Automatic driving operation risk assessment method and system, storage medium and electronic equipment

Abstract

The invention provides an automatic driving operation risk assessment method and system, a storage medium and electronic equipment. The automatic driving operation risk assessment method comprises the steps that all safety factors related to automatic driving in a target area road are collected; determining weight coefficients of all safety factors; calculating a risk score of the road in the target area according to the weight coefficient of the safety factor; and comparing the risk score of the target area road with a preset risk grade division threshold to obtain a risk grade of the target area road, and completing evaluation. According to the method, all road safety factors in the automatic driving scene are collected, a multi-dimensional scene evaluation risk grade index system is constructed according to different types of accident scene features of the vehicle to perform risk evaluation on the target area road, the evaluation result is more accurate, the applicability is wider, and the safety and robustness of an automatic driving system are further improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to an automatic driving operation risk assessment method, system, storage medium and electronic device. Background Art

[0002] With the improvement of driving automation, the complex driving scenarios and driving tasks encountered by autonomous vehicles are becoming more and more diverse. Driving risk assessment, as an important means to ensure and verify the safe operation of autonomous driving systems, has always been a research focus in the field of autonomous driving. During the operation of autonomous vehicles, scenario operation risk assessment is a key link to ensure the safe operation of vehicles in complex traffic environments.

[0003] Traditional empirical judgment methods and qualitative analysis methods still have limitations when dealing with emergencies, uncertain factors and complex dynamic scenarios, and perform poorly when faced with new or complex scenarios. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method, system, storage medium and electronic device for assessing the risks of autonomous driving operation. Through the road infrastructure in the autonomous driving vehicle operation scenario, the possibility of traffic accidents on road sections is quantitatively assessed. The system reflects the comprehensive impact of various factors such as highway infrastructure conditions, roadside environment, traffic operation conditions, etc. in the autonomous driving vehicle operation environment on the driving safety of autonomous driving vehicles. According to the evaluation and classification results, a safety improvement implementation plan and targeted treatment measures for high-risk sections are formulated in steps, which can be further improved to enhance the safety and robustness of the autonomous driving system.

[0005] In a first aspect, the present application provides a method, system, storage medium and electronic device for assessing the risk of autonomous driving operation, including:

[0006] Collect all safety factors involved in autonomous driving on the roads in the target area;

[0007] Determine the weight coefficients of all safety factors;

[0008] Calculating the risk score of the target area road according to the weight coefficient of the safety factor;

[0009] The risk score of the target area road is compared with a preset risk level classification threshold to obtain the risk level of the target area road, and the assessment is completed.

[0010] In some embodiments, the safety factors include:

[0011] Vehicle speed, traffic flow, lane width, radius of flat curves, curve safety, induction signs and markings, vibrating shoulder markings, road surface condition, slope, disturbance, roadside hazards, distance to roadside hazards, hard shoulder width, median type, number of single lanes, speed difference between different types of vehicles, intersection type, intersection angle, intersection safety, sight distance, channelization, speed management, access point type and auxiliary roads.

[0012] In some embodiments, determining the weight coefficients of all safety factors includes:

[0013] Standardize all the safety factors to obtain the index values ​​of all the safety factors;

[0014] According to the index values ​​of all the safety factors, the subjective weights and objective weights of all the safety factors are calculated respectively;

[0015] The weight coefficients of all safety factors are calculated according to the subjective weight and the objective weight.

[0016] In some embodiments, the subjective weights of all the safety factors are determined using a hierarchical analysis method.

[0017] In some embodiments, an entropy weight method is used to determine the objective weights of all the safety factors.

[0018] In some embodiments, all the safety factors are index-standardized to obtain index values ​​of all safety factors, including:

[0019] Divide all safety factors into positive safety factors and negative safety factors;

[0020] Performing positive indicator normalization on the positive safety factors;

[0021] The negative safety factors are subjected to negative index normalization to obtain index values ​​of all safety factors.

[0022] In some embodiments, calculating the risk score of the target area road according to the weight coefficient of the safety factor includes:

[0023] According to the formula:

[0024] PRS=PRS1+PRS2+...+PRS n =P1×S1×v1×q1×i1×w1+P2×S2×v2×q2×i2×w2+...+P n ×S n ×v n ×q n ×i n × n

[0025] Calculate the risk score PRS of the target area road;

[0026] Where PRS i Expressed as the safety risk value of different types of accidents; P i Indicates the probability coefficient of accidents caused by safety factors; S i Indicates the severity coefficient of the accident caused by safety factors; v i Indicates the influence coefficient of driving speed; q i represents the influence coefficient of traffic flow, i n represents the traffic composition influence coefficient, w n Represents the weather influence coefficient.

[0027] In a second aspect, an autonomous driving operation risk assessment system is provided, the system comprising:

[0028] A collection unit, used to collect all safety factors involved in autonomous driving on the roads in the target area;

[0029] A determination unit for determining weight coefficients of all safety factors;

[0030] A calculation unit, used for calculating the risk score of the target area road according to the weight coefficient of the safety factor;

[0031] The comparison unit is used to compare the risk score of the target area road with a preset risk level classification threshold to obtain the risk level of the target area road and complete the evaluation.

[0032] In a third aspect, a storage medium stores a computer program that can be executed by one or more processors and can be used to implement the autonomous driving operation risk assessment method as described in the first aspect above.

[0033] In a fourth aspect, an electronic device includes a memory and a processor, wherein a computer program is stored in the memory, and the memory and the processor are communicatively connected to each other. When the computer program is executed by the processor, the method for assessing the risk of autonomous driving operation as described in the first aspect above is executed.

[0034] The present application provides a method, system, storage medium and electronic device for risk assessment of autonomous driving operation, including: collecting all safety factors involved in autonomous driving on target area roads; determining the weight coefficients of all safety factors; calculating the risk score of the target area roads according to the weight coefficients of the safety factors; comparing the risk score of the target area roads with the preset risk level division threshold to obtain the risk level of the target area roads and complete the assessment. This application collects all road safety factors in the autonomous driving scenario, and constructs a multi-dimensional scenario assessment risk level indicator system to conduct risk assessment on target area roads according to the characteristics of different types of vehicle accident scenarios. The assessment results are more accurate and more widely applicable, further improving the safety and robustness of the autonomous driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0036] Figure 1 A flowchart of an autonomous driving operation risk assessment method provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of the structure of an autonomous driving operation risk assessment system provided in an embodiment of the present application;

[0038] Figure 3 A connection block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0040] Embodiment 1

[0041] Figure 1 A flowchart of a method for assessing risk of autonomous driving operation provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes:

[0042] S101, collecting all safety factors involved in autonomous driving on roads in the target area;

[0043] S102. Determine weight coefficients of all safety factors;

[0044] S103, calculating the risk score of the target area road according to the weight coefficient of the safety factor;

[0045] S104: Compare the risk score of the target area road with a preset risk level classification threshold to obtain the risk level of the target area road, and complete the assessment.

[0046] It should be noted that the present invention designs a risk assessment method and system for autonomous driving vehicle operation scenarios based on iRAP. According to the impact model of highway infrastructure and traffic conditions on determining the probability and possible severity of accidents, the traffic operation risk of autonomous driving vehicles in highway facility operation scenarios is quantitatively analyzed. Combined with traffic condition indicators, the scenario risk score is calculated according to the impact model, and this value is used to represent the degree of highway risk within the road section. In this study, the scenario risk level is divided into four levels, represented by Roman numerals Ⅰ, Ⅱ, Ⅲ, and Ⅳ from low to high. Based on comprehensive consideration of various factors, the calculated safety risk level will serve as the basic basis for dividing the safety risk level of autonomous driving scenario operations.

[0047] The iRAP-based assessment method does not require collision detection. It combines expert knowledge and accident data analysis to obtain safety factors (such as vehicles, obstacles, etc.), and then models them according to highway risk assessment technology to achieve risk assessment.

[0048] This study systematically calculates the risk by identifying the key causal factors that affect the risk, combining different types of accidents, road attributes and their related weights, and finally conducts a refined risk classification for the entire scenario. The evaluation process involves comprehensive consideration of multiple key factors, including road grade and road attributes, completeness of road facilities, changes in traffic flow and vehicle speed, and other traffic factors that affect the performance of the autonomous driving system in different scenarios. This evaluation method takes into account the mutual influence between traffic participants, such as potential conflicts between motor vehicles and non-motor vehicles, and the behavioral patterns of other traffic participants such as pedestrians.

[0049] In some embodiments, the safety factors include:

[0050] Vehicle speed, traffic flow, lane width, radius of flat curves, curve safety, induction signs and markings, vibrating shoulder markings, road surface condition, slope, disturbance, roadside hazards, distance to roadside hazards, hard shoulder width, median type, number of single lanes, speed difference between different types of vehicles, intersection type, intersection angle, intersection safety, sight distance, channelization, speed management, access point type and auxiliary roads.

[0051] It should be noted that through field investigation of the main static safety factors affecting road safety, such as the number of lanes, road flatness, type of median isolation zone, curvature, slope, road access points, intersection conditions, etc., the detailed records of each influencing factor and the compilation of an influencing factor record table are conducive to the subsequent calculation of the risk of autonomous driving operation. Continuous roads with unchanged or similar main influencing factors are divided into the same section and numbered. If the same influencing factor changes on the same section, it should be recorded according to the worst case. For example, if a non-motor vehicle isolation zone is missing in part of a section, then this section is recorded as "no non-motor vehicle isolation zone". Vehicle speed and traffic flow are important dynamic safety factors that affect safety risks. Vehicle speed can be determined according to the speed limit of the section, and traffic flow needs to be investigated on each divided section to obtain the average daily traffic flow of each section.

[0052] In some embodiments, determining the weight coefficients of all safety factors includes:

[0053] Standardize all the safety factors to obtain the index values ​​of all the safety factors;

[0054] According to the index values ​​of all the safety factors, the subjective weights and objective weights of all the safety factors are calculated respectively;

[0055] The weight coefficients of all safety factors are calculated according to the subjective weight and the objective weight.

[0056] In some embodiments, the subjective weights of all the safety factors are determined using a hierarchical analysis method.

[0057] In some embodiments, an entropy weight method is used to determine the objective weights of all the safety factors.

[0058] In some embodiments, the step of normalizing all the safety factors to obtain the index values ​​of all the safety factors includes:

[0059] Divide all safety factors into positive safety factors and negative safety factors;

[0060] Performing positive indicator normalization on the positive safety factors;

[0061] The negative safety factors are subjected to negative index normalization to obtain index values ​​of all safety factors.

[0062] It should be noted that when calculating the risk score, the basic attributes of the road need to be calculated using the corresponding risk coefficient. The risk coefficient value of each basic attribute is the weight determination part. This study uses the combined weighting method to determine the weights of various indicators.

[0063] Considering the shortcomings of a single weighting method, this study uses the Analytic Hierarchy Process (AHP) to determine the subjective weight, the entropy weight method (EWM) to determine the objective weight, and then combines the two weights through the ideal point method to determine the final weight. The specific steps are as follows:

[0064] First, all the safety factors are standardized. Specifically, the formula is used:

[0065]

[0066] Standardize the positive indicators of all positive safety factors;

[0067] Where, d ij is the index value after standardization; f ij is the jth safety factor value of the ith object; is the maximum value of the j-th safety factor level interval; It is the minimum value of the j-th safety factor level interval.

[0068] Using the formula:

[0069]

[0070] Standardize negative indicators of all negative safety factors;

[0071] Where, d ij is the index value after standardization; f ij is the jth safety factor value of the ith object; is the maximum value of the j-th safety factor level interval; It is the minimum value of the j-th safety factor level interval.

[0072] Finally, the index value with safety factors is obtained.

[0073] Then, according to the index value of the safety factor, the formula is:

[0074]

[0075]

[0076] G j =1-p ij

[0077]

[0078] Calculate the objective weight of each safety factor;

[0079] Where: pij is the proportion of the jth safety factor of object i in the entire evaluation system; H j is the entropy value of safety factor j; G is the information utility value of safety factor j; W j It is the objective weight of each safety factor.

[0080] Then, a hierarchical structure is constructed based on the safety factors, including the goal layer, the criterion layer, and the indicator layer;

[0081] The judgment matrix is ​​constructed for the criterion layer and the indicator layer respectively, which can be expressed as:

[0082]

[0083] Then, according to the judgment matrix between the evaluation indicators, the formula is adopted:

[0084]

[0085]

[0086] Each matrix is ​​checked for consistency and the consistency ratio R is calculated c To test the consistency of pairwise comparisons;

[0087] Where: max is the maximum eigenvalue of the matrix; n is the number of indicators, R c is the consistency ratio, I c is the consistency index, I r is the average random consistency index;

[0088] Then, according to the consistency test results, the formula is used:

[0089] w jk =A jk ·B jk

[0090]

[0091] Calculate the subjective weight of each safety factor;

[0092] Where: W jkis the weight of the kth indicator layer indicator of the jth criterion layer indicator, B jk is the weight of the kth indicator layer evaluated by the expert; A jk is the weight of the jth criterion level indicator evaluated by the expert, W h,k is the average weight of the kth indicator evaluated by experts.

[0093] Then, a combined weight is calculated according to the objective weight and the subjective weight as the final weight of each safety factor.

[0094] Specifically, in order to balance the influence of subjective and objective factors on the weight of safety factors, this application adopts the ideal point method for combined weighting. The principle is to minimize the deviation between the vector objective function and the problem under consideration, and to reduce the difference between the subjective and objective weights and the ideal point. According to the formula:

[0095]

[0096]

[0097] Calculate the final weight of all safety factors;

[0098] In the formula, w j is the subjective weight of the jth safety factor; W j is the objective weight of the jth safety factor; k j is the unnormalized combined weight, K j is the final weight after normalization. In the above formulas, i,j=1,2,…,n.

[0099] In some embodiments, calculating the risk score of the target area road according to the weight coefficient of the safety factor includes:

[0100] According to the formula:

[0101] PRS=PRS1+PRS2+...+PRS n =P1×S1×v1×q1×i1×w1+P2×S2×v2×q2×i2×w2+...+P n ×S n ×v n ×q n ×i n × n

[0102] Calculate the risk score PRS of the target area road;

[0103] Where PRS i Expressed as the safety risk value of different types of accidents; P i Indicates the probability coefficient of accidents caused by safety factors; Si Indicates the severity coefficient of the accident caused by safety factors; v i Indicates the influence coefficient of driving speed; q i represents the influence coefficient of traffic flow, i n represents the traffic composition influence coefficient, w n Represents the weather influence coefficient.

[0104] It should be noted that the safety risk score PRS for various types of accidents in autonomous driving on the target area roads is obtained by the sum of the safety risk values ​​of different types of accidents that may occur in autonomous driving on the target area roads, and the safety risk values ​​of different types of accidents are obtained by the product of the probability coefficient of the accident caused by safety factors, the severity coefficient of the accident caused by safety factors, the influence coefficient of driving speed, the influence coefficient of traffic flow, the influence coefficient of traffic composition and the influence coefficient of weather, and the probability coefficient of the accident caused by safety factors, the severity coefficient of the accident caused by safety factors, the influence coefficient of driving speed and the influence coefficient of traffic flow are obtained by the product of the final weights of the safety factors mentioned above.

[0105] It should be noted that the different coefficients of different types of accidents involve different safety factors. Taking the off-road accident risk type as an example, the safety factors involved in the probability coefficient of the accident include lane width, flat curve radius, curve safety, induction sign markings, shoulder vibration markings, road surface conditions, slope and disturbance, while in the intersection accident risk type, the safety factors involved in the probability coefficient of the accident include intersection type, intersection angle, intersection safety, slope, disturbance, sight distance, channelization and speed management. Therefore, the safety risk values ​​obtained for different types of accidents are different, and the final sum is obtained to obtain the safety risk score PRS of various types of accidents for autonomous driving on the target area roads.

[0106] It should be added that the traffic composition influence coefficient is: mainly considering the influence of the proportion of large vehicles on the risk level. When the proportion of large vehicles is 0%-10%, the influence coefficient is 1; as the proportion of large vehicles increases, the influence coefficient also increases.

[0107] The weather impact coefficient is: 1 in good weather and greater than 1 in bad weather.

[0108] In some embodiments, the step S104 compares the risk score of the target area road with a preset risk level classification threshold to obtain the risk level of the target area road, thereby completing the assessment.

[0109] It should be noted that the risk level of the target area road is divided according to the calculated risk score according to the risk score threshold shown in Table 1. Taking into account four major factors, including road grade and road flatness and other road facility factors, traffic flow and speed and other traffic participant factors, vehicle-to-non-vehicle conflict and other traffic participant factors, and climate and environmental factors, the safety risk assessment level of autonomous driving is divided into four categories based on the assessed safety risk level: safety risk I (low risk), safety risk II (general risk), safety risk III (higher risk), and safety risk IV (high risk).

[0110] Table 1

[0111] Security risk level Risk Score Ⅳ 2.5～5 Ⅲ 5～12.5 Ⅱ 12.5～22.5 Ⅰ ＞22.5

[0112] The risk score of the target area road is compared with a preset risk level classification threshold to obtain the safety risk level of the target area road, thereby completing the assessment.

[0113] In summary, the embodiment of the present application provides a method for assessing the risk of autonomous driving operation, including: collecting all safety factors involved in autonomous driving in target area roads; determining the weight coefficients of all safety factors; calculating the risk score of the target area roads according to the weight coefficients of the safety factors; comparing the risk score of the target area roads with the preset risk level division threshold to obtain the risk level of the target area roads and complete the assessment. This application collects all road safety factors in the autonomous driving scenario, and constructs a multi-dimensional scenario assessment risk level indicator system to conduct risk assessment on the target area roads according to the characteristics of different types of vehicle accident scenarios. The assessment results are more accurate and more widely applicable, further improving the safety and robustness of the autonomous driving system.

[0114] Embodiment 2

[0115] Based on the autonomous driving operation risk assessment method disclosed in the above embodiment of the present invention, Figure 2 Specifically disclosed is an autonomous driving operation risk assessment system that applies the autonomous driving operation risk assessment method.

[0116] like Figure 2 As shown, an embodiment of the present invention discloses an autonomous driving operation risk assessment system, the system comprising:

[0117] A collection unit 201 is used to collect all safety factors involved in autonomous driving on the target area road;

[0118] A determination unit 202, used to determine weight coefficients of all safety factors;

[0119] A calculation unit 203, configured to calculate a risk score of the target area road according to a weight coefficient of the safety factor;

[0120] The comparison unit 204 is used to compare the risk score of the target area road with a preset risk level classification threshold to obtain the risk level of the target area road and complete the evaluation.

[0121] The specific working processes of the collection unit 201, the determination unit 202, the calculation unit 203 and the comparison unit 204 in the autonomous driving operation risk assessment system disclosed in the above embodiment of the present invention can be referred to the corresponding content in the autonomous driving operation risk assessment method disclosed in the above embodiment of the present invention, and will not be repeated here.

[0122] In summary, the embodiment of the present application provides an autonomous driving operation risk assessment system, including: a collection unit 201, used to collect all safety factors involved in autonomous driving in the target area roads; a determination unit 202, used to determine the weight coefficients of all safety factors; a calculation unit 203, used to calculate the risk score of the target area roads according to the weight coefficients of the safety factors; a comparison unit 204, used to compare the risk score of the target area roads with a preset risk level division threshold, obtain the risk level of the target area roads, and complete the assessment. This application collects all road safety factors in the autonomous driving scenario, and constructs a multi-dimensional scenario evaluation risk level indicator system according to the characteristics of different types of vehicle accident scenarios to conduct risk assessment on the target area roads. The assessment results are more accurate and more applicable, further improving the safety and robustness of the autonomous driving system.

[0123] Embodiment 3

[0124] This embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App application store, etc., on which a computer program is stored. When the computer program is executed by a processor, the method steps of the first embodiment can be implemented, and this embodiment will not be repeated here.

[0125] Embodiment 4

[0126] Figure 3 A connection block diagram of an electronic device 300 provided in an embodiment of the present application, such as Figure 3As shown, the electronic device 300 may include: a processor 301 , a memory 302 , a multimedia component 303 , an input / output (I / O) interface 304 , and a communication component 305 .

[0127] The processor 301 is used to execute all or part of the steps in the method for assessing risk of autonomous driving operation in Example 1. The memory 302 is used to store various types of data, which may include, for example, instructions of any application or method in the electronic device, and data related to the application.

[0128] The processor 301 can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is used to execute the autonomous driving operation risk assessment method in the above-mentioned embodiment 1.

[0129] The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0130] The multimedia component 303 may include a screen and an audio component, the screen may be a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals. The received audio signal may be further stored in a memory or sent via a communication component. The audio component also includes at least one speaker for outputting audio signals.

[0131] The I / O interface 304 provides an interface between the processor 301 and other interface modules, which may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons.

[0132] The communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 305 can include: Wi-Fi module, Bluetooth module, NFC module.

[0133] In summary, the present application provides a method, system, storage medium and electronic device for risk assessment of autonomous driving operation, the method comprising: collecting all safety factors involved in autonomous driving in target area roads; determining the weight coefficients of all safety factors; calculating the risk score of the target area roads according to the weight coefficients of the safety factors; comparing the risk score of the target area roads with the preset risk level division threshold, obtaining the risk level of the target area roads, and completing the assessment. This application collects all road safety factors in the autonomous driving scenario, and constructs a multi-dimensional scenario assessment risk level index system according to the characteristics of different types of vehicle accident scenarios to conduct risk assessment on target area roads. The assessment results are more accurate and more applicable, further improving the safety and robustness of the autonomous driving system.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed method can also be implemented in other ways. The method embodiments described above are merely illustrative.

[0135] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0136] Although the implementation methods disclosed in this application are as above, the above contents are only the implementation methods adopted for facilitating the understanding of this application, and are not intended to limit this application. Any technician in the technical field to which this application belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in this application, but the scope of patent protection of this application shall still be based on the scope defined in the attached claims.

Claims

1. A method for assessing the risk of autonomous driving operation, characterized in that: The method comprises: Collect all safety factors involved in autonomous driving on the roads in the target area; Determine the weight coefficients of all safety factors; Calculating the risk score of the target area road according to the weight coefficient of the safety factor; The risk score of the target area road is compared with a preset risk level classification threshold to obtain the risk level of the target area road, and the assessment is completed.

2. The method according to claim 1, characterized in that: The safety factors include: Vehicle speed, traffic flow, lane width, radius of flat curves, curve safety, induction signs and markings, vibrating shoulder markings, road surface condition, slope, disturbance, roadside hazards, distance to roadside hazards, hard shoulder width, median type, number of single lanes, speed difference between different types of vehicles, intersection type, intersection angle, intersection safety, sight distance, channelization, speed management, access point type and auxiliary roads.

3. The method according to claim 1, characterized in that The weight coefficients of all safety factors are determined, including: Standardize all the safety factors to obtain the index values ​​of all the safety factors; According to the index values ​​of all the safety factors, the subjective weights and objective weights of all the safety factors are calculated respectively; The weight coefficients of all safety factors are calculated according to the subjective weight and the objective weight.

4. The method according to claim 3, characterized in that The analytic hierarchy process is used to determine the subjective weights of all the safety factors described.

5. The method according to claim 3, characterized in that: The entropy weight method is used to determine the objective weights of all the safety factors described.

6. The method according to claim 3, characterized in that The step of normalizing all the safety factors to obtain the index values ​​of all the safety factors includes: Divide all safety factors into positive safety factors and negative safety factors; Performing positive indicator normalization on the positive safety factors; The negative safety factors are subjected to negative index normalization to obtain index values ​​of all safety factors.

7. The method according to claim 1, characterized in that Calculating the risk score of the target area road according to the weight coefficient of the safety factor includes: According to the formula: PRS=PRS1+PRS2+...+PRS n =P1×S1×v1×q1×i1×w1+P2×S2×v2×q2×i2×w2+...+P n ×S n ×v n ×q n ×i n ×w n Calculate the risk score PRS of the target area road; Where PRS i Expressed as the safety risk value of different types of accidents; P i Indicates the probability coefficient of accidents caused by safety factors; S i Indicates the severity coefficient of the accident caused by safety factors; v i Indicates the influence coefficient of driving speed; q i represents the influence coefficient of traffic flow, i n represents the traffic composition influence coefficient, w n Represents the weather influence coefficient.

8. An autonomous driving operation risk assessment system, characterized in that: The system comprises: A collection unit, used to collect all safety factors involved in autonomous driving on the roads in the target area; A determination unit for determining weight coefficients of all safety factors; A calculation unit, used for calculating the risk score of the target area road according to the weight coefficient of the safety factor; The comparison unit is used to compare the risk score of the target area road with a preset risk level classification threshold to obtain the risk level of the target area road and complete the evaluation.

9. A storage medium, characterized in that: The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the automatic driving operation risk assessment method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a memory and a processor, the memory stores a computer program, the memory and the processor are communicatively connected to each other, and when the computer program is executed by the processor, the automatic driving operation risk assessment method as described in any one of claims 1 to 7 is executed.

Images