Road traffic organization plan optimization method and device based on behavioral characteristics requirements

Abstract

The present invention discloses a method and device for optimizing road traffic organization plans based on behavioral characteristics. The method includes the following steps: monitoring the driving status of motor vehicles in motor vehicle lanes to obtain driving parameter information of motor vehicles; monitoring the driving status of non-motor vehicles in non-motor vehicle lanes to obtain waiting position information of non-motor vehicles at intersections; calculating the average driving information and traffic density within a preset time period; constructing a parking demand prediction model for motor vehicles at intersections; constructing a road condition assessment model; and outputting a road condition evaluation score to optimize road traffic control. By performing real-time lane-by-lane monitoring of motor vehicle behavior on the road, more accurate vehicle condition data and road condition information can be obtained. By monitoring motor vehicles in different lanes, different time periods, and different intervals, the ability to analyze and identify road conditions can be expanded, more realistically tailored to the situation, and improving the safety, order, and smoothness of traffic organization.

Description

Technical Field

[0001] The present invention relates to the field of road traffic technology, and in particular to a method and device for optimizing a road traffic organization plan based on behavioral characteristic requirements. Background Art

[0002] Today's cities are facing increasingly severe traffic congestion. Urban traffic congestion, primarily manifested as road congestion, refers to a phenomenon where excessive vehicle density (the number of vehicles per unit distance on a road) impacts vehicle speed. To alleviate traffic congestion, local governments have implemented measures such as increasing investment in urban transportation infrastructure, establishing a multi-dimensional transportation system, implementing administrative and economic measures to curb traffic demand, and developing and improving public transportation.

[0003] In theory, urban traffic congestion is caused by traffic demand exceeding traffic supply. As cities develop, population and material production activities gather in large numbers due to the agglomeration effect. Intensive urban land development, coupled with the rapid growth of motorized travel driven by economic development and rising incomes, inevitably leads to a continuous increase in urban traffic demand, particularly on roads. However, the growth of urban traffic supply capacity exhibits a discontinuous and phased nature. Once built, transportation infrastructure is difficult to alter in the short term. Furthermore, the construction of transportation infrastructure often creates new sources of traffic. Therefore, traffic congestion is common and, to a certain extent, unavoidable. Optimizing road traffic organization involves scientifically and rationally allocating traffic to specific times, routes, vehicle types, and traffic flows within limited road space, ensuring that road traffic remains orderly and efficient.

[0004] Road traffic organization optimization involves scientifically and rationally dividing the use of roads by time, route, vehicle type, and direction within limited road space, ensuring that road traffic remains orderly and efficient. Traffic organization can be categorized into three aspects, based on the scope and content of research: micro-traffic organization, regional traffic organization, and macro-traffic organization. Micro-traffic organization is the foundation of regional traffic organization, while macro-traffic organization primarily refers to macro-traffic policies. Micro-traffic organization, the foundation of regional traffic organization, encompasses intersection traffic organization, road section traffic organization, and integrated intersection-section traffic organization. Currently, micro-traffic organization primarily focuses on intersection traffic organization.

[0005] Currently, road traffic organization optimization primarily considers indicators of traffic efficiency, such as road capacity and traffic safety. Systematic design rarely integrates the micro-characteristics of traffic participants' behavior and the impact of the environment on them. This can easily lead to optimized traffic organization designs that do not conform to the behavioral characteristics of traffic participants, potentially causing traffic disorder and a high incidence of traffic violations, impacting traffic capacity and posing a threat to traffic safety. Therefore, current road traffic organization optimization methods fail to fully and systematically consider factors influencing road traffic, making it impossible to effectively optimize road traffic plans.

[0006] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0007] In response to the problems in the related art, the present invention proposes a road traffic organization plan optimization method and device based on behavioral characteristic requirements to overcome the above-mentioned technical problems existing in the existing related art.

[0008] To this end, the specific technical solutions adopted in the present invention are as follows:

[0009] According to one aspect of the present invention, a method for optimizing a road traffic organization plan based on behavioral characteristics requirements is provided, the method comprising the following steps:

[0010] Monitor the driving status of motor vehicles on motorway lanes and obtain driving parameter information of motor vehicles;

[0011] Monitor the driving status of non-motor vehicles in non-motor vehicle lanes and obtain the waiting position information of non-motor vehicles at intersections;

[0012] Calculate the average driving information and traffic density within a preset time period;

[0013] Construct a prediction model for motor vehicle parking demand at intersections;

[0014] Construct a road condition assessment model;

[0015] Output road condition evaluation scores to optimize road traffic control.

[0016] Furthermore, the device for monitoring the driving status of motor vehicles in the motor vehicle lane includes a number of high-definition cameras and speed radars arranged at equal intervals. The high-definition cameras and speed radars divide the motor vehicle lane into a number of sections longitudinally, and the motor vehicle lane includes a right-turn lane, a straight lane and a left-turn lane arranged horizontally, and a speed radar is separately installed in each lane.

[0017] Furthermore, the non-motor vehicle lane includes a driving area and an illegal parking area set at an intersection. Non-motor vehicles that are located in the illegal parking area and remain parked are regarded as illegally parked vehicles, and high-definition cameras at the intersection are used to monitor and record the number of illegally parked vehicles.

[0018] Furthermore, the driving parameter information includes the driving speed and headway of the motor vehicle measured by a speed measuring radar.

[0019] Furthermore, the calculation of the average speeds of several motor vehicles and the traffic density within a preset time period of a single speed measurement interval of a motor vehicle lane after calibration includes the following steps:

[0020] Monitor the driving status of motor vehicles on the motor vehicle lane and obtain driving parameter information of the motor vehicles. The driving parameter information includes the calibrated driving speed and headway of the motor vehicle measured and calculated using the speed measurement radar and the navigation software inside the vehicle, and calculate the average driving speed and headway of several motor vehicles within a preset time period in a single speed measurement interval of the calibrated motor vehicle lane. The calculation formula is as follows:

[0021]

[0022] Where v is the average speed of several motor vehicles in a preset time period in a single speed measurement interval of the motor vehicle lane after calibration, It represents the average speed of several vehicles in a single lane in section AB, v m V is the average speed value measured by the vehicle's internal navigation software and filtered by the speed limit value of the current lane. i B-A represents the measured speed of vehicle i, n represents the total number of vehicles in interval AB, and the mean headway time is calculated in the same way as above;

[0023] Calculate the traffic density of a single lane within a preset time period of a single speed measurement interval on a moving lane using the following formula:

[0024]

[0025] Among them, K(t) represents the traffic density, t0 represents the monitoring start time, t represents the monitoring duration, A represents the starting position of the interval, B represents the end position of the interval, Q A (t) represents the number of vehicles entering from A at time t, Q B (T) represents the number of vehicles leaving from B at time t, L represents the interval distance, and E(t) represents the number of vehicles in the interval AB at time t. The formula is E(t)=E(t0)+Q A (t)-Q B (t), E(t0) represents the initial number of vehicles between the observation interval AB at the observation start time t=t0.

[0026] Furthermore, the calculation formula for constructing the intersection motor vehicle parking demand prediction model is as follows:

[0027] P mt =P m(t-1) +∑B m (δ t -λ t ),t=1,2,…;

[0028] P m0 =∑B m η;

[0029] Among them, P m represents the parking position requirement of lane m in the motorway, P mt represents the parking position demand in lane m of the motorway within time period t, P m0 Indicates the initial moment of the vehicle being parked, B m represents the length scale of m lanes, δ t represents the traffic arrival volume generated in time period t, λ t represents the traffic departure volume generated in time period t, and η represents the initial number of parked vehicles per unit land area.

[0030] Furthermore, the construction of the road condition assessment model includes the following steps:

[0031] The mean value of the driving parameter information, traffic density, parking demand information at intersections, and the number of illegally parked non-motor vehicles are used as road information data;

[0032] Analyzing and processing the internal structural characteristics of the road information data to establish a road information set;

[0033] Analyze the information change scenarios in the road information set and extract dynamic indicators of road conditions;

[0034] Using the road condition dynamic indicators as Bayesian network nodes, determining the Bayesian network structure, and then using the mutual information method to sort the relevance of the road condition dynamic indicators and screen the Bayesian network nodes;

[0035] Input the Bayesian network node parameters to obtain the road condition assessment model.

[0036] Furthermore, the specific calculation method for ranking the relevance of the road condition dynamic indicators using the mutual information method is:

[0037]

[0038] Where I(X; Y) is the joint probability distribution of indicator X and indicator Y, and the P(x) and P(y) distributions represent the marginal probability distributions of indicator X and indicator Y. The larger the I(X; Y) value, the stronger the correlation and the higher the ranking.

[0039] Furthermore, if the I(X; Y) value is less than or equal to 0.04, it indicates that the road traffic condition is smooth; if the I(X; Y) value is greater than 0.04 and less than 0.06, it indicates that the road condition is general with slight or partial traffic jam; if the I(X; Y) value is greater than or equal to 0.06, it indicates that the road is congested.

[0040] According to another aspect of the present invention, there is also provided a device for optimizing a road traffic organization plan based on behavioral characteristics requirements, the device comprising a speed measuring radar, a high-definition camera, and a receiving control center;

[0041] Among them, speed radars and high-definition cameras are set at equal distances on the side of the motor vehicle road and at intersections.

[0042] The beneficial effects of the present invention are as follows: by carrying out real-time monitoring of the behavior of motor vehicles on the road in lanes, it is possible to ensure the acquisition of more accurate vehicle condition data and road condition information; by monitoring motor vehicles in different lanes, different time periods and different intervals, it is possible to expand the analysis and identification capabilities of road conditions, that is, by integrating the driving speed and headway of vehicles in multiple intervals, it is possible to analyze the road conditions before the vehicle enters the intersection, and judge the real-time road conditions based on the behavioral characteristics of the vehicle; and when entering the intersection, by introducing the intersection motor vehicle parking demand prediction model, it is possible to accurately judge the traffic congestion situation at the intersection in combination with the parking demand situation before the intersection, further improving the ability and accuracy of road condition analysis, facilitating targeted optimization and resolution of traffic organization, and at the same time introducing non-motor vehicle monitoring, expanding the scope of analysis of road conditions, increasing the impact of non-motor vehicles on road conditions, being more in line with reality, and improving the safety, orderliness and smoothness of traffic organization. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 1 is a flow chart of a method for optimizing a road traffic organization plan based on behavioral characteristics according to an embodiment of the present invention;

[0045] Figure 2 2 is a schematic diagram of the structure of a device for optimizing a road traffic organization plan based on behavioral characteristic requirements according to an embodiment of the present invention.

[0046] In the picture:

[0047] 1. Speed ​​measuring radar; 2. High-definition camera; 3. Receiving control center. DETAILED DESCRIPTION

[0048] According to one embodiment of the present invention, Figure 1 As shown, a road traffic organization scheme optimization method based on behavioral characteristic requirements is provided, and the method includes the following steps:

[0049] S1. Monitor the driving status of motor vehicles on the motorway and obtain driving parameter information of the motor vehicles;

[0050] Among them, the device for monitoring the driving status of motor vehicles in the motor vehicle lane includes several high-definition cameras and speed radars arranged at equal intervals. The high-definition cameras and speed radars divide the motor vehicle lane into several sections longitudinally, and the motor vehicle lane includes a right-turn lane, a straight lane and a left-turn lane arranged horizontally, and a speed radar is separately installed in each lane.

[0051] S2. Monitor the driving status of non-motor vehicles in the non-motor vehicle lane and obtain the waiting position information of non-motor vehicles at the intersection;

[0052] Among them, the non-motor vehicle lane includes a driving area and an illegal parking area set up at the intersection. Non-motor vehicles that are located in the illegal parking area and remain parked are regarded as illegally parked vehicles, and high-definition cameras at the intersection are used to monitor and record the number of illegally parked vehicles.

[0053] S3. Calculate the average value of driving information and traffic density within a preset time period;

[0054] The driving parameter information includes the motor vehicle's driving speed and headway time measured and calculated using a speed radar and navigation software inside the vehicle;

[0055] The calculation of the mean value of driving information and the traffic flow density within the preset time period includes the following steps:

[0056] S31. Calculate the average speed and headway of several motor vehicles within a preset time period in a single speed measurement interval of the calibrated motor vehicle lane using the following formula:

[0057] Monitor the driving status of motor vehicles on the motor vehicle lane and obtain driving parameter information of the motor vehicles. The driving parameter information includes the calibrated driving speed and headway of the motor vehicle measured and calculated using the speed measurement radar and the navigation software inside the vehicle, and calculate the average driving speed and headway of several motor vehicles within a preset time period in a single speed measurement interval of the calibrated motor vehicle lane. The calculation formula is as follows:

[0058]

[0059] Where v is the average speed of several motor vehicles in a preset time period in a single speed measurement interval of the motor vehicle lane after calibration, It represents the average speed of several vehicles in a single lane in section AB, v m V is the average speed value measured by the vehicle's internal navigation software and filtered by the speed limit value of the current lane. i B-A represents the measured speed of vehicle i, n represents the total number of vehicles in interval AB, and the mean headway time is calculated in the same way as above;

[0060] S32. Calculate the traffic density of a single lane within a preset time period of a single speed measurement interval of a moving lane. The calculation formula is as follows:

[0061]

[0062] Among them, K(t) represents the traffic density, t0 represents the monitoring start time, t represents the monitoring duration, A represents the starting position of the interval, B represents the end position of the interval, Q A (t) represents the number of vehicles entering from A at time t, Q B (T) represents the number of vehicles leaving from B at time t, L represents the interval distance, and E(t) represents the number of vehicles in the interval AB at time t. The formula is E(t)=E(t0)+Q A (t)-Q B (t), E(t0) represents the initial number of vehicles between the observation interval AB at the observation start time t=t0.

[0063] S4. Constructing a prediction model for parking demand of motor vehicles at intersections;

[0064] The calculation formula for constructing the intersection motor vehicle parking demand prediction model is as follows:

[0065] P mt =P m(t-1) +∑B m (δ t -λ t ),t=1,2,…;

[0066] P m0 =∑B m η;

[0067] Among them, P m represents the parking position requirement of lane m in the motorway, P mt represents the parking position demand in lane m of the motorway within time period t, P m0 Indicates the initial moment of the vehicle being parked, B mrepresents the length scale of m lanes, δ t represents the traffic arrival volume generated in time period t, λ t represents the traffic departure volume generated in time period t, and η represents the initial number of parked vehicles per unit land area.

[0068] S5. Constructing a road condition assessment model;

[0069] The construction of the road condition assessment model includes the following steps:

[0070] S51, taking the mean value of the driving parameter information, the traffic density, the parking demand information at the intersection, and the number of illegally parked non-motor vehicles as road information data;

[0071] S52: Analyze and process the internal structural features of the road information data to establish a road information set;

[0072] S53, analyzing information change scenarios in the road information set and extracting dynamic indicators of road conditions;

[0073] S54, using the road condition dynamic indicators as Bayesian network nodes, determining the Bayesian network structure, and then using the mutual information method to sort the relevance of the road condition dynamic indicators and screen the Bayesian network nodes;

[0074] S55. Input the Bayesian network node parameters to obtain a road condition assessment model.

[0075] The specific calculation method for ranking the relevance of the road condition dynamic indicators using the mutual information method is:

[0076]

[0077] Where I(X; Y) is the joint probability distribution of indicator X and indicator Y, and the P(x) and P(y) distributions represent the marginal probability distributions of indicator X and indicator Y. The larger the I(X; Y) value, the stronger the correlation and the higher the ranking.

[0078] S6. Output road condition evaluation scores and optimize road traffic control.

[0079] Among them, the I(X; Y) value less than or equal to 0.04 indicates that the road traffic condition is smooth, the I(X; Y) value greater than 0.04 and less than 0.06 indicates that the road condition is general with slight or partial traffic jams, and the I(X; Y) value greater than or equal to 0.06 indicates that the road is congested.

[0080] According to another embodiment of the present invention, Figure 2As shown, a road traffic organization plan optimization device based on behavioral characteristics is also provided, which includes a speed radar 1, a high-definition camera 2 and a receiving control center 3;

[0081] The speed radar 1 and the high-definition camera 2 are arranged at equal distances on the side of the motor vehicle road and at the intersection.

[0082] In summary, the above-mentioned technical solutions of the present invention enable real-time lane-by-lane monitoring of motor vehicle behavior on the road, ensuring the acquisition of more accurate vehicle condition data and road condition information. By monitoring motor vehicles in different lanes, time periods, and intervals, the ability to analyze and identify road conditions can be expanded. Furthermore, the vehicle's internal navigation software is utilized to measure and calculate calibrated motor vehicle speeds and headway times. This is essentially based on the average speed value measured by the vehicle's internal navigation software and filtered by the speed limit of the current lane. That is, the speeds and headway times of vehicles in multiple intervals are calculated by comprehensively considering various factors. This allows for road condition analysis before a vehicle enters an intersection, determining real-time road conditions based on the vehicle's behavioral characteristics. Furthermore, when entering an intersection, the introduction of an intersection parking demand prediction model allows for accurate determination of intersection congestion conditions based on pre-intersection parking demand, further improving the ability and accuracy of road condition analysis and facilitating targeted optimization and resolution of traffic organization. Furthermore, the introduction of non-motor vehicle monitoring expands the scope of road condition analysis, increases the impact of non-motor vehicles on road conditions, and provides a more realistic approach to improving safe, orderly, and smooth traffic organization.

[0083] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A road traffic organization scheme optimization method based on behavioral characteristics requirements, characterized by: The method comprises the following steps: Monitor the driving status of motor vehicles on the motor vehicle lane and obtain driving parameter information of the motor vehicles. The driving parameter information includes the calibrated driving speed and headway of the motor vehicle measured and calculated using the speed measurement radar and the navigation software inside the vehicle, and calculate the average driving speed and headway of several motor vehicles within a preset time period in a single speed measurement interval of the calibrated motor vehicle lane. The calculation formula is as follows: Where v is the average speed of several motor vehicles in a preset time period in a single speed measurement interval of the motor vehicle lane after calibration, It represents the average speed of several vehicles in a single lane in section AB, v m V is the average speed value measured by the vehicle's internal navigation software and filtered by the speed limit value of the current lane. i B-A represents the measured speed of vehicle i, n represents the total number of vehicles in interval AB, and the mean headway time is calculated in the same way as above; Calculate the traffic density of a single lane within a preset time period of a single speed measurement interval on a moving lane using the following formula: Among them, K(t) represents the traffic density, t0 represents the monitoring start time, t represents the monitoring duration, A represents the starting position of the interval, B represents the end position of the interval, Q A (t) represents the number of vehicles entering from A at time t, Q B (T) represents the number of vehicles leaving from B at time t, L represents the interval distance, and E(t) represents the number of vehicles in the interval AB at time t. The formula is E(t)=E(t0)+Q A (t)-Q B (t), E(t0) represents the initial number of vehicles between the observation interval AB at the observation start time t = t0; Monitor the driving status of non-motor vehicles in non-motor vehicle lanes and obtain waiting position information of non-motor vehicles at intersections; Calculate the average driving information and traffic density within a preset time period; Construct a prediction model for the parking demand of motor vehicles at an intersection. The calculation formula for constructing the prediction model for the parking demand of motor vehicles at an intersection is as follows: P mt =P m(t-1) +∑B m (d t -l t ),t=1,2,…; P m0 =∑B m or; Among them, P m represents the parking position requirement of lane m in the motorway, P mt represents the parking position demand in lane m of the motorway within time period t, P m0 Indicates the initial moment of the vehicle being parked, B m represents the length scale of m lanes, δ t represents the traffic arrival volume generated in time period t, λ t represents the traffic departure volume generated in time period t, and η represents the initial number of parked vehicles per unit land area; Construct a road condition assessment model; Output road condition evaluation scores to optimize road traffic control; The construction of the road condition assessment model comprises the following steps: The mean value of the driving parameter information, traffic density, parking demand information at intersections, and the number of illegally parked non-motor vehicles are used as road information data; Analyzing and processing the internal structural features of the road information data to establish a road information set; Analyze the information change scenarios in the road information set and extract dynamic indicators of road conditions; Using the road condition dynamic indicators as Bayesian network nodes, determining the Bayesian network structure, and then using the mutual information method to sort the relevance of the road condition dynamic indicators and screen the Bayesian network nodes; Input the Bayesian network node parameters to obtain the road condition assessment model.

2. The method for optimizing road traffic organization scheme based on behavioral characteristics requirements according to claim 1 is characterized in that: The device for monitoring the driving status of motor vehicles in the motor vehicle lane includes a number of high-definition cameras and speed radars arranged at equal intervals. The high-definition cameras and speed radars divide the motor vehicle lane into a number of sections longitudinally, and the motor vehicle lane includes a right-turn lane, a straight lane and a left-turn lane arranged horizontally, and a speed radar is separately installed in each lane.

3. The method for optimizing road traffic organization scheme based on behavioral characteristics requirements according to claim 2 is characterized in that: The non-motor vehicle lane includes a driving area and an illegal parking area set at an intersection. Non-motor vehicles that are located in the illegal parking area and remain parked are considered illegally parked vehicles, and high-definition cameras at the intersection are used to monitor and record the number of illegally parked vehicles.

4. The method for optimizing road traffic organization scheme based on behavioral characteristics requirements according to claim 3 is characterized in that: The specific calculation method for ranking the relevance of the road condition dynamic indicators using the mutual information method is: Where I(X; Y) is the joint probability distribution of indicator X and indicator Y, and the P(x) and P(y) distributions represent the marginal probability distributions of indicator X and indicator Y. The larger the I(X; Y) value, the stronger the correlation and the higher the ranking.

5. The method for optimizing road traffic organization scheme based on behavioral characteristics requirements according to claim 4 is characterized in that: If the I(X; Y) value is less than or equal to 0.04, it indicates that the road traffic condition is smooth; if the I(X; Y) value is greater than 0.04 and less than 0.06, it indicates that the road condition is general with slight or partial traffic jam; if the I(X; Y) value is greater than or equal to 0.06, it indicates that the road is congested.

6. A device for optimizing a road traffic organization plan based on behavioral characteristics, for implementing the method for optimizing a road traffic organization plan based on behavioral characteristics according to any one of claims 1 to 5, characterized in that: The device comprises a speed measuring radar (1), a high-definition camera (2) and a receiving control center (3); The speed measuring radar (1) and the high-definition camera (2) are arranged at equal distances on the side of the motor vehicle road and at the intersection.

Images