond to environmental changes in real time, generate accurate decision-making models, and provide a scientific basis for pedestrian flow management and facility configuration. Summary of the Invention

[0004] The purpose of this application is to provide a large-space pedestrian flow simulation system.

[0005] A large-space pedestrian flow simulation system, comprising: Autonomous decision-making behavior simulation module: used to simulate pedestrians' behavioral decisions in complex spaces, including path selection, speed adjustment, and avoidance behavior; Environmental perception module: used to identify obstacles, channel layout, exit locations, and other environmental features in the space to support pedestrian environmental adaptation behavior simulation; Time period traffic simulation module: used to simulate pedestrian flow density and distribution in different time periods, and analyze and optimize the configuration of various service facilities; Visualization display module: Displays simulation results through heat maps, traffic matrices, and evacuation path tracing, providing quantitative indicators, including traffic speed, bottleneck capacity, and evacuation efficiency, to assist decision-making.

[0006] Preferably, the autonomous decision-making behavior simulation module specifically includes: Path selection unit: determines the spatial target that the pedestrian wants to reach based on the pedestrian's destination; Spatial evaluation unit: Calculates the travel cost of each optional path based on the spatial layout, obstacles, and channel width information provided by the environmental perception module; Path planning unit: Based on the pedestrian's goals and spatial evaluation, the Dijkstra algorithm is used to calculate the optimal path or suboptimal path and select the most suitable route for the pedestrian. The Dijkstra algorithm formula is: Where C(P) is the total travel cost of path P, w i is the weight of each path, d i is the distance of the path segment, n is the number of samples; Speed ​​adjustment unit: dynamically adjusts the pace of pedestrians based on the density of surrounding pedestrians and channel width factors; Traffic adaptation unit: adjusts its own speed according to the direction and speed of pedestrian flow in the environment to avoid collisions and congestion; Avoidance behavior unit: Detects the distance between pedestrians and other pedestrians and obstacles in real time. When a collision risk is detected, it triggers an avoidance action. After the avoidance action is completed, the pedestrian replans the path based on the real-time situation and returns to the original route. Decision weight and behavior evaluation unit: By setting the weights of decision behaviors, evaluating the priorities of path selection, speed adjustment, and avoidance behavior, and combining the outputs of path selection, speed adjustment, and avoidance behavior, a comprehensive decision model is generated. Based on the output of the comprehensive decision model, the optimal behavior of pedestrians in a specific environment is obtained.

[0007] Preferably, the dynamically adjusting the pedestrian's pace according to the distribution density of surrounding pedestrians and the channel width factors specifically includes: Based on the density and channel width information, the pedestrian's pace is dynamically adjusted. The formula for pace adjustment is as follows: v a is the adjusted pedestrian speed, v max is the maximum speed of pedestrians, D is the pedestrian density in the current area, MD is the maximum density of pedestrian flow, W c is the current width of the channel, Wr the minimum width required for pedestrians; During the pace adjustment process, a smoothing function is used to smoothly transition the pedestrian's speed change. The smoothing function formula is: v n =v c +γ×(v a -v c ) Where, v n is the new speed after adjustment, v c is the current speed, v a is the target speed calculated based on the density and width factors, and γ is the smoothing factor used to control the smoothness of the pace adjustment.

[0008] Preferably, the steps of setting weights for decision-making behaviors, evaluating the priorities of path selection, speed adjustment, and avoidance behaviors, and combining the outputs of path selection, speed adjustment, and avoidance behaviors to generate a comprehensive decision-making model, and obtaining the optimal action mode for pedestrians in a specific environment based on the output of the comprehensive decision-making model specifically include: Behavior weights are set, including path selection weight, speed adjustment weight, and avoidance behavior weight, to evaluate the behavior module output. The output of each behavior is combined with its corresponding weight to generate a comprehensive decision model. Based on the output of the decision model, the optimal action mode for pedestrians is obtained by comprehensively considering path selection, speed adjustment, and avoidance behavior. The formula of the comprehensive decision model is: D t =w p P0+w s ·V o +w a A0 Where D t is the comprehensive decision output, i.e. the final action decision, P0 is the output of path selection, w p is the output weight coefficient of path selection, V o is the output of speed adjustment, w s is the weight coefficient of the speed adjustment output, A0 is the output of the avoidance behavior, w a The weight coefficient for the output of the avoidance behavior.

[0009] Preferably, the environment perception module specifically includes: Obstacle recognition and dynamic update unit: Identify fixed obstacles in the space, including walls, pillars, furniture, and road signs; Dynamic obstacle recognition unit: Identifies dynamic obstacles, detects the distance between pedestrians in real time, updates the status of dynamic obstacles based on pedestrian movements, identifies obstacles, and plans paths to avoid collisions; Aisle layout and space planning: Identify and quantify changes in aisle width, capacity, and layout. By analyzing the aisle layout, determine whether there is congestion and dynamically adjust pedestrian paths. Use sensors and predefined models to identify exit locations in the space and guide pedestrians toward their target locations. The environmental dynamic update and feedback unit monitors changes in the surrounding environment, including pedestrian density, flow direction, and obstacle location, updates perception data, and updates the pedestrian decision model in real time based on the environmental perception data.

[0010] Preferably, the environment perception module further includes: Sensor Data Fusion and Environmental Reasoning Unit: This unit integrates data from different sensors to form an environmental perception model. It then performs environmental reasoning based on the perceived data, analyzing the degree of spatial congestion, obstacle distribution, and path accessibility, supporting pedestrians' autonomous decision-making and behavioral adjustments. Real-time state assessment and environmental adaptation unit: At each moment, the system assesses the current environmental state, including pedestrian speed, density, and path congestion; According to the real-time evaluation results, the pedestrian behavior strategy is adjusted. Through the perceived environmental changes, the pedestrian density and flow in different time periods are predicted. Based on historical data and real-time perception data, future environmental changes are predicted, and the pedestrian paths and behaviors are planned and adjusted in advance, and the environmental adaptation strategy is adjusted in advance.

[0011] Preferably, the predicting of future environmental changes based on historical data and real-time perception data, planning and adjusting pedestrian paths and behaviors in advance, and adjusting environmental adaptation strategies in advance specifically include: Based on historical pedestrian flow data, analyze pedestrian density and flow trends in different time periods to predict possible congestion areas and channel bottlenecks in the future; Combining real-time data with historical data and using machine learning technology, we can predict environmental change trends and predict high-density areas and channel blockages that will appear in the next period of time. Combined with the prediction results, it dynamically adjusts the future pedestrian path choices, predicts the flow conditions in different time periods in advance, and provides the optimal evacuation and access routes based on the predicted pedestrian density and path capacity; Adjust pedestrian behavior strategies based on real-time status assessment and prediction results.

[0012] Preferably, the real-time collected data is combined with historical data, and machine learning technology is used to predict environmental change trends, and the prediction of high-density areas and channel blockages that will appear in the next period of time specifically includes: The prediction formula is: Where, P c (t) represents the congestion level at time t, represents the pedestrian flow density at time t, ρ t Represents a threshold density.

[0013] Preferably, the time period flow simulation module specifically includes: Use sensors to obtain current pedestrian flow data in real time, normalize the collected data, and divide the data into time periods; Based on traffic volume and area, a pedestrian density calculation model is established to predict density distribution at different time periods. Historical data is used for trend analysis, and time series analysis is applied to predict future flow trends. The analysis area is divided into grid cells. By simulating the pedestrian density and flow in each cell, the pedestrian flow and distribution in different time periods are simulated. The pedestrian flow speed and direction are adjusted according to the time period, and the change of density over time is simulated.

[0014] Preferably, the method of establishing a pedestrian density calculation model based on traffic flow and area, predicting density distribution in different time periods, using historical data for trend analysis, and applying time series analysis to predict future flow trends specifically includes: The prediction formula is: Where, X t represents the observation value at time t, is the autoregressive coefficient, X t-1 , X t-2 , X t-p is the observation value at the past p moments.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a large-space pedestrian flow simulation system that comprehensively considers factors such as pedestrian behavior, environmental perception, and density to generate an optimal path and dynamically adjust the pace to avoid congestion and collisions. At the same time, the system uses sensor data fusion and machine learning technology to perceive environmental changes in real time and predict future flow trends, optimizing channel layout and facility configuration. The time period flow simulation module predicts flow density in different time periods through historical data and real-time perception data, and the visualization display module intuitively presents the simulation results, providing real-time support and optimization solutions for decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a system module framework diagram of the present invention; Figure 2 This is a unit framework diagram of the autonomous decision-making behavior simulation module in the present invention. DETAILED DESCRIPTION

[0017] The following is combined with Figure 1 -Attached Figure 2 , further details of this application are given.

[0018] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0019] Reference Figure 1 As shown, a large-space pedestrian flow simulation system includes: Autonomous decision-making behavior simulation module: used to simulate pedestrians' behavioral decisions in complex spaces, including path selection, speed adjustment, and avoidance behavior; Environmental perception module: used to identify obstacles, channel layout, exit locations, and other environmental features in the space to support pedestrian environmental adaptation behavior simulation; Time period traffic simulation module: used to simulate pedestrian flow density and distribution in different time periods, and analyze and optimize the configuration of various service facilities; Visualization display module: Displays simulation results through heat maps, traffic matrices, and evacuation path tracing, providing quantitative indicators, including traffic speed, bottleneck capacity, and evacuation efficiency, to assist decision-making.

[0020] Reference Figure 2 As shown in Figure 1, the autonomous decision-making behavior simulation module specifically includes: Path selection unit: determines the spatial target that the pedestrian wants to reach based on the pedestrian's destination; Spatial evaluation unit: Calculates the travel cost of each optional path based on the spatial layout, obstacles, and channel width information provided by the environmental perception module; Path planning unit: Based on the pedestrian's goals and spatial evaluation, the Dijkstra algorithm is used to calculate the optimal path or suboptimal path and select the most suitable route for the pedestrian. The Dijkstra algorithm formula is: Where C(P) is the total travel cost of path P, w i is the weight of each path, d i is the distance of the path segment, n is the number of samples; Speed ​​adjustment unit: dynamically adjusts the pace of pedestrians based on the density of surrounding pedestrians and channel width factors; Traffic adaptation unit: adjusts its own speed according to the direction and speed of pedestrian flow in the environment to avoid collisions and congestion; Avoidance behavior unit: Detects the distance between pedestrians and other pedestrians and obstacles in real time. When a collision risk is detected, it triggers an avoidance action. After the avoidance action is completed, the pedestrian replans the path based on the real-time situation and returns to the original route. Decision weight and behavior evaluation unit: By setting the weights of decision behaviors, evaluating the priorities of path selection, speed adjustment, and avoidance behavior, and combining the outputs of path selection, speed adjustment, and avoidance behavior, a comprehensive decision model is generated. Based on the output of the comprehensive decision model, the optimal behavior of pedestrians in a specific environment is obtained.

[0021] Dynamically adjusting pedestrian pace based on surrounding pedestrian density and channel width factors includes: Based on the density and channel width information, the pedestrian's pace is dynamically adjusted. The formula for pace adjustment is as follows: v a is the adjusted pedestrian speed, v max is the maximum speed of pedestrians, D is the pedestrian density in the current area, MD is the maximum density of pedestrian flow, W c is the current width of the channel, W r Minimum width required for pedestrians; During the pace adjustment process, a smoothing function is used to smoothly transition the pedestrian's speed change. The smoothing function formula is: v n =v c +γ×(v a -v c ) Where, v n is the new speed after adjustment, v c is the current speed, v a is the target speed calculated based on the density and width factors, and γ is the smoothing factor used to control the smoothness of the pace adjustment.

[0022] By setting the weights of decision-making behaviors and evaluating the priorities of path selection, speed adjustment, and avoidance behavior, a comprehensive decision-making model is generated based on the outputs of path selection, speed adjustment, and avoidance behavior. Based on the output of the comprehensive decision-making model, the optimal action mode for pedestrians in a specific environment is obtained, including: Behavior weights are set, including path selection weight, speed adjustment weight, and avoidance behavior weight, to evaluate the behavior module output. The output of each behavior is combined with its corresponding weight to generate a comprehensive decision model. Based on the output of the decision model, the optimal action mode for pedestrians is obtained by comprehensively considering path selection, speed adjustment, and avoidance behavior. The formula of the comprehensive decision model is: D t =wp P0+w s ·V o +w a A0 Where D t is the comprehensive decision output, i.e. the final action decision, P0 is the output of path selection, w p is the output weight coefficient of path selection, V o is the output of speed adjustment, w s is the weight coefficient of the speed adjustment output, A0 is the output of the avoidance behavior, w a The weight coefficient for the output of the avoidance behavior.

[0023] The environmental perception module specifically includes: Obstacle recognition and dynamic update unit: Identify fixed obstacles in the space, including walls, pillars, furniture, and road signs; Dynamic obstacle recognition unit: Identifies dynamic obstacles, detects the distance between pedestrians in real time, updates the status of dynamic obstacles based on pedestrian movements, identifies obstacles, and plans paths to avoid collisions; Aisle layout and space planning: Identify and quantify changes in aisle width, capacity, and layout. By analyzing the aisle layout, determine whether there is congestion and dynamically adjust pedestrian paths. Use sensors and predefined models to identify exit locations in the space and guide pedestrians toward their target locations. The environmental dynamic update and feedback unit monitors changes in the surrounding environment, including pedestrian density, flow direction, and obstacle location, updates perception data, and updates the pedestrian decision model in real time based on the environmental perception data.

[0024] The environmental perception module also includes: Sensor Data Fusion and Environmental Reasoning Unit: This unit integrates data from different sensors to form an environmental perception model. It then performs environmental reasoning based on the perceived data, analyzing the degree of spatial congestion, obstacle distribution, and path accessibility, supporting pedestrians' autonomous decision-making and behavioral adjustments. Real-time state assessment and environmental adaptation unit: At each moment, the system assesses the current environmental state, including pedestrian speed, density, and path congestion; Adjust pedestrian behavior strategies based on real-time assessment results. By sensing environmental changes, predict pedestrian density and flow over different time periods. Based on historical data and real-time sensing data, predict future environmental changes, plan and adjust pedestrian paths and behaviors in advance, and adjust environmental adaptation strategies in advance. According to the pedestrian density and channel width, the system dynamically adjusts the pedestrian's pace and speed to avoid congestion and collision and ensure smooth flow.

[0025] Based on historical data and real-time perception data, we predict future environmental changes, plan and adjust pedestrian paths and behaviors in advance, and adjust environmental adaptation strategies in advance. Specifically, we include: Based on historical pedestrian flow data, analyze pedestrian density and flow trends in different time periods to predict possible congestion areas and channel bottlenecks in the future; Combining real-time data with historical data and using machine learning technology, we can predict environmental change trends and predict high-density areas and channel blockages that will appear in the next period of time. Combined with the prediction results, it dynamically adjusts the future pedestrian path choices, predicts the flow conditions in different time periods in advance, and provides the optimal evacuation and access routes based on the predicted pedestrian density and path capacity; Adjust pedestrian behavior strategies based on real-time status assessment and prediction results; Based on historical traffic data and real-time perception data, the system can simulate pedestrian flow and density distribution in different time periods to help optimize channel layout and service facility allocation.

[0026] By combining real-time data with historical data and using machine learning technology, we can predict environmental change trends and the occurrence of high-density areas and channel blockages in the next period of time. Specifically, we can: The prediction formula is: Where, P c (t) represents the congestion level at time t, represents the pedestrian flow density at time t, ρ t Represents a threshold density.

[0027] The time period traffic simulation module specifically includes: Use sensors to obtain current pedestrian flow data in real time, normalize the collected data, and divide the data into time periods; Based on traffic volume and area, a pedestrian density calculation model is established to predict density distribution at different time periods. Historical data is used for trend analysis, and time series analysis is applied to predict future flow trends. The analysis area is divided into grid cells. By simulating the pedestrian density and flow in each cell, the pedestrian flow and distribution in different time periods are simulated. The pedestrian flow speed and direction are adjusted according to the time period, and the change of density over time is simulated.

[0028] Based on traffic volume and area, a pedestrian density calculation model is established to predict density distribution at different time periods. Historical data is used for trend analysis, and time series analysis is applied to predict future flow trends. Specific details include: The prediction formula is: Where, X t represents the observation value at time t, is the autoregressive coefficient, X t-1 , X t-2 , X t-p is the observation value at the past p moments.

[0029] In summary, the advantages of the present invention are: By comprehensively considering multiple factors of pedestrian behavior, such as destination, environmental perception, and surrounding density, the optimal travel path is generated, ensuring the flow efficiency of pedestrians in complex environments; According to pedestrian density and channel width, the system dynamically adjusts pedestrian pace and speed to avoid congestion and collisions and ensure smooth flow; By fusing data from different sensors, the system can dynamically perceive environmental changes, assess current flow conditions, and predict future flow trends through machine learning technology, thus avoiding potential bottlenecks or congested areas in advance. Based on historical traffic data and real-time perception data, the system can simulate pedestrian flow and density distribution in different time periods to help optimize channel layout and service facility configuration; Through heat maps, traffic matrices, and evacuation path tracking, the system can intuitively display simulation results and provide real-time decision support, allowing decision makers to quickly analyze and make reasonable adjustments.

[0030] The examples of this specific embodiment are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Identical components are represented by the same reference numerals. Therefore, any equivalent changes made based on the structure, shape, and principle of this application should be included in the scope of protection of this application.

Claims

1. A large-space pedestrian flow simulation system, characterized in that: include: Autonomous decision-making behavior simulation module: used to simulate pedestrians' behavioral decisions in complex spaces, including path selection, speed adjustment, and avoidance behavior; Environmental perception module: used to identify obstacles, channel layout, exit locations, and other environmental features in the space to support pedestrian environmental adaptation behavior simulation; Time period traffic simulation module: used to simulate pedestrian flow density and distribution in different time periods, and analyze and optimize the configuration of various service facilities; Visualization display module: Displays simulation results through heat maps, traffic matrices, and evacuation path tracing, providing quantitative indicators, including traffic speed, bottleneck capacity, and evacuation efficiency, to assist decision-making.

2. The ultra-large space pedestrian flow simulation system according to claim 1, characterized in that: The autonomous decision-making behavior simulation module specifically includes: Path selection unit: determines the spatial target that the pedestrian wants to reach based on the pedestrian's destination; Spatial evaluation unit: Calculates the travel cost of each optional path based on the spatial layout, obstacles, and channel width information provided by the environmental perception module; Path planning unit: Based on the pedestrian's goals and spatial evaluation, the Dijkstra algorithm is used to calculate the optimal path or suboptimal path and select the most suitable route for the pedestrian. The Dijkstra algorithm formula is: Where C(P) is the total travel cost of path P, w i is the weight of each path, d i is the distance of the path segment, and n is the number of samples; Speed ​​adjustment unit: dynamically adjusts the pace of pedestrians based on the density of surrounding pedestrians and channel width factors; Traffic adaptation unit: adjusts its own speed according to the direction and speed of pedestrian flow in the environment to avoid collisions and congestion; Avoidance behavior unit: Detects the distance between pedestrians and other pedestrians and obstacles in real time. When a collision risk is detected, it triggers an avoidance action. After the avoidance action is completed, the pedestrian replans the path based on the real-time situation and returns to the original route. Decision weight and behavior evaluation unit: By setting the weights of decision behaviors, evaluating the priorities of path selection, speed adjustment, and avoidance behavior, and combining the outputs of path selection, speed adjustment, and avoidance behavior, a comprehensive decision model is generated. Based on the output of the comprehensive decision model, the optimal behavior of pedestrians in a specific environment is obtained.

3. The ultra-large space pedestrian flow simulation system according to claim 2, characterized in that: The dynamic adjustment of pedestrian pace according to the distribution density of surrounding pedestrians and channel width factors specifically includes: Based on the density and channel width information, the pedestrian's pace is dynamically adjusted. The formula for pace adjustment is as follows: v a is the adjusted pedestrian speed, v max is the maximum speed of pedestrians, D is the pedestrian density in the current area, MD is the maximum density of pedestrian flow, W c is the current width of the channel, W r Minimum width required for pedestrians; During the pace adjustment process, a smoothing function is used to smoothly transition the pedestrian's speed change. The smoothing function formula is: v n =v c +γ×(v a -v c ) Where, v n is the new speed after adjustment, v c is the current speed, v a is the target speed calculated based on the density and width factors, and γ is the smoothing factor used to control the smoothness of the pace adjustment.

4. The ultra-large space pedestrian flow simulation system according to claim 2, characterized in that: The above-mentioned decision-making behavior weights are set to evaluate the priorities of path selection, speed adjustment, and avoidance behavior. The outputs of path selection, speed adjustment, and avoidance behavior are combined to generate a comprehensive decision-making model. Based on the output of the comprehensive decision-making model, the optimal action mode for pedestrians in a specific environment is obtained. Specifically, the following are included: Behavior weights are set, including path selection weight, speed adjustment weight, and avoidance behavior weight, to evaluate the behavior module output. The output of each behavior is combined with its corresponding weight to generate a comprehensive decision model. Based on the output of the decision model, the optimal action mode for pedestrians is obtained by comprehensively considering path selection, speed adjustment, and avoidance behavior. The formula of the comprehensive decision model is: D t =w p ·P0+w s ·V o +w a ·A0 Where D t is the comprehensive decision output, i.e. the final action decision, P0 is the output of path selection, w p is the output weight coefficient of path selection, V o is the output of speed adjustment, w s is the weight coefficient of the speed adjustment output, A0 is the output of the avoidance behavior, w a The weight coefficient for the output of the avoidance behavior.

5. The ultra-large space pedestrian flow simulation system according to claim 1, characterized in that: The environment perception module specifically includes: Obstacle recognition and dynamic update unit: Identifies fixed obstacles in the space, including walls, pillars, furniture, and road signs; Dynamic obstacle recognition unit: Identifies dynamic obstacles, detects the distance between pedestrians in real time, updates the status of dynamic obstacles based on pedestrian movements, identifies obstacles, and plans paths to avoid collisions; Aisle layout and space planning: Identify and quantify changes in aisle width, capacity, and layout. By analyzing the aisle layout, determine whether there is congestion and dynamically adjust pedestrian paths. Use sensors and predefined models to identify exit locations in the space and guide pedestrians toward their target locations. The environmental dynamic update and feedback unit monitors changes in the surrounding environment, including pedestrian density, flow direction, and obstacle location, updates perception data, and updates the pedestrian decision model in real time based on the environmental perception data.

6. The ultra-large space pedestrian flow simulation system according to claim 1, characterized in that: The environment perception module also includes: Sensor Data Fusion and Environmental Reasoning Unit: This unit integrates data from different sensors to form an environmental perception model. It then performs environmental reasoning based on the perceived data, analyzing the degree of spatial congestion, obstacle distribution, and path accessibility, supporting pedestrians' autonomous decision-making and behavioral adjustments. Real-time state assessment and environmental adaptation unit: At each moment, the system assesses the current environmental state, including pedestrian speed, density, and path congestion; According to the real-time evaluation results, the pedestrian behavior strategy is adjusted. Through the perceived environmental changes, the pedestrian density and flow in different time periods are predicted. Based on historical data and real-time perception data, future environmental changes are predicted, and the pedestrian paths and behaviors are planned and adjusted in advance, and the environmental adaptation strategy is adjusted in advance.

7. The ultra-large space pedestrian flow simulation system according to claim 6, characterized in that: The method of predicting future environmental changes based on historical data and real-time perception data, planning and adjusting pedestrian paths and behaviors in advance, and adjusting environmental adaptation strategies in advance specifically includes: Based on historical pedestrian flow data, analyze pedestrian density and flow trends in different time periods to predict possible congestion areas and channel bottlenecks in the future; Combining real-time data with historical data and using machine learning technology, we can predict environmental change trends and predict high-density areas and channel blockages that will appear in the next period of time. Combined with the prediction results, it dynamically adjusts the future pedestrian path choices, predicts the flow conditions in different time periods in advance, and provides the optimal evacuation and access routes based on the predicted pedestrian density and path capacity; Adjust pedestrian behavior strategies based on real-time status assessment and prediction results.

8. The ultra-large space pedestrian flow simulation system according to claim 7, characterized in that: The real-time collected data is combined with historical data, and machine learning technology is used to predict environmental change trends, predict the high-density areas that will appear in the next period of time, and predict the specific channel blockages. include: The prediction formula is: Where, P c (t) represents the congestion level at time t, represents the pedestrian flow density at time t, ρ t Represents a threshold density.

9. The ultra-large space pedestrian flow simulation system according to claim 1, characterized in that: The time period flow simulation module specifically includes: Use sensors to obtain current pedestrian flow data in real time, normalize the collected data, and divide the data into time periods; Based on traffic volume and area, a pedestrian density calculation model is established to predict density distribution at different time periods. Historical data is used for trend analysis, and time series analysis is applied to predict future flow trends. The analysis area is divided into grid cells. By simulating the pedestrian density and flow in each cell, the pedestrian flow and distribution in different time periods are simulated. The pedestrian flow speed and direction are adjusted according to the time period, and the change of density over time is simulated.

10. The ultra-large space pedestrian flow simulation system according to claim 9, characterized in that: Based on the flow rate and area, a pedestrian density calculation model is established to predict the density distribution in different time periods, and historical data is used for trend analysis. Time series analysis is applied to predict future flow trends. include: The prediction formula is: Where, X t represents the observation value at time t, is the autoregressive coefficient, X t-1 , X t-2 , X t-p is the observation value at the past p moments.

Images