Human-Vehicle Interaction Simulation Method, System and Application Based on Improved Social Force Model

Abstract

The present invention relates to the fields of urban traffic management, supervision, and traffic simulation, and provides a human-vehicle interaction simulation method, system, and application based on an improved social force model; the method includes S1 constructing an improved social force model; S2 constructing a decision-making model, which is used to determine the behavior patterns when pedestrians and vehicles meet; S3 given the initial basic data of pedestrians and vehicles, using the improved social force model and the decision-making model, perform interactive simulation on the movement of people and vehicles. The present invention can be applied to scenarios where vehicles and pedestrians cross and mix, such as intersections without traffic lights, including cross intersections and multi-directional intersections. The present invention significantly improves the authenticity of the model in complex traffic environments, can more accurately simulate the behavior decisions of pedestrians in actual scenarios, especially in the case of potential conflicts between pedestrians and vehicles; through the introduction of modular design and transfer learning, the model can quickly adapt to dynamically changing environments.

Description

Technical Field

[0001] The present invention relates to the fields of urban traffic management, supervision, and traffic simulation, and particularly to a human-vehicle interaction simulation method, system, and application based on an improved social force model, which can be used in traffic management and supervision, and is particularly applicable to an information processing system for traffic prediction purposes. Background Art

[0002] In an urban mixed traffic system, pedestrians will have frequent and complex interactions with different traffic participants and the surrounding environment. These interactions involve the path selection, speed adjustment, and avoidance of potential risks of individual pedestrians. To better understand and simulate pedestrian behavior, the social force model has been widely used in pedestrian simulation. This model can effectively simulate how pedestrians adjust their movement trajectories in a traffic environment to avoid collisions with others, and can also combine environmental factors, such as buildings, obstacles, etc., to further optimize the simulation of pedestrian movement.

[0003] In the social force model, a pedestrian is regarded as a moving particle under force, and the movement trajectory is determined by the movement simulation equation in the model. The behavior of each pedestrian is described by the psychological force and physical force in the equation. The psychological force reflects the internal intention of the pedestrian, and the physical force reflects the collision avoidance behavior generated by the pedestrian to avoid collisions. At each simulation moment, the pedestrian dynamically adjusts his movement state according to the resultant force obtained from the model equation, thereby truly reproducing the movement behavior of pedestrians in a real scenario.

[0004] Authorized Chinese Patent CN115092166B, an interactive autonomous driving speed planning method based on a social force model, solves the problem that the current speed planning method has poor rationality of the planned speed due to ignoring the interaction between people. Authorized Chinese Patent CN110414365B, a method, system, and medium for predicting the trajectory of crossing pedestrians based on a social force model, can improve the safety of autonomous driving vehicles when driving in a zebra crossing area with mixed traffic of people and vehicles, and reduce the delay rate of vehicles. Authorized Chinese Patent CN102682303B, a method for detecting abnormal crowd events based on an LBP weighted social force model, performs the detection of abnormal crowd behaviors by innovatively calculating the social force by combining optical flow and LBP spectrum.

[0005] The social force model shows good results in most pedestrian simulations, but it has obvious limitations when dealing with complex vehicle-pedestrian interaction scenarios. First, it ignores the speed difference. In the formula of the social force model, the psychological force differences generated by vehicles with different speeds on pedestrians are not fully considered. In actual scenarios, pedestrians' perception and reaction to vehicles often vary significantly with the change of vehicle speed. Vehicles traveling at high speeds usually make pedestrians feel greater pressure and a sense of urgency, resulting in pedestrians being more cautious or rapid when making avoidance decisions. However, when calculating the interaction force between pedestrians and vehicles, the social force model usually fails to weight-adjust the vehicle speed as an influencing factor, leading to inaccurate simulation of pedestrians' reactions and inability to truly reflect pedestrians' psychological pressure and behavior choices. Second, there is the problem of decision-making limitations. The model relies on simple mechanical calculations and mainly describes pedestrians' movement behaviors through physical and psychological forces. However, during the vehicle-pedestrian interaction process, pedestrians' decisions are often affected by multiple factors, such as the perception and judgment of vehicle speed, intention, and surrounding environmental risks, and these complex cognitive processes are difficult to accurately simulate through a simple mechanical model.

[0006] In existing traffic management, it is necessary to monitor traffic flow in real time and even make advance predictions. There is an urgent need to develop effective traffic data processing methods and systems with predictive purposes. Summary of the Invention

[0007] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a human-vehicle interaction simulation method, system, and application based on an improved social force model. By introducing an improved social force model and a decision model, the problem of simulating pedestrians' behaviors in complex vehicle-pedestrian interaction scenarios is solved.

[0008] The present invention adopts the following technical solutions:

[0009] On the one hand, the present invention provides a human-vehicle interaction simulation method based on an improved social force model, including:

[0010] S1. Construct an improved social force model, which is used to simulate the influence of driving force, vehicle-pedestrian interaction force, pedestrian-pedestrian interaction force, and obstacle repulsive force on the walking speed of pedestrians; the improved social force model optimizes the influence of vehicle speed, distance, and interaction angle between vehicles and pedestrians on pedestrian movement.

[0011] S2. Construct a decision model, which is used to determine the behavior patterns when pedestrians and vehicles meet; the decision model optimizes the influence of vehicle speed, distance, and interaction angle between vehicles and pedestrians on pedestrian decisions.

[0012] S3. Given the initial basic data of pedestrians and vehicles, use the improved social force model in step S1 and the decision model in step S2 to perform interactive simulation on the movement of pedestrians and vehicles.

[0013] For any of the possible implementation manners described above, a further implementation manner is provided. In step S1, the improved social force model is expressed as:

[0014]

[0015] (2)

[0016]

[0017] f ij psy = A ped exp. [ ( r ij - d ij ) / B ped ] n ij ⃗ （ 4 ）

[0018]

[0019]

[0020] f io psy = A obs exp. [ ( r i - d io ) / B obs ] n io ⃗ （ 7 ）

[0021]

[0022]

[0023]

[0024] (11)

[0025] (12)

[0026] In the formula: The driving force for the pedestrian towards the destination, which drives the pedestrian to the destination. The pedestrian adjusts the current speed and direction according to the desired speed and direction at certain intervals. The interaction force between pedestrians; The repulsive force of the obstacle on the pedestrian; The interaction force between the pedestrian and the vehicle; The random factor; N1, N2, and N are the total numbers of vehicles, obstacles, and pedestrians respectively;

[0027] , The mass and speed of the pedestrian, , respectively represent the desired speed and desired movement direction of the pedestrian, The interval time;

[0028] The psychological force and physical force of the interaction force between pedestrians respectively; The distance between the centroids of pedestrians, , is the sum of the radii of two pedestrians. When two pedestrians approach, a psychological force to avoid approaching each other is generated; the judgment of the physical force is determined by When the distance between two pedestrians is less than a certain distance, decides, is a piecewise function. When the distance between pedestrians is less than a certain distance, > , then a physical force is generated; when ≤ , , no physical force is generated; , are parameters used to adjust the interaction strength between pedestrians, , The elastic coefficient and sliding friction coefficient of the human body respectively reflect the coefficient of the human body's reaction to collision or approach and the friction coefficient generated when approaching, is the direction of the force exerted by pedestrian j on target pedestrian i, is the tangential speed difference between pedestrians;

[0029] The psychological force and physical force of the repulsive force of the obstacle on the pedestrian respectively, The pedestrian radius, is the distance between the centroid of the pedestrian and the obstacle. When the pedestrian and the obstacle approach, a psychological force to avoid approaching each other is generated; the judgment of the physical force is determined by When the distance between the pedestrian and the obstacle is less than a certain distance, > , then a physical force is generated; when ≤ , ; 、 are parameters for adjusting the intensity of the action of obstacles on pedestrians, 、 are the human body elastic coefficient and the sliding friction coefficient, respectively reflecting the coefficient of the human body's response to collision or approach and the friction coefficient generated during approach, is the direction of the force exerted by the obstacle on the pedestrian, is the unit vector in the tangential direction between the pedestrian and the obstacle; is the velocity vector of pedestrian i;

[0030] 、 parameters for adjusting the intensity of the action of vehicles on pedestrians, is the distance between the pedestrian and the vehicle; the anisotropy coefficient describes the relationship between the interaction force and the angle between the vehicle driving direction and the pedestrian movement direction. is the parameter for adjusting the anisotropic characteristics, represents the angle between the pedestrian movement direction and the vehicle driving direction, ranging from to ; is the unit vector from pedestrian i to the vehicle;

[0031] parameters for evaluating whether the speed difference between the vehicle and the pedestrian exceeds the set threshold , is the speed difference between the pedestrian and the vehicle, and u is the parameter for adjusting the influence of the speed difference on the acting force, is the vehicle speed.

[0032] For any of the possible implementation manners as described above, a further implementation manner is provided. The parameters 、 、 、 、 、 、 、u in the improved social force model are optimized by the Bayesian optimization method; the specific Bayesian optimization method is as follows:

[0033] Z1, the Bayesian model is:

[0034] Parameter space , where ={ 、 、 、 、 、 、 、 }, each Represents a parameter group used to perform one evaluation of the objective function;

[0035] The objective function F( ) = Y: Y is the output objective value after the input parameter group ; the output objective value Y is the average displacement error of pedestrians; after a certain simulation process, the predicted trajectories of all pedestrians are obtained, and the average displacement error of pedestrians is calculated based on the predicted trajectories and the true trajectories; the average displacement error formula is:

[0036] ;

[0037] is the x - coordinate of the predicted position of pedestrian i at time t, is the y - coordinate of the predicted position of pedestrian i at time t, is the x - coordinate of the true position of pedestrian i at time t, is the y - coordinate of the true position of pedestrian i at time t, and N is the total number of pedestrians;

[0038] The acquisition function S: used to select the optimal parameter group for the next evaluation ;

[0039] ;

[0040] The dataset D: contains all the evaluated parameter groups and the corresponding objective values ;

[0041] , where n is the total number of evaluations;

[0042] Z2. Initialization:

[0043] Randomly select K parameter groups for the initial evaluation of the objective function to obtain the dataset D, where K is the number of initial sampling times;

[0044]

[0045] Z3. Iterative optimization:

[0046] In each iteration, Bayesian optimization performs the following steps:

[0047] Z31. Gaussian process modeling:

[0048] Assume that the objective function is continuous in the parameter space and satisfies the Gaussian process; this means that the value of the objective function at any position in the parameter space can be described by a mean function and a variance function to represent its distribution characteristics; specifically, the distribution form of the value of the objective function at a given position is expressed as:

[0049] ;

[0050] is the mean value of all objective function values that have been iterated so far, is the variance of all objective function values that have been iterated so far; P() is the probability distribution, D t is the current data set, x t+1 is the parameter group for the next iteration;

[0051] Z32. Select the next parameter group: At each iteration, Bayesian optimization selects the next group of parameter groups to be evaluated; through the acquisition function S, the parameter with the largest potential improvement is selected :

[0052] ;

[0053] ;

[0054] is the optimal objective value iterated to the current step, is the objective function value of the parameter group;

[0055] Z33. Update the data set: The selected parameter points are used to calculate the objective function values through the objective function, and the results are added to the existing training data; then, the updated data set is used to refit the Gaussian process model to make more accurate predictions in the next iteration:

[0056]

[0057] Z34. Termination condition: Reach the maximum number of iterations or meet the convergence condition to obtain the optimal parameter group ;

[0058] = { , , , , , , , }.

[0059] For any of the possible implementation manners as described above, a further implementation manner is provided. In step S2, the decision method adopted by the decision model is specifically:

[0060] X1. Calculate the future conflict points between pedestrians and vehicles

[0061] X2. If there is a conflict point, calculate the time for the pedestrian and the vehicle to reach the conflict point according to their speeds and directions at the current moment, and determine the order of arrival.

[0062] X3. If the vehicle arrives at the conflict point first, then:

[0063] X31. Calculate the position of the pedestrian when the vehicle reaches the conflict point, and determine the risk area and dangerous area of the vehicle at the conflict point according to the driving direction of the vehicle; the risk area is the area where there is a potential conflict between the pedestrian and the vehicle, and the dangerous area is the area where the conflict between the pedestrian and the vehicle cannot be avoided.

[0064] X32. Judge whether the future position of the pedestrian is within the risk area.

[0065] If the future position of the pedestrian is not within the risk area of the vehicle, continue to calculate the motion state of the pedestrian according to the improved social force model.

[0066] If the pedestrian is in the risk area, further judge whether it is in the dangerous area.

[0067] If the pedestrian is in the risk area and not in the dangerous area, calculate the time difference between the pedestrian and the vehicle reaching the conflict point; if the time difference does not exceed the set threshold, the decision output is to slow down slowly along the current direction; if the time difference exceeds the threshold, the decision output is to enter hesitation.

[0068] If the pedestrian is in the dangerous area, further judge the interaction angle between the pedestrian and the vehicle; when the interaction angle is a lateral interaction, the decision output is to stop suddenly along the current direction; when the interaction angle is a front-back interaction, the decision output is to make a sharp turn.

[0069] X4. If the pedestrian arrives at the conflict point first, then:

[0070] X41. Calculate the position of the vehicle when the person reaches the conflict point, and determine the risk area and dangerous area of the vehicle at the conflict point according to the driving direction of the vehicle.

[0071] X42. Judge whether the vehicle is within the risk area.

[0072] If the pedestrian is not within the risk area, continue to calculate the motion state according to the social force model.

[0073] If the pedestrian is within the risk area, further judge whether the pedestrian is in the dangerous area or the risk area.

[0074] If the pedestrian is in the risk area and not in the dangerous area, calculate the time difference between the pedestrian and the vehicle reaching the conflict point; if the time difference does not exceed the set threshold, the output decision is to accelerate slowly along the current direction; if the time difference exceeds the threshold, the output is to enter the hesitation state.

[0075] If a pedestrian is in a dangerous area, it is judged according to the interaction angle; when the interaction angle is a lateral interaction, the output decision is to run and accelerate in the current direction; when the interaction angle is a front-back interaction, the output decision is to make a sharp turn.

[0076] For any of the possible implementation manners described above, a further implementation manner is provided. The specific method of step S3 includes:

[0077] S31. Input the initial basic data of the pedestrian and the vehicle, where the basic data includes the initial positions, speeds, time steps, and destinations of the pedestrian and the vehicle;

[0078] S32. Calculate the target position of the pedestrian at the current time step, where the target position is determined according to the planned path between the actual position at the current time step and the destination;

[0079] According to the Astar algorithm, by inputting the final destination position, the Astar algorithm will plan an optimal path (the shortest or with the lowest cost) for the pedestrian to reach the final destination from the current position. This path is composed of a series of discrete points, and each point can be regarded as a node on the path. The algorithm will output the target position (the next node that should be moved towards at the current moment);

[0080] S33. Input the current speed vector, current position, and target position of the pedestrian into the improved social force model, and calculate the resultant force it receives;

[0081] S34. Enter the decision model, and generate the decision output at the current time step based on the relative distance and speed between the pedestrian and the vehicle;

[0082] S35. Adjust the resultant force received by the pedestrian according to the decision output obtained at the current time step;

[0083] S36. Adjust the speed of the pedestrian according to the resultant force adjusted in step S35, and calculate the actual position of the pedestrian at the next time step;

[0084] S37. Repeat steps S32 - S36 until all time steps are completed.

[0085] For any of the possible implementation manners described above, a further implementation manner is provided. In step S35, the specific method of adjusting the resultant force received by the pedestrian according to the decision output is:

[0086] When the pedestrian chooses to make a sharp turn, the improved social force model adjusts the social force to a force perpendicular to the direction of the vehicle according to the relative position direction between the pedestrian and the vehicle. The direction of the force depends on the position of the pedestrian relative to the vehicle and is determined according to the direction to be avoided;

[0087] When a pedestrian chooses slow acceleration or running acceleration, the social force is adjusted to the acceleration force along the current velocity direction, and the walking speed and acceleration upper limit of the pedestrian are adjusted to higher running speed and acceleration.

[0088] When a pedestrian chooses to decelerate or make an emergency stop, the social force is adjusted to the acceleration force along the current reverse velocity, and the acceleration of the pedestrian is replaced with a higher emergency stop acceleration.

[0089] When a pedestrian leaves the dangerous area but is still in the risk area, the previous decision is maintained, and the pedestrian continues to run, decelerate or turn until leaving the risk area.

[0090] In step S32, the Astar algorithm is used to calculate the target position of the pedestrian.

[0091] On the other hand, the present invention also provides a human-vehicle interaction simulation system based on an improved social force model, which is used to implement the above method. The system includes:

[0092] A social force calculation module, which calculates the social force received by the pedestrian according to the improved social force model.

[0093] A decision-making module, which is used to determine the behavior pattern when a pedestrian and a vehicle meet.

[0094] An interaction simulation module, which gives the initial basic data of the pedestrian and the vehicle, and uses the social force calculation module and the decision-making module to perform an interaction simulation on the movement of the pedestrian and the vehicle.

[0095] On the other hand, the present invention also provides an application of a human-vehicle interaction simulation method based on an improved social force model, and the method is applied to a scenario where vehicles and pedestrians are mixed in a crossway.

[0096] For any of the above possible implementation manners, a further implementation manner is provided. The method is applied to an intersection without traffic lights; the intersection includes a crossroads and a multi-directional intersection.

[0097] The beneficial effects of the present invention are as follows:

[0098] 1. Improve the authenticity of the simulated trajectory: By combining the Astar algorithm, the improved social force model and the decision-making model based on human-vehicle interaction, the present invention significantly improves the authenticity in a complex traffic environment. Traditional models often ignore subtle interaction details when dealing with the dynamic interaction between pedestrians and vehicles, such as the immediate impact of vehicle speed changes on pedestrian behavior. By introducing dynamic factors such as relative speed and distance, the present invention can more accurately simulate the behavior decision-making of pedestrians in actual scenarios, especially in the case of potential conflicts between pedestrians and vehicles. Compared with the traditional social force model, the average displacement error of the improved social force model is reduced by 11% on average.

[0099] 2. Improve the safety of simulation results. By combining with the decision-making module, pedestrians can more accurately predict and respond to potential collision risks during the interaction with vehicles. Compared with the traditional social force model, the improved social force model reduces the average relative error of the post-encroachment time by 8%.

[0100] The post-encroachment time is an important indicator in the traffic field for evaluating potential conflict risks, which refers to the time difference between the passing times of two traffic participants (such as pedestrians and vehicles) at a common conflict point.

[0101]

[0102] is the time for the vehicle to reach the conflict point at the current speed and direction, is the time for the pedestrian to reach the conflict point at the current speed and direction.

[0103] The formula for the relative error of the post-encroachment time is:

[0104]

[0105] is the PET value of the simulation trajectory, is the PET value of the real trajectory.

[0106] 3. The simulation system of the present invention can be applied to traffic flow management and supervision in real scenarios to warn of possible traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0107] Figure 1 The figure shows a schematic diagram of the decision model in the embodiment of the present invention.

[0108] Figure 2 The figure shows a flowchart of the interactive simulation in the embodiment.

[0109] Figure 3 The figure shows a schematic diagram of the dangerous area of the vehicle in the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0110] The following will describe the specific embodiments of the present invention in detail with reference to the specific drawings. It should be noted that the technical features described in the following embodiments or the combination of technical features should not be considered isolated, and they can be combined with each other to achieve better technical effects.

[0111] An embodiment of the present invention provides a human-vehicle interaction simulation method based on an improved social force model, including:

[0112] S1. Construct an improved social force model, which is used to simulate the influence of driving force, pedestrian-vehicle interaction force, pedestrian-pedestrian interaction force, and obstacle repulsion force on the walking speed of pedestrians. The improved social force model optimizes the influence of the speed, distance, and interaction angle between pedestrians and vehicles on the walking of pedestrians.

[0113] S2. Construct a decision-making model, which is used to determine the behavior patterns when pedestrians and vehicles meet. The decision-making model optimizes the influence of the speed, distance, and interaction angle between pedestrians and vehicles on the decision-making of pedestrians.

[0114] S3. Given the initial basic data of pedestrians and vehicles, use the improved social force model in step S1 and the decision-making model in step S2 to conduct interactive simulations on the movement of pedestrians and vehicles.

[0115] The specific process is as Figure 2 shown.

[0116] 1. Traditional social force model:

[0117] In the social force model, it can be divided into driving force, pedestrian-vehicle interaction force, pedestrian-pedestrian interaction force, obstacle repulsion force, and a random force, as shown in formula (1).

[0118]

[0119] is the driving force of the destination on the pedestrian, driving the pedestrian to the destination. As shown in formula (2), the pedestrian will adjust the current speed and direction according to the desired speed and direction at a certain interval. , is the mass and speed of the pedestrian. , represents the desired speed and desired movement direction of the pedestrian. is the interval time.

[0120]

[0121] The interaction force between pedestrians can be divided into psychological force and physical force, as shown in formulas (3), (4), and (5). is the distance between the centroids of pedestrians. , is the sum of the radii of two pedestrians. When two pedestrians have no physical contact ( ), a psychological force to avoid approaching each other will be generated. The judgment of the physical force is determined by < ). When the distance between pedestrians is less than a certain distance ( > > ), a physical force will be generated. When ≤ When , no physical force is generated;; , is a parameter for adjusting the intensity of the interaction between pedestrians, , are the elastic coefficient and the sliding friction coefficient of the human body, respectively reflecting the coefficient of the human body's response to collision or approach and the coefficient of the frictional force generated during approach, is the direction of the force exerted by pedestrian j on target pedestrian i, is the tangential velocity difference between pedestrians.

[0122]

[0123] f ij psy = A i exp. [ ( r ij - d ij ) / B i ] n ij ⃗ （ 4 ）

[0124]

[0125] (11 - 1)

[0126] The repulsive force of the obstacle on the pedestrian is also divided into psychological force and physical force, as shown in formulas (6), (7), and (8), The radius of the pedestrian, is the distance between the centroid of the pedestrian and the obstacle. When there is no physical contact between the pedestrian and the obstacle ( < ), a psychological force to avoid approaching each other will be generated. The judgment of the physical force is determined by . When the distance between the pedestrian and the obstacle is less than a certain distance ( > ), then a physical force is generated, . A and B are parameters for adjusting the intensity of the wall's action on the pedestrian, , are the elastic coefficient and the sliding friction coefficient, is the direction of the force exerted by the obstacle on the pedestrian, is the unit vector in the tangential direction between the pedestrian and the obstacle.

[0127]

[0128] f io psy = A obs exp. [ ( r i - d io ) / B obs ] n io ⃗ （ 7 ）

[0129]

[0130] (11 - 2)

[0131] The interaction force between pedestrians and vehicles is mainly composed of an attenuation function and an anisotropy function, as shown in formulas (a), (b), and (c). A and B are parameters for adjusting the intensity of the vehicle's action on pedestrians. is the distance between the pedestrian and the vehicle. The anisotropy coefficient describes the relationship between the interaction force and the angle between the vehicle's driving direction and the pedestrian's movement direction. is a parameter for adjusting the anisotropy characteristics. represents the angle between the pedestrian's movement direction and the vehicle's driving direction, with a range from to .

[0132] ( , A, B)

[0133]

[0134]

[0135] 2. Improved social force model:

[0136] The current pedestrian - vehicle social force model mainly considers the influence of the distance and interaction angle between pedestrians and vehicles on the force exerted on pedestrians. However, in actual traffic scenarios, the speed difference between pedestrians and vehicles is often very significant, especially during the process of vehicle acceleration or emergency braking, and the required time and distance are quite different from the movement characteristics of pedestrians. Therefore, considering only the distance and angle is not sufficient to comprehensively describe the force exerted by vehicles on pedestrians. For example, under the same interaction distance and angle conditions, a vehicle with a low speed close to that of pedestrians has a completely different impact on pedestrians compared to a vehicle with a high speed.

[0137] Therefore, the influence of the speed difference is added to the calculation of the vehicle's force. Parameters for evaluating whether the speeds of a vehicle and a pedestrian exceed a set threshold. When the vehicle speed is within the acceptable range of the pedestrian, the force exerted by the vehicle on the pedestrian can ignore the influence of speed differences. However, when the vehicle speed exceeds this threshold, it means that the pedestrian may perceive potential safety risks in the interaction with the vehicle, which will then have a significant impact on their behavior. The speed difference between the pedestrian and the vehicle, and adjust the parameter that the speed difference affects the force.

[0138]

[0139]

[0140] (12)

[0141] Parameter optimization:

[0142] The parameters in the improved social force model 、 、 、 、 、 、 、u are optimized by the Bayesian optimization method; the specific Bayesian optimization method is as follows:

[0143] Z1. The Bayesian model is:

[0144] Parameter space , where ={ 、 、 、 、 、 、 、 }, each represents a parameter group and is used to perform one evaluation of the objective function;

[0145] The objective function F( ) = Y: Y is the output objective value after inputting the parameter group , and the output objective value Y is the average displacement error of the pedestrians; after a certain simulation process, the predicted trajectories of all pedestrians are obtained, and the average displacement error of the pedestrians is calculated based on the predicted trajectories and the true trajectories; the formula for the average displacement error is:

[0146] ;

[0147] is the x coordinate of the predicted position of pedestrian i at time t, is the y - coordinate of the predicted position of pedestrian i at time t, is the x - coordinate of the true position of pedestrian i at time t, is the y - coordinate of the true position of pedestrian i at time t, and N is the total number of pedestrians;

[0148] Acquisition function S: used to select the optimal parameter group for the next evaluation ;

[0149] ;

[0150] Dataset D: contains all the evaluated parameter groups and the corresponding objective values ;

[0151] , where n is the total number of evaluations;

[0152] Z2. Initialization:

[0153] Randomly select K parameter groups for the initial evaluation of the objective function to obtain the dataset D, where K is the number of sampling times for initialization;

[0154]

[0155] Z3. Iterative optimization:

[0156] In each iteration, Bayesian optimization performs the following steps:

[0157] Z31. Gaussian process modeling:

[0158] Assume that the objective function is continuous in the parameter space and satisfies the Gaussian process; this means that the value of the objective function at any position in the parameter space can be described by a mean function and a variance function to represent its distribution characteristics; specifically, the distribution form of the value of the objective function at a given position is expressed as:

[0159] ;

[0160] is the mean of all the objective function values that have been iterated so far, is the variance of all the objective function values that have been iterated so far; P() is the probability distribution, D t is the current dataset, x t+1 is the parameter group for the next iteration;

[0161] Z32. Select the next parameter group: In each iteration, Bayesian optimization selects the next group of parameter groups to be evaluated; through the acquisition function S, select the parameter with the maximum potential improvement :

[0162] ;

[0163] ;

[0164] is the optimal objective value iterated to the current step, is the objective function value of the parameter group;

[0165] Z33. Update the dataset: The selected parameter points are used to calculate the objective function value through the objective function, and the results are added to the existing training data; then, the updated dataset is used to refit the Gaussian process model to make more accurate predictions in the next iteration:

[0166]

[0167] Z34. Termination condition: Reach the maximum number of iterations or meet the convergence condition to obtain the optimal parameter group ;

[0168] ={ , , , , , , , }.

[0169] 3. Decision model

[0170] As Figure 1 shown, the decision-making method adopted by the decision model is specifically:

[0171] X1. Calculate the future conflict point between the pedestrian and the vehicle

[0172] X2. If there is a conflict point, calculate the time for the pedestrian and the vehicle to reach the conflict point according to the speed and direction of the pedestrian and the vehicle at the current moment, and determine the order of arrival;

[0173] X3. If the vehicle arrives at the conflict point first, then:

[0174] X31. Calculate the position of the pedestrian when the vehicle arrives at the conflict point, and determine the risk area and dangerous area of the vehicle at the conflict point according to the driving direction of the vehicle; the risk area is the area where there is a potential conflict between the pedestrian and the vehicle, and the dangerous area is the area where the conflict between the pedestrian and the vehicle cannot be avoided;

[0175] In a specific embodiment, there is a certain buffer distance between the risk area and the dangerous area, and the conflict has not reached an emergency level. The dangerous area directly leads to collisions or serious accidents.

[0176] AsFigure 3 As shown, assume the width of the vehicle is \(w\) and the length is \(l\). The dangerous area extends outward from the current vehicle width and length by a distance, and a buffer part with a length of is set in the direction of the vehicle speed, , where \(k\) is a hyperparameter, and \(v\) is the vehicle speed magnitude.

[0177] X32. Determine whether the future position of the pedestrian is within the risk area;

[0178] If the future position of the pedestrian is not within the risk area of the vehicle, continue to calculate the pedestrian's motion state according to the improved social force model;

[0179] If the pedestrian is in the risk area, further determine whether it is in the dangerous area;

[0180] If the pedestrian is in the risk area and not in the dangerous area, calculate the time difference between the pedestrian and the vehicle reaching the conflict point; if the time difference does not exceed the set threshold, the decision output is to slowly decelerate in the current direction; if the time difference exceeds the threshold, the decision output is to enter hesitation;

[0181] If the pedestrian is in the dangerous area, further determine the interaction angle between the pedestrian and the vehicle; when the interaction angle is a lateral interaction, the decision output is to suddenly stop in the current direction; when the interaction angle is a front - rear interaction, the decision output is to make a sharp turn;

[0182] X4. If the pedestrian reaches the conflict point first, then:

[0183] X41. Calculate the position of the vehicle when the person reaches the conflict point, and determine the risk area and dangerous area of the vehicle at the conflict point according to the vehicle's driving direction;

[0184] X42. Determine whether the vehicle is within the risk area;

[0185] If the pedestrian is not within the risk area, continue to calculate the motion state according to the social force model;

[0186] If the pedestrian is within the risk area, further determine whether the pedestrian is in the dangerous area or the risk area;

[0187] If the pedestrian is in the risk area and not in the dangerous area, calculate the time difference between the pedestrian and the vehicle reaching the conflict point; if the time difference does not exceed the set threshold, the output decision is to slowly accelerate in the current direction; if the time difference exceeds the threshold, the output is to enter the hesitation state;

[0188] If the pedestrian is in the dangerous area, judge according to the interaction angle; when the interaction angle is a lateral interaction, the output decision is to run and accelerate in the current direction; when the interaction angle is a front - rear interaction, the output decision is to make a sharp turn.

[0189] The hesitation state is a dynamic speed adjustment mechanism when pedestrians cannot clearly judge whether they can safely pass through the conflict point. When pedestrians clearly judge whether they can safely pass through the conflict point, they will temporarily maintain the current speed and wait to make a judgment when the distance from the vehicle is closer.

[0190] For the above-mentioned slow acceleration, the acceleration is less than the set upper limit value; for running acceleration, the acceleration is greater than the set upper limit value.

[0191] For any of the possible implementation methods as described above, a further implementation method is provided. The specific method of step S3 includes:

[0192] S31. Input the initial basic data of pedestrians and vehicles. The basic data includes the initial positions, speeds, time steps, and destinations of pedestrians and vehicles.

[0193] S32. Calculate the target position of the pedestrian at the current time step. The target position is determined according to the planned path between the actual position at the current time step and the destination.

[0194] S33. Input the current speed vector, current position, and target position of the pedestrian into the improved social force model to calculate the resultant force acting on the pedestrian.

[0195] S34. Enter the decision-making model and generate the decision output at the current time step based on the relative distance and speed between the pedestrian and the vehicle.

[0196] S35. Adjust the resultant force acting on the pedestrian according to the decision output obtained at the current time step.

[0197] S36. Adjust the speed of the pedestrian according to the resultant force adjusted in step S35, and calculate the actual position of the pedestrian at the next time step.

[0198] S37. Repeat steps S32 - S36 until all time steps are completed.

[0199] The interactive simulation process is as Figure 2 shown.

[0200] In a specific embodiment, in step S32, the Astar algorithm is used to calculate the target position of the pedestrian at the next time step. According to the Astar algorithm, by inputting the final destination position, the Astar algorithm will plan an optimal path (the shortest or with the lowest cost) for the pedestrian to reach the final destination from the current position. This path is composed of a series of discrete points, and each point can be regarded as a node on the path. The algorithm will output the target position (the next node towards which the pedestrian moves at the current moment).

[0201] In a specific embodiment, in step S35, the specific method for adjusting the resultant force on the pedestrian according to the decision output is as follows:

[0202] When the pedestrian chooses a sharp turn, the improved social force model adjusts the social force to a force perpendicular to the vehicle direction according to the relative position direction between the pedestrian and the vehicle. The direction of the force depends on the position of the pedestrian relative to the vehicle and is determined according to the direction to be avoided.

[0203] When the pedestrian chooses to accelerate slowly or run at an accelerated pace, the social force is adjusted to an acceleration force along the current speed direction, and the walking speed and acceleration upper limit of the pedestrian are adjusted to higher running speeds and accelerations.

[0204] When the pedestrian chooses to decelerate or make an emergency stop, the social force is adjusted to an acceleration force along the current reverse speed, and the acceleration of the pedestrian is replaced with a higher emergency stop acceleration.

[0205] When the pedestrian leaves the dangerous area but is still in the risk area, maintain the previous decision and continue to run, decelerate or turn until leaving the risk area.

[0206] The above higher running speeds and accelerations are all set with minimum limits according to test or statistical data, and the higher emergency stop acceleration is also set with a minimum limit according to test or statistical data.

[0207] An embodiment of the present invention provides a human-vehicle interaction simulation system based on an improved social force model. The system is used to implement the above method, and the system includes:

[0208] A social force calculation module, which calculates the social force received by the pedestrian according to the improved social force model.

[0209] A decision-making module, which is used to determine the behavior pattern when the pedestrian and the vehicle meet.

[0210] An interaction simulation module, which gives the initial basic data of the pedestrian and the vehicle, and uses the social force calculation module and the decision-making module to perform an interaction simulation on the movement of the pedestrian and the vehicle.

[0211] An embodiment of the present invention provides an application of a human-vehicle interaction simulation method based on an improved social force model. The method is applied to the scenario of mixed traffic of vehicles and pedestrians.

[0212] In a specific embodiment, the method is applied to an intersection without traffic lights; the intersection includes a crossroads and a multi-directional intersection.

[0213] When dealing with pedestrian-vehicle interactions, traditional social force models do not fully consider the influence of vehicle speed factors. In particular, there is a lag in pedestrian responses when the vehicle approaches or passes at high speed. By improving the social force model and combining the resultant force acting on the pedestrian with the dynamic changes in the environment, the present invention enhances the model's ability to describe the influence of vehicle speed and can more accurately simulate the force state of pedestrians, especially in complex traffic scenarios with a large speed difference between pedestrians and vehicles.

[0214] Optimization of the decision-making model based on pedestrian-vehicle interaction: In the process of pedestrian-vehicle interaction, traditional decision-making models usually ignore the complex interaction process between pedestrians and vehicles and the diversity of pedestrian decision-making behaviors, resulting in insufficient accuracy of the model in dealing with pedestrian-vehicle interaction scenarios. By designing a special decision-making module, the present invention generates reasonable risk avoidance decisions based on the relative speed, position, and distance between pedestrians and vehicles, significantly improving the safety and decision-making rationality of pedestrians in complex traffic environments.

[0215] Although several embodiments of the present invention have been given in this article, those skilled in the art should understand that the embodiments in this article can be changed without departing from the spirit of the present invention. The above embodiments are only exemplary and should not be used as a limitation of the scope of the rights of the present invention.

Claims

1. A human-vehicle interaction simulation method based on an improved social force model, characterized in that: The method comprises: S1. Construct an improved social force model, which is used to simulate the influence of driving force, human-vehicle interaction force, pedestrian-to-pedestrian interaction force, and obstacle repulsion on pedestrian travel speed; the improved social force model optimizes the influence of speed, distance, and interaction angle between people and vehicles on pedestrian travel; S2. Constructing a decision model, wherein the decision model is used to determine the behavior pattern of pedestrians and vehicles when they meet; the decision model optimizes the influence of speed, distance and interaction angle between pedestrians and vehicles on pedestrian decision-making; S3, given the initial basic data of pedestrians and vehicles, using the improved social force model of step S1 and the decision model of step S2, interactively simulating the movement of pedestrians and vehicles; In step S1, the improved social force model is expressed as: ； （2）； ； ； ； ； ； ； ； ； （11）； （12）； Where: The driving force of the destination on pedestrians, For the interaction between pedestrians, is the repulsive force of obstacles on pedestrians, is the interaction force between pedestrians and vehicles, is a random factor, N1, N2, and N are the total number of vehicles, obstacles, and pedestrians, respectively; , is the mass and speed of pedestrians, , They represent the pedestrian’s expected speed and expected direction of movement, respectively. is the interval time; They are the psychological and physical forces of interaction between pedestrians; is the distance between the centroids of pedestrians, , are two pedestrian radii When two pedestrians approach each other, a psychological force is generated to avoid each other; the physical force is determined by Decide, is a piecewise function. When the distance between pedestrians is less than a certain distance, > , physical force is generated; when ≤ hour, , no physical force is generated; , is a parameter used to adjust the intensity of interaction between pedestrians. , are the elastic coefficient and sliding friction coefficient of the human body, is the direction of the force exerted by pedestrian j on target pedestrian i, is the speed difference between pedestrians in the tangential direction; They are the psychological force and physical force of the obstacles’ repulsive force on pedestrians, is the pedestrian radius, is the distance between the center of mass of the pedestrian and the obstacle. When the pedestrian and the obstacle are close to each other, a psychological force is generated to avoid getting close to each other. The physical force is determined by Determine that when the distance between pedestrians and obstacles is less than a certain distance, > , physical force is generated; when ≤ hour, , no physical force is generated; , It is a parameter used to adjust the intensity of the obstacle’s effect on pedestrians. is the direction of the force acting on the obstacle. is the unit vector tangential to the pedestrian and the obstacle; is the velocity vector of pedestrian i; , Parameters used to adjust the intensity of the vehicle's impact on pedestrians, is the distance between the pedestrian and the vehicle; the anisotropic characteristics describe the relationship between the interaction force and the angle between the vehicle driving direction and the pedestrian moving direction. is the parameter to adjust the anisotropic characteristics, Indicates the angle between the pedestrian's movement direction and the vehicle's travel direction, ranging from arrive between; is the unit vector of pedestrian i pointing to the vehicle; Used to assess whether the speed difference between vehicles and pedestrians exceeds a set threshold Parameters, is the speed difference between pedestrians and vehicles, u is the parameter for adjusting the speed difference affecting the force, is the vehicle speed.

2. The human-vehicle interaction simulation method based on the improved social force model as claimed in claim 1, characterized in that: The parameters in the improved social force model , , , , , , , u is optimized by Bayesian optimization method; the Bayesian optimization method is as follows: Z1, the Bayesian model is: Parameter Space ,in ={ , , , , , , , }, each Represents a parameter group used to perform an objective function evaluation; Objective function F( ) = Y: Y is the input parameter group The output target value after the simulation is obtained, and the output target value Y is the average displacement error of the pedestrians; the predicted trajectories of all pedestrians are obtained after a certain simulation process, and the average displacement error of the pedestrians is calculated based on the predicted trajectory and the actual trajectory; the average displacement error The formula is: ； is the x-coordinate of the predicted position of pedestrian i at time t, is the y coordinate of the predicted position of pedestrian i at time t, is the x-coordinate of the real position of pedestrian i at time t, is the y coordinate of the real position of pedestrian i at time t, and N is the total number of pedestrians; Acquisition function S: used to select the optimal parameter set for the next evaluation ; ； Dataset D: contains all parameter sets that have been evaluated and the corresponding target value ; , n is the total number of evaluations; Z2, initialization: Randomly select K parameter groups for initial evaluation of the objective function to obtain the data set D, where K is the number of initialization samplings; Z3, iterative optimization: At each iteration, Bayesian optimization performs the following steps: Z31, Gaussian process modeling: Assume that the objective function is continuous in the parameter space and satisfies the Gaussian process; this means that the value of the objective function at any position in the parameter space can be described by a mean function and a variance function; specifically, the distribution form of the value of the objective function at a given position is expressed as: ； is the mean of all objective function values ​​that have been iterated so far, is the variance of all objective function values ​​that have been iterated; P() is the probability distribution, D t is the current data set, x t+1 is the parameter group for the next iteration; Z32, select the next parameter group: At each iteration, Bayesian optimization selects the next set of parameters to evaluate; through the acquisition function S, the parameters with the greatest potential improvement are selected : ； ； To iterate to the optimal target value of the current step, is the objective function value of the parameter group; Z33, Update the data set: The selected parameter points are passed through the objective function to calculate the objective function value, and the result is added to the existing training data; then, the updated data set is used to refit the Gaussian process model to make more accurate predictions in the next iteration: Z34, termination condition: reaching the maximum number of iterations or satisfying the convergence condition, and obtaining the optimal parameter set ; ={ 、 、 、 、 、 、 、 }。 3. The human-vehicle interaction simulation method based on the improved social force model as claimed in claim 1, characterized in that: In step S2, the decision-making method adopted by the decision model is specifically: X1. Calculate the future conflict point between pedestrians and vehicles X2. If there is a conflict point, calculate the time it takes for pedestrians and vehicles to reach the conflict point according to their current speeds and directions, and determine the order of arrival; X3. If the vehicle reaches the conflict point first, then: X31. Calculate the position of the pedestrian when the vehicle reaches the conflict point, and determine the risk area and the danger area of ​​the vehicle at the conflict point according to the driving direction of the vehicle; the risk area is an area where there is a potential conflict between the pedestrian and the vehicle, and the danger area is an area where the conflict between the pedestrian and the vehicle cannot be avoided; X32, determine whether the pedestrian's future position is within the risk area; If the pedestrian's future position is not within the risk area of ​​the vehicle, the pedestrian's motion state is calculated according to the improved social force model; If the pedestrian is in the risk area, it is further determined whether it is in the dangerous area; If the pedestrian is in the risk area and not in the danger area, the time difference between the pedestrian and the vehicle arriving at the conflict point is calculated; If the time difference does not exceed the set threshold, the decision output is to slow down in the current direction; If the time difference exceeds the threshold, the decision output is to enter hesitation; If the pedestrian is in the danger zone, the interaction angle between the pedestrian and the vehicle is further determined; when the interaction angle is lateral interaction, the decision output is an emergency stop in the current direction; when the interaction angle is front-to-back interaction, the decision output is a sharp turn; X4. If the pedestrian reaches the conflict point first, then: X41. Calculate the position of the vehicle when the person arrives at the conflict point, and determine the risk area and danger area of ​​the vehicle at the conflict point based on the vehicle's driving direction; X42. Determine whether the vehicle is located in the risk area; If the pedestrian is not in the risk area, the motion state calculation continues based on the social force model; If the pedestrian is in the risk area, it is further determined whether the pedestrian is in the danger area or the risk area; If the pedestrian is in the risk area and not in the dangerous area, the time difference between the pedestrian and the vehicle reaching the conflict point is calculated; If the time difference does not exceed the set threshold, the output decision is to slowly accelerate in the current direction; If the time difference exceeds the threshold, the output enters a hesitant state; If the pedestrian is in a dangerous area, a judgment is made based on the interaction angle; when the interaction angle is a lateral interaction, the output decision is to run and accelerate in the current direction; when the interaction angle is a forward and backward interaction, the output decision is a sharp turn.

4. The human-vehicle interaction simulation method based on the improved social force model as claimed in claim 1, characterized in that: The specific method of step S3 includes: S31, inputting initial basic data of pedestrians and vehicles, wherein the basic data includes initial positions, speeds, time steps, and destinations of pedestrians and vehicles; S32, calculating the target position of the pedestrian at the current time step, wherein the target position is determined according to the planned path between the actual position at the current time step and the destination; S33, inputting the pedestrian's current velocity vector, current position and target position into the improved social force model to calculate the resultant force on the pedestrian; S34, entering the decision model, and generating a decision output for the current time step based on the relative distance and speed between the pedestrian and the vehicle; S35, adjusting the resultant force on the pedestrian according to the decision output obtained at the current time step; S36, adjusting the speed of the pedestrian according to the resultant force adjusted in step S35, and calculating the actual position of the pedestrian in the next time step; S37. Repeat steps S32-S36 until all time steps are completed.

5. The human-vehicle interaction simulation method based on the improved social force model as claimed in claim 4, characterized in that: In step S35, the specific method for adjusting the resultant force on the pedestrian according to the decision output is: When pedestrians choose to make a sharp turn, the improved social force model adjusts the social force to a force perpendicular to the direction of the vehicle according to the relative position of the pedestrian and the vehicle. The direction of the force depends on the position of the pedestrian relative to the vehicle and is determined according to the direction to be avoided. When the pedestrian chooses to accelerate slowly or run, the social force is adjusted to the acceleration force along the current speed direction, and the pedestrian's walking speed and acceleration upper limit are adjusted to a higher running speed and acceleration; When the pedestrian chooses to slow down or stop suddenly, the social force is adjusted to the acceleration force along the current reverse speed, and the pedestrian's acceleration is replaced by a higher emergency stop acceleration; When the pedestrian leaves the danger zone but is still in the risk area, maintain the previous decision and continue running, slowing down or turning until leaving the risk area.

6. The human-vehicle interaction simulation method based on the improved social force model as claimed in claim 5, characterized in that: In step S32, the target position of the pedestrian is calculated using the Astar algorithm.

7. A human-vehicle interaction simulation system based on an improved social force model, characterized in that: The system is used to implement the method according to any one of claims 1 to 6, and the system includes: The social force calculation module calculates the social forces on pedestrians based on the improved social force model; A decision module is used to determine the behavior patterns of pedestrians and vehicles when they meet; The interactive simulation module is configured to interactively simulate the movement of pedestrians and vehicles by using the social force calculation module and the decision-making module given the initial basic data of pedestrians and vehicles.

8. An application of a human-vehicle interaction simulation method based on an improved social force model, characterized in that: The method as described in any one of claims 1 to 6 is applied to a scene where vehicles and pedestrians are crossing and mixing.

9. The application of the human-vehicle interaction simulation method based on the improved social force model as claimed in claim 8, characterized in that: The method is applied to an intersection without a traffic light; the intersection includes a cross intersection and a multi-directional intersection.

Images