Vehicle path planning method and system based on AI

Abstract

The invention discloses an AI-based vehicle path planning method and system, and relates to the technical field of vehicle path planning, and the method comprises the steps: obtaining the data of an included angle between the sun irradiation light and the vehicle advancing direction, the illumination intensity data, a preset road surface reflection coefficient, and the traffic duration data of a road section, and carrying out the analysis and calculation, thereby obtaining a dynamic risk index; the dynamic risk index is used for predicting the influence of sunlight of different road sections on the safety in the vehicle driving process; the total area and the pothole area of the road section, the total number of passing vehicles and the number of accident vehicles of the road section in one year, and the total area and the shadow area of the lane to be driven in the road section are analyzed and calculated, and a static risk index is obtained; according to the method, the dynamic risk index is constructed, so that the influence of the solar ray included angle, the illumination intensity and the road reflection coefficient on the driving safety is quantified, the dynamic risk assessment is realized in combination with the passing duration, and the risk early warning capability in a complex illumination scene is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle path planning, and in particular to an AI-based vehicle path planning method and system. Background Art

[0002] With the development of intelligent transportation systems, vehicle path planning technology has become an important means to improve travel efficiency and safety. Traditional path planning methods mainly rely on the shortest path generated by map APIs or real-time traffic data, and use algorithms to calculate distance, travel time, and congestion to achieve rapid route optimization. However, such methods usually only focus on the timeliness and convenience of the path, ignoring the potential threats to driving safety caused by environmental factors, such as dynamic risks such as the direction of sunlight and the intensity of road reflection, as well as static risks such as road quality and accident-prone areas. Therefore, existing technologies cannot effectively avoid safety hazards in complex scenarios, resulting in a high risk of accidents in planned paths.

[0003] In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0004] The purpose of this invention is to solve the problem that traditional path planning methods tend to ignore the potential threats of environmental factors to driving safety, cannot effectively avoid safety hazards in complex scenarios, and lead to a high risk of accidents in the planned path.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: an AI-based vehicle path planning method, comprising the following steps:

[0006] Step 1: Enter the departure and destination points, generate a preliminary route plan based on the map API, and divide the route plan into sections according to direction changes;

[0007] Step 2: Obtain data on the angle between the sun's rays and the vehicle's direction of travel, light intensity data, a preset road surface reflectivity, and road section travel time data for analysis and calculation to derive a dynamic risk index. The dynamic risk index is used to predict the impact of sunlight on vehicle driving safety in different road sections.

[0008] Step 3: Obtain the total area and pothole area of the road section, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in a year, the total area of the lanes to be driven and the shadow area in the road section, and analyze and calculate them to obtain a static risk index. The static risk index is used to reflect the probability of accidents occurring on the road section;

[0009] Step 4: Obtain traffic congestion index data and road friction coefficient data for the road section, and analyze and calculate them in combination with the dynamic risk index and static risk index to obtain a comprehensive safety index. The comprehensive safety index is used to reflect the safety of the vehicle's driving path plan;

[0010] Step 5: Obtain the comprehensive safety indexes of multiple groups of vehicle driving path plans and compare them, and select the vehicle driving path corresponding to the maximum comprehensive safety index as the optimal plan.

[0011] Furthermore, the process of obtaining the angle data between the sun's rays and the vehicle's travel direction is as follows:

[0012] S11. Collect multiple historical angles between sunlight and vehicle travel directions at different road sections as a dataset, randomly divide the dataset into a training set and a test set, and mark the corresponding time at each angle in the training set as a label;

[0013] S12. Constructing an angle judgment model based on a convolutional neural network, training the angle judgment model using a training set, and testing the angle judgment model using a test set to obtain a qualified angle judgment model;

[0014] S13. Obtain the vehicle's direction of travel on each road section through a path plan generated based on the map API, and input the vehicle's direction of travel into a qualified angle judgment model to determine the angle between the sunlight on the road section to be analyzed and the vehicle's direction of travel.

[0015] Furthermore, the calculation process of the dynamic risk index is as follows:

[0016] S21, obtaining angle data between the sun's rays and the vehicle's travel direction, light intensity data, a preset road surface reflection coefficient, and road section travel time data for analysis and calculation;

[0017] S22. Calculate the dynamic risk index DR of the i-th path plan according to the following formula: i :

[0018]

[0019] Where N is the number of road sections divided by the i-th path plan, θ k is the angle between the sun’s rays and the vehicle’s traveling direction on the kth road section, I k is the light intensity of the kth road segment, ρ k The road surface reflection coefficient preset for the kth road section, time k is the time it takes for a vehicle to pass the kth road section, δ is the preset dynamic risk conversion coefficient, and the larger the value of the dynamic risk index, the greater the impact of sunlight on vehicle driving safety;

[0020] S23. Obtain a preset dynamic risk threshold, compare the calculated dynamic risk index with the preset dynamic risk threshold, and when the dynamic risk index is greater than the preset dynamic risk threshold, remove the path plan corresponding to the dynamic risk index, and integrate the remaining path plans into a deepening plan set.

[0021] Furthermore, the calculation process of the static risk index is as follows:

[0022] S31. Obtain the total area and pothole area of the road section where the deepening plan is concentrated, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in one year, and the total area and shadow area of the lanes to be driven in the road section for analysis and calculation;

[0023] S32. Calculate the static risk index SR of the i-th path plan according to the following formula: i :

[0024]

[0025] Among them, a k is the pothole area of the kth road section, A k is the total area of the kth road section, α is the preset road section weight coefficient, m k is the number of vehicles involved in accidents on the kth road section in one year, M k is the total number of vehicles passing through the k-th road section in one year, β is the preset accident weight coefficient, r k is the shadow area of the lane to be driven in the kth road section, R k is the total area of the lane to be driven in the kth road section, γ is the preset shadow weight coefficient, and α+β+γ=1. The larger the value of the static risk index, the greater the possibility of an accident.

[0026] S33. Obtain a preset static risk threshold, compare the calculated static risk index with the preset static risk threshold, and when the static risk index is greater than the preset static risk threshold, remove the path plan corresponding to the static risk index, and integrate the remaining path plans into an optimized plan set.

[0027] Furthermore, the calculation process of the comprehensive safety index is as follows:

[0028] S41, obtaining traffic congestion index data and road friction coefficient data for the road section where the optimization plan is concentrated, and performing analysis and calculation based on the dynamic risk index and the static risk index;

[0029] S42. Calculate the comprehensive safety index CS of the i-th path plan according to the following formula: i :

[0030]

[0031] Among them, C k is the traffic congestion index of the kth road section, μ k is the road friction coefficient of the kth road section. The larger the value of the comprehensive safety index is, the higher the safety of the vehicle driving path plan is.

[0032] The present invention also provides an AI-based vehicle path planning system, comprising a path division unit, an AI dynamic analysis unit, an AI static analysis unit, a solution removal unit, a comprehensive analysis unit, and a path determination unit;

[0033] The route division unit is used to receive the departure and destination information input by the user, and generate a preliminary route plan based on the map API. At the same time, the route in the preliminary route plan is divided into sections according to the direction change;

[0034] The AI dynamic analysis unit is used to analyze and calculate the angle data between the sun's rays and the vehicle's travel direction, the light intensity data, the preset road surface reflection coefficient, and the travel time of the road section to obtain a dynamic risk index;

[0035] The AI static analysis unit is used to analyze and calculate the static risk index by obtaining the total area and pothole area of the road section, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in a year, and the total area and shadow area of the lanes to be driven in the road section;

[0036] The solution removal unit is used to determine whether the preliminary path solution in the path division unit meets the requirements by obtaining the comparison results of the dynamic risk index and the dynamic risk threshold, and the comparison results of the static risk index and the static risk threshold, and remove the path solution that does not meet the requirements;

[0037] The comprehensive analysis unit is used to obtain the traffic congestion index data and road friction coefficient data of the road section, and analyze and calculate the dynamic risk index and static risk index to obtain the comprehensive safety index;

[0038] The path determination unit is used to obtain the comprehensive safety indexes of multiple groups of vehicle driving path plans and compare them, and select the vehicle driving path corresponding to the maximum comprehensive safety index as the optimal plan.

[0039] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0040] This AI-based vehicle routing method and system constructs a dynamic risk index that not only quantifies the impact of sun angle, light intensity, and road reflectivity on driving safety, but also dynamically assesses risk by incorporating travel time, significantly improving risk warning capabilities in complex lighting scenarios. Furthermore, the static risk index innovatively integrates static factors such as pothole rate, historical accident rate, and shadow coverage, accurately reflecting the inherent risk level of a road section through weighted coefficients, effectively avoiding high-accident areas that are often overlooked by traditional methods. Furthermore, the comprehensive safety index utilizes a combined dynamic and static risk analysis, incorporating traffic congestion index and road friction coefficient to form a multi-dimensional safety evaluation system, enabling route selection to balance efficiency and safety. Predicting sun angle data using a convolutional neural network model not only improves the accuracy of environmental parameter acquisition but also enhances the system's adaptability to complex road conditions. A phased solution removal mechanism (deepening the solution set → optimizing the solution set) enables the gradual filtering of high-risk paths, conserving subsequent analysis and computing resources and improving vehicle routing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Shown is a schematic flow chart of the method of the present invention;

[0042] Figure 2 Shows a schematic diagram of the system structure of the present invention;

[0043] Figure 3 A schematic diagram showing the angle between the sun's rays and the vehicle's traveling direction according to the present invention is shown. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0045] Example 1:

[0046] like Figure 1 As shown, an AI-based vehicle path planning method first inputs the departure and destination, and generates multiple sets of preliminary path plans based on the map API. At the same time, the paths in the preliminary path plans are divided according to direction changes to form multiple road sections (for example, if the vehicle goes straight first, then turns left, and finally turns right to reach the destination, the path is divided into three sections, i.e., the straight line is the first section, the left turn is the second section, and the right turn is the third section).

[0047] Then, the angle data between the sun's rays and the vehicle's travel direction (the angle data is in radians), the light intensity data, the preset road surface reflection coefficient (the reflection coefficient for asphalt roads is 0.1-0.2, and the reflection coefficient for cement roads is 0.3-0.4), and the travel time data of the road section are obtained for analysis and calculation to obtain the dynamic risk index. The dynamic risk index is used to predict the impact of sunlight on vehicle driving safety in different road sections. It should be noted that the process of obtaining the angle data between the sun's rays and the vehicle's travel direction is as follows:

[0048] S11. Collect multiple historical angles between sunlight and vehicle travel directions at different road sections as a dataset, randomly divide the dataset into a training set and a test set, and mark the corresponding time at each angle in the training set as a label;

[0049] S12. Constructing an angle judgment model based on a convolutional neural network, training the angle judgment model using a training set, and testing the angle judgment model using a test set to obtain a qualified angle judgment model;

[0050] S13. Obtain the vehicle's direction of travel on each road section through a path plan generated based on the map API, and input the vehicle's direction of travel into a qualified angle judgment model to determine the angle between the sunlight on the road section to be analyzed and the vehicle's direction of travel.

[0051] The calculation process of the dynamic risk index is as follows:

[0052] S21, obtaining angle data between the sun's rays and the vehicle's travel direction, light intensity data, a preset road surface reflection coefficient, and road section travel time data for analysis and calculation;

[0053] S22. Calculate the dynamic risk index DR of the i-th path plan according to the following formula: i :

[0054]

[0055] Where N is the number of road sections divided by the i-th path plan, θ k is the angle between the sun’s rays and the vehicle’s traveling direction on the kth road section, I k is the light intensity of the kth road segment, ρ k The road surface reflection coefficient preset for the kth road section, time k is the time it takes for a vehicle to pass through the kth road section, δ is the preset dynamic risk conversion coefficient (used to ensure the consistency of the dimensions in the formula calculation). The larger the value of the dynamic risk index, the greater the impact of sunlight on vehicle driving safety;

[0056] S23. Obtain a preset dynamic risk threshold, compare the calculated dynamic risk index with the preset dynamic risk threshold, and when the dynamic risk index is greater than the preset dynamic risk threshold, remove the path plan corresponding to the dynamic risk index, and integrate the remaining path plans into a deepening plan set.

[0057] Then, the total area and pothole area of the road section, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in a year, the total area of the lanes to be driven in the road section and the shadow area (mainly the trees on the green belt and the buildings blocking the sunlight, and then forming shadows on the road surface) are obtained for analysis and calculation to obtain the static risk index. The static risk index is used to reflect the possibility of accidents in the road section. It should be added that the lanes in the driving section are divided into straight lanes, left-turn lanes and right-turn lanes, and the lanes to be driven in the road section refer to the driving lanes selected by the vehicle in the current section. For example, if the vehicle turns right in the next section, the vehicle needs to select the right-turn lane as the driving lane in the current section.

[0058] The calculation process of the static risk index is as follows:

[0059] S31. Obtain the total area and pothole area of the road section where the deepening plan is concentrated, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in one year, and the total area and shadow area of the lanes to be driven in the road section for analysis and calculation;

[0060] S32. Calculate the static risk index SR of the i-th path plan according to the following formula: i :

[0061]

[0062] Among them, a k is the pothole area of the kth road section, A k is the total area of the kth road section, α is the preset road section weight coefficient, m k is the number of vehicles involved in accidents on the kth road section in one year, M k is the total number of vehicles passing through the k-th road section in one year, β is the preset accident weight coefficient, r k is the shadow area of the lane to be driven in the kth road section, R k is the total area of the lane to be driven in the kth road section, γ is the preset shadow weight coefficient, and α+β+γ=1. The larger the value of the static risk index, the greater the possibility of an accident.

[0063] S33. Obtain a preset static risk threshold, compare the calculated static risk index with the preset static risk threshold, and when the static risk index is greater than the preset static risk threshold, remove the path plan corresponding to the static risk index, and integrate the remaining path plans into an optimized plan set.

[0064] Afterwards, the traffic congestion index data and road friction coefficient data of the road section are obtained, and combined with the dynamic risk index and static risk index for analysis and calculation to obtain a comprehensive safety index. The comprehensive safety index is used to reflect the safety of the vehicle's driving path plan.

[0065] The calculation process of the comprehensive safety index is as follows:

[0066] S41, obtaining traffic congestion index data and road friction coefficient data for the road section where the optimization plan is concentrated, and performing analysis and calculation based on the dynamic risk index and the static risk index;

[0067] S42. Calculate the comprehensive safety index CS of the i-th path plan according to the following formula: i :

[0068]

[0069] Among them, C k is the traffic congestion index of the kth road section, μ k is the road friction coefficient of the kth road section. The larger the value of the comprehensive safety index is, the higher the safety of the vehicle driving path plan is.

[0070] Finally, the comprehensive safety indexes of multiple groups of vehicle driving path plans are obtained and compared, and the vehicle driving path corresponding to the maximum comprehensive safety index is selected as the optimal plan.

[0071] By constructing a dynamic risk index, it not only quantifies the impact of sun angle, light intensity, and road reflectivity on driving safety, but also dynamically assesses risk by incorporating travel time, significantly improving risk warning capabilities in complex lighting scenarios. Furthermore, the static risk index innovatively incorporates static factors such as pothole rate, historical accident rate, and shadow coverage, accurately reflecting the inherent risk level of a road section through weighted coefficients, effectively avoiding high-accident areas that are often overlooked by traditional methods. Furthermore, the comprehensive safety index utilizes a combined dynamic and static risk analysis, incorporating traffic congestion index and road friction coefficient to form a multi-dimensional safety assessment system, enabling route selection to balance efficiency and safety. Using a convolutional neural network model to predict sun angle data not only improves the accuracy of environmental parameter acquisition but also enhances the system's adaptability to complex road conditions. A phased solution removal mechanism (deepening the solution set → optimizing the solution set) enables the gradual filtering of high-risk paths, conserving subsequent analysis and computing resources and improving vehicle route planning efficiency.

[0072] Example 2:

[0073] like Figure 2-3 As shown, an AI-based vehicle path planning system includes a path division unit, an AI dynamic analysis unit, an AI static analysis unit, a solution removal unit, a comprehensive analysis unit, and a path determination unit;

[0074] The path division unit is used to receive the departure and destination information input by the user, and generate multiple sets of preliminary path plans based on the map API. At the same time, the path in the preliminary path plan is divided according to the direction change to form multiple road segments;

[0075] The AI dynamic analysis unit is used to analyze and calculate the angle between the sun's rays and the vehicle's travel direction, light intensity data (measured by a light sensor), the preset road surface reflectivity, and the travel time of the road section to derive a dynamic risk index.

[0076] The AI static analysis unit is used to analyze and calculate the static risk index by obtaining the total area of the road section and the area of potholes (potholes are automatically detected through image recognition technology), the total number of vehicles passing through the road section and the number of vehicles involved in accidents in a year, and the total area of the lanes to be driven in the road section and the shadow area.

[0077] The solution removal unit is used to determine whether the preliminary path solution in the path division unit meets the requirements by obtaining the comparison results of the dynamic risk index and the dynamic risk threshold, and the comparison results of the static risk index and the static risk threshold, and remove the path solution that does not meet the requirements;

[0078] The comprehensive analysis unit is used to obtain the traffic congestion index data and road friction coefficient data of the road section, and analyze and calculate the dynamic risk index and static risk index to obtain the comprehensive safety index;

[0079] The path determination unit is used to obtain the comprehensive safety indexes of multiple groups of vehicle driving path plans and compare them, and select the vehicle driving path corresponding to the maximum comprehensive safety index as the optimal plan.

[0080] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0081] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by those skilled in the art according to actual conditions.

[0082] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A vehicle path planning method based on AI, characterized in that: The following steps are involved: Step 1: Enter the departure and destination points, generate a preliminary route plan based on the map API, and divide the route plan into sections according to direction changes; Step 2: Obtain data on the angle between the sun's rays and the vehicle's direction of travel, light intensity data, a preset road surface reflectivity, and road section travel time data for analysis and calculation to derive a dynamic risk index. The dynamic risk index is used to predict the impact of sunlight on vehicle driving safety in different road sections. Step 3: Obtain the total area and pothole area of the road section, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in a year, the total area of the lanes to be driven and the shadow area in the road section, and analyze and calculate them to obtain a static risk index. The static risk index is used to reflect the probability of accidents occurring on the road section; Step 4: Obtain traffic congestion index data and road friction coefficient data for the road section, and analyze and calculate them in combination with the dynamic risk index and static risk index to obtain a comprehensive safety index. The comprehensive safety index is used to reflect the safety of the vehicle's driving path plan; Step 5: Obtain the comprehensive safety indexes of multiple groups of vehicle driving path plans and compare them, and select the vehicle driving path corresponding to the maximum comprehensive safety index as the optimal plan.

2. The AI-based vehicle path planning method according to claim 1, characterized in that: The process of obtaining the angle data between the sun's rays and the vehicle's travel direction is as follows: S11. Collect multiple historical angles between sunlight and vehicle travel directions at different road sections as a dataset, randomly divide the dataset into a training set and a test set, and mark the corresponding time at each angle in the training set as a label; S12. Constructing an angle judgment model based on a convolutional neural network, training the angle judgment model using a training set, and testing the angle judgment model using a test set to obtain a qualified angle judgment model; S13. Obtain the vehicle's direction of travel on each road section through a path plan generated based on the map API, and input the vehicle's direction of travel into a qualified angle judgment model to determine the angle between the sunlight on the road section to be analyzed and the vehicle's direction of travel.

3. The AI-based vehicle path planning method according to claim 1, characterized in that: The calculation process of the dynamic risk index is as follows: S21, obtaining angle data between the sun's rays and the vehicle's travel direction, light intensity data, a preset road surface reflection coefficient, and road section travel time data for analysis and calculation; S22. Calculate the dynamic risk index DR of the i-th path plan according to the following formula: i : Where N is the number of road sections divided by the i-th path plan, θ k is the angle between the sun’s rays and the vehicle’s traveling direction on the kth road section, I k is the light intensity of the kth road segment, ρ k The road surface reflection coefficient preset for the kth road section, time k is the time it takes for a vehicle to pass the kth road section, δ is the preset dynamic risk conversion coefficient, and the larger the value of the dynamic risk index, the greater the impact of sunlight on vehicle driving safety; S23. Obtain a preset dynamic risk threshold, compare the calculated dynamic risk index with the preset dynamic risk threshold, and when the dynamic risk index is greater than the preset dynamic risk threshold, remove the path plan corresponding to the dynamic risk index, and integrate the remaining path plans into a deepening plan set.

4. The AI-based vehicle path planning method according to claim 1, characterized in that: The calculation process of the static risk index is as follows: S31. Obtain the total area and pothole area of the road section where the deepening plan is concentrated, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in one year, and the total area and shadow area of the lanes to be driven in the road section for analysis and calculation; S32. Calculate the static risk index SR of the i-th path plan according to the following formula: i : Among them, a k is the pothole area of the kth road section, A k is the total area of the kth road section, α is the preset road section weight coefficient, m k is the number of vehicles involved in accidents on the k-th road section in one year, M k is the total number of vehicles passing through the k-th road section in one year, β is the preset accident weight coefficient, r k is the shadow area of the lane to be driven in the kth road section, R k is the total area of the lane to be driven in the kth road section, γ is the preset shadow weight coefficient, and α+β+γ=1. The larger the value of the static risk index, the greater the possibility of an accident. S33. Obtain a preset static risk threshold, compare the calculated static risk index with the preset static risk threshold, and when the static risk index is greater than the preset static risk threshold, remove the path plan corresponding to the static risk index, and integrate the remaining path plans into an optimized plan set.

5. The AI-based vehicle path planning method according to claim 1, characterized in that: The calculation process of the comprehensive safety index is as follows: S41, obtaining traffic congestion index data and road friction coefficient data for the road section where the optimization plan is concentrated, and performing analysis and calculation based on the dynamic risk index and the static risk index; S42. Calculate the comprehensive safety index CS of the i-th path plan according to the following formula: i : Among them, C k is the traffic congestion index of the kth road section, μ k is the road friction coefficient of the kth road section. The larger the value of the comprehensive safety index is, the higher the safety of the vehicle driving path plan is.

6. An AI-based vehicle path planning system, characterized in that: It includes path division unit, AI dynamic analysis unit, AI static analysis unit, solution removal unit, comprehensive analysis unit, and path determination unit; The route division unit is used to receive the departure and destination information input by the user, and generate a preliminary route plan based on the map API. At the same time, the route in the preliminary route plan is divided into sections according to the direction change; The AI dynamic analysis unit is used to analyze and calculate the angle data between the sun's rays and the vehicle's travel direction, the light intensity data, the preset road surface reflection coefficient, and the travel time of the road section to obtain a dynamic risk index; The AI static analysis unit is used to analyze and calculate the static risk index by obtaining the total area and pothole area of the road section, the total number of vehicles passing through the road section and the number of vehicles involved in accidents in a year, and the total area and shadow area of the lanes to be driven in the road section; The solution removal unit is used to determine whether the preliminary path solution in the path division unit meets the requirements by obtaining the comparison results of the dynamic risk index and the dynamic risk threshold, and the comparison results of the static risk index and the static risk threshold, and remove the path solution that does not meet the requirements; The comprehensive analysis unit is used to obtain the traffic congestion index data and road friction coefficient data of the road section, and analyze and calculate the dynamic risk index and static risk index to obtain the comprehensive safety index; The path determination unit is used to obtain the comprehensive safety indexes of multiple groups of vehicle driving path plans and compare them, and select the vehicle driving path corresponding to the maximum comprehensive safety index as the optimal plan.

Images