Traffic risk assessment method and device

Abstract

The application provides a traffic risk assessment method and device, and belongs to the field of intelligent traffic. The traffic risk assessment method comprises the following steps: describing the characteristics of a traffic scene by running a design domain element, determining the type of the traffic scene according to the characteristics of the traffic scene; determining a traffic participant in the traffic scene according to the type of the traffic scene; obtaining the motion information of the traffic participant, and respectively calculating the traffic scene element complexity and the potential collision degree of the traffic participant according to the motion information of the traffic participant; and calculating a dynamic expected safety index according to the traffic scene element complexity and the potential collision degree of the traffic participant. The application can evaluate traffic risk and improve the road traffic safety.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation, and in particular to a method and apparatus for assessing traffic risks. Background Technology

[0002] With rapid urbanization and the increasing motorization of roads, people's lives have become more convenient. However, the explosive growth of motor vehicles has also brought about safety issues such as traffic congestion and accidents. Road traffic accidents are the leading cause of death across all age groups. Therefore, accurately and effectively predicting future traffic accident risks can help individuals choose safer routes and options for their travel. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a traffic risk assessment method and apparatus that can evaluate traffic risks and improve road traffic safety.

[0004] To address the aforementioned technical problems, embodiments of the present invention provide the following technical solutions:

[0005] On one hand, embodiments of the present invention provide a traffic risk assessment method, including:

[0006] The characteristics of a traffic scenario are described by running design domain elements, and the type of traffic scenario is determined based on the characteristics of the traffic scenario.

[0007] The traffic participants in the traffic scenario are determined based on the type of traffic scenario.

[0008] Obtain motion information of traffic participants, and calculate the complexity of traffic scene elements and the potential collision degree of traffic participants based on the motion information of traffic participants;

[0009] The dynamic expected safety index is calculated based on the complexity of traffic scene elements and the potential collision levels of traffic participants.

[0010] In some embodiments, the method further includes:

[0011] When the dynamic expected safety index is greater than or less than a preset threshold, traffic participants are reminded to take evasive action.

[0012] In some embodiments, the operational design domain elements include: road structure, traffic participants, infrastructure, environmental and weather conditions.

[0013] In some embodiments, the method further includes obtaining a traffic risk assessment benchmark value under a benchmark traffic scenario;

[0014] The calculation of the dynamic expected safety index based on the complexity of traffic scene elements and the potential collision level of traffic participants includes:

[0015] The traffic risk assessment value under the current traffic scenario is calculated based on the complexity of traffic scenario elements and the potential collision level of traffic participants;

[0016] The dynamic expected safety index is calculated based on the traffic risk assessment benchmark and the traffic risk assessment value.

[0017] In some embodiments, based on the complexity of traffic scene elements Potential collision level with traffic participants Calculate the traffic risk assessment value under the current traffic scenario. include:

[0018] Calculate using the following formula , and :

[0019]

[0020]

[0021]

[0022] in, In the traffic scenario, the first Traffic participants With the Traffic participants The coupling relationship between them and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. This indicates the number of different types of traffic participants in a traffic scenario. The number of traffic participants. This indicates the number of traffic participants of the same type. Indicating the first in a traffic scenario Traffic participants With the Traffic participants The forces between them.

[0023] In some embodiments, the following formula is used to calculate the interaction forces between different traffic participants. :

[0024]

[0025] in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, For free-flowing vehicle spacing, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. It is the radius of the driver's focal point. , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The quality.

[0026] In some embodiments, based on the traffic risk assessment benchmark value and the aforementioned traffic risk assessment value Calculating the dynamic expected security index involves using the following formula. :

[0027]

[0028] On the other hand, embodiments of the present invention also provide a traffic risk assessment device, comprising:

[0029] The first processing module is used to describe the characteristics of traffic scenarios by running design domain elements, and to determine the type of traffic scenario based on the characteristics of the traffic scenario.

[0030] The second processing module is used to determine the traffic participants in the traffic scene according to the type of the traffic scene.

[0031] The motion information acquisition module is used to acquire motion information of traffic participants;

[0032] The first calculation module is used to calculate the complexity of traffic scene elements and the potential collision degree of traffic participants based on the motion information of traffic participants.

[0033] The second calculation module is used to calculate the dynamic expected safety index based on the complexity of traffic scene elements and the potential collision level of traffic participants.

[0034] In some embodiments, the apparatus further includes:

[0035] The alert module is used to remind traffic participants to take evasive action when the dynamic expected safety index is greater than or less than a preset threshold.

[0036] In some embodiments, the apparatus further includes:

[0037] The acquisition module is used to acquire benchmark values ​​for traffic risk assessment under a baseline traffic scenario.

[0038] The second calculation module is specifically used to calculate the traffic risk assessment value under the current traffic scenario based on the complexity of traffic scenario elements and the potential collision degree of traffic participants; and to calculate the dynamic expected safety index based on the traffic risk assessment benchmark value and the traffic risk assessment value.

[0039] In some embodiments, the second calculation module is specifically used to calculate the traffic risk assessment value under the current traffic scenario using the following formula. :

[0040] ;

[0041] The first calculation module is specifically used to calculate the complexity of traffic scene elements using the following formula. Potential collision level with traffic participants :

[0042]

[0043]

[0044] in, In the traffic scenario, the first Traffic participants With the Traffic participants The coupling relationship between them and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. This indicates the number of different types of traffic participants in a traffic scenario. The number of traffic participants. This indicates the number of traffic participants of the same type. Indicating the first in a traffic scenario Traffic participants With the Traffic participants The forces between them.

[0045] In some embodiments, the first calculation module is specifically used to calculate the interaction forces between different traffic participants using the following formula. :

[0046]

[0047] in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, For free-flowing vehicle spacing, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. It is the radius of the driver's focal point. , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The quality.

[0048] In some embodiments, the second calculation module is specifically used to calculate the dynamic expected security index using the following formula. :

[0049]

[0050] in, This represents the traffic risk assessment value under the current traffic scenario. This serves as the benchmark value for traffic risk assessment in the baseline traffic scenario.

[0051] This invention also provides a traffic risk assessment device, comprising:

[0052] processor; and

[0053] A memory, in which computer program instructions are stored,

[0054] When the computer program instructions are executed by the processor, the processor performs the steps in the traffic risk assessment method described above.

[0055] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps in the traffic risk assessment method described above.

[0056] The embodiments of the present invention have the following beneficial effects:

[0057] In the above scheme, the characteristics of traffic scenarios are described by operational design domain elements. Based on these characteristics, the type of traffic scenario is determined, and based on the type, the traffic participants within the scenario are identified. Then, the motion information of all traffic participants, including pedestrians and vehicles, can be obtained. Based on this motion information, the complexity of traffic scenario elements and the potential collision level of traffic participants are calculated. A dynamic expected safety index is then calculated based on these two indicators, enabling rapid assessment of the safety situation in traffic scenarios. This is valuable not only for vehicle route planning but also for traffic controllers to rationally plan traffic and predict when to intervene. By considering the interaction of hazard, vulnerability, and exposure levels through the two indicators of traffic scenario element complexity and potential collision level of traffic participants, the scheme measures the risk of traffic areas. This embodiment's technical solution enables long-term risk assessment of traffic scenarios within the constraints of the operational design domain, promoting the further development of autonomous vehicles and connected environments, and improving road traffic safety. Attached Figure Description

[0058] Figure 1 This is a flowchart illustrating the traffic risk assessment method according to an embodiment of the present invention;

[0059] Figure 2 This is a schematic diagram illustrating the operation of design domain elements in an embodiment of the present invention;

[0060] Figure 3 This is a system architecture diagram for implementing traffic risk assessment in an embodiment of the present invention;

[0061] Figure 4 Schematic diagrams for different types of traffic scenarios;

[0062] Figure 5 A schematic diagram showing the positions of traffic participants in a traffic scenario;

[0063] Figure 6 This is a flowchart illustrating another embodiment of the traffic risk assessment method of the present invention;

[0064] Figure 7 This is a structural block diagram of the traffic risk assessment device according to an embodiment of the present invention;

[0065] Figure 8 This is a schematic diagram of the composition of the traffic risk assessment equipment according to an embodiment of the present invention. Detailed Implementation

[0066] To make the technical problems, technical solutions and advantages of the embodiments of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0067] With the rapid development of connected technologies, intelligent transportation systems (ITS) will utilize various sensors, communication systems, and control systems to predict and analyze road hazards and avoid potential dangers. However, the primary traffic participants in ITS—autonomous vehicles—operate in a wide and complex dynamic environment. Interactions between different road users in this environment can easily lead to decision-making conflicts and potential traffic accidents. Therefore, to achieve a truly safe ITS, it is necessary to define in detail all overlapping conditions, use cases, constraints, and scenarios that the primary traffic participants—autonomous vehicles—may encounter. Furthermore, while traffic datasets contain rich information, extracting relevant information and linking this data to risks is a technical problem that needs to be solved. Additionally, current technologies for assessing traffic risks only consider vehicle-to-vehicle interactions, without adequately considering the interactions between vehicles and other traffic participants.

[0068] Considering the safety of intelligent transportation systems and the operating conditions of autonomous driving, in a dynamically changing environment, it is necessary to fully ensure that autonomous vehicles are always within the operating design domain, and to ensure that the transportation system is always within the safety threshold through long-term risk assessment and analysis.

[0069] Embodiments of the present invention provide a traffic risk assessment method and apparatus that can accurately evaluate traffic risks.

[0070] Example 1

[0071] This invention provides a traffic risk assessment method, such as... Figure 1 As shown, it includes:

[0072] Step 101: Describe the characteristics of the traffic scenario by running design domain elements, and determine the type of traffic scenario based on the characteristics of the traffic scenario;

[0073] like Figure 2 and Figure 3 As shown, this embodiment defines the architecture of the Operational Design Domain (ODD). The ODD primarily details all overlapping conditions, use cases, constraints, and scenarios, even edge cases, that traffic participants, such as autonomous vehicles, may encounter. The ODD not only defines the functional requirements of the subsystem components responsible for performing Dynamic Driving Tasks (DDT) and Dynamic Driving Task Support (DDT Fallback), but also the functional requirements of the subsystem components responsible for monitoring the ODD. For any road traffic system, defining the ODD architecture of the traffic environment can limit the traffic scenarios in which autonomous vehicles operate.

[0074] S11, In this embodiment, the characteristics of the traffic scenario are described by running design domain elements, as shown in Table 1. The running design domain elements include at least:

[0075] Table 1. Operational Design Domain Elements

[0076]

[0077] Traffic participants include vehicles, pedestrians, cyclists, and animals; infrastructure includes navigation aids, traffic management equipment, restricted areas, and special road use rules; the road environment and terrain along the current and projected routes include lane type and related road type, slope, camber, curvature, inclination, road friction coefficient, road structure, lane speed limit information, road surface roughness, and locational elements of air density; environmental and weather conditions include surface temperature, air temperature, wind, visibility, precipitation, icing, lighting, glare, electromagnetic interference, clutter, vibration, and other types of sensor noise.

[0078] After describing the characteristics of the system's operating environment using operational design domain elements, based on actual traffic scenarios, traffic participants such as autonomous vehicles not only need to drive normally in typical highway scenarios, but also need to operate safely in complex environments and dangers. Furthermore, the complex systems comprising autonomous vehicles must ensure safety in the event of system failures. Therefore, as... Figure 4 As shown, based on the complexity level of ODD elements, traffic scenarios can be divided into typical traffic scenarios, dangerous traffic scenarios, and edge case scenarios. Of course, the types of traffic scenarios are not limited to these; they can include many other types. This embodiment only uses typical traffic scenarios, dangerous traffic scenarios, and edge case scenarios as examples for illustration. In this embodiment, a typical traffic scenario can be a typical highway scenario, a dangerous traffic scenario can be a traffic scenario where a traffic accident occurs, and an intersection can be an edge case scenario.

[0079] Step 102: Determine the traffic participants in the traffic scenario based on the type of traffic scenario;

[0080] After determining the type of actual traffic scenario, the operational design domain elements under the actual traffic scenario are categorized and extracted. This allows us to determine the boundaries of the operational design domain, including which traffic participants are involved in the traffic scenario. For example, in a typical traffic scenario, since pedestrians, animals, and cyclists generally do not appear on highways, the traffic participants in a typical traffic scenario may only include vehicles. In a marginal case scenario, since pedestrians, animals, cyclists, and vehicles may all appear at intersections, the traffic participants in a marginal case scenario include pedestrians, animals, cyclists, and vehicles.

[0081] Step 103: Obtain motion information of traffic participants, and calculate the complexity of traffic scene elements and the potential collision degree of traffic participants based on the motion information of traffic participants;

[0082] An optimized deployment scheme for roadside sensors in the traffic environment with low cost and full-domain perception coverage can be constructed in advance within the architecture of the operational design domain. This scheme acquires motion information of traffic participants in the traffic scene through a combination of vehicle-mounted sensors and roadside sensors. Roadside sensors can be roadside cameras, while vehicle-mounted sensors include radar and vehicle-mounted cameras. For example... Figure 2 As shown, the requirements for sensors in the perception subsystem can be: detection range of traffic objects within 50m; full coverage of traffic scenarios by roadside sensors; and for vehicle-mounted sensors, a combination of left-side radar, right-side radar, and forward radar.

[0083] In this embodiment, the target of traffic risk assessment can be a vehicle, such as an autonomous vehicle, or a traffic monitoring platform.

[0084] When the target of a traffic risk assessment is a vehicle, priority should be given to entities with a collision risk, such as... Figure 2As shown, the entity includes dynamic objects (e.g., vulnerable road users and their corresponding motion characteristics), static instances (e.g., road boundaries, traffic guidance, and communication signals), and obstacles. The traffic participants of interest to the vehicle may only include those around the vehicle, as these are the only ones who could potentially pose a risk to the vehicle's movement. The vehicle only needs to acquire motion information of these surrounding traffic participants. This information can be obtained from roadside sensors and other vehicle-mounted sensors via connected technologies, or from onboard sensors. The distance between the surrounding traffic participants and the vehicle is less than a preset value. This preset value can be adjusted according to different traffic scenarios; for example, it could be 500m in a typical traffic scenario and 200m in an edge case scenario.

[0085] When the traffic risk assessment is performed on a traffic monitoring platform, the platform should prioritize entities with collision risks, such as... Figure 2 As shown, the entity includes dynamic objects (such as vulnerable road users and their corresponding motion characteristics), static instances (such as road boundaries, traffic guidance, and communication signals), and obstacles. The traffic participants of interest to the traffic monitoring platform can be those throughout the entire traffic scenario. The platform can acquire motion information of traffic participants throughout the entire traffic scenario through roadside sensors and vehicle-mounted sensors using connected technologies.

[0086] The motion information of traffic participants includes, but is not limited to, their location, speed, acceleration, and distance from other traffic participants.

[0087] Roadside sensors can capture effective motion information of traffic participants, supporting the management of the operational design domain. However, potential areas with occlusion must also be considered. Within a certain range, the installation parameters of roadside sensors have a certain impact on their sensing performance. Operational design domain management imposes different requirements on the sensing performance of roadside sensors under different circumstances, requiring analysis of the sensor's detection range, reliability, accuracy and precision, false positives and false negatives, and sensing latency. Furthermore, based on the coverage areas of the deployed roadside sensors, the sensing performance under specific environments and scenarios can be further analyzed.

[0088] For example, in typical traffic scenarios, highways are highly dynamic and unpredictable. If a vehicle fails to respond correctly within a short time when the movement of other vehicles changes, accidents can easily occur. Therefore, during driving, it is essential to accurately assess the current driving risk (based on dynamic highway traffic information) by acquiring real-time information on the movement of surrounding vehicles and making appropriate decisions (such as acceleration or deceleration) to effectively ensure driving safety. Therefore, it is necessary to propose requirements based on the mapping relationship between operational design domain elements and the needs of the perception subsystem.

[0089] The information required for highway scenarios can be obtained by installing roadside sensors and onboard sensors on the vehicle itself. The longitudinal and lateral speeds, longitudinal and lateral coordinates, and wheel (steering wheel) angles of the vehicle and surrounding vehicles can be collected in real time from the traffic monitoring perspective or the onboard perspective. Some of the information obtained is shown in Table 2.

[0090] Table 2. Start and End Status Information for Each Vehicle

[0091]

[0092] The operational design domain elements mainly include: road structure (terrain and related location features), environmental weather conditions (surface temperature, air temperature, wind, visibility, lighting, etc.), traffic participants (pedestrians, motor vehicles, cyclists, animals, etc.), and infrastructure (navigation aids, traffic management equipment, etc.). Based on these operational design domain elements, the requirements for the perception subsystem include: 1) detecting traffic participants within a 50m range; 2) using a combination of left-hand, right-hand, and forward-facing radars; and 3) achieving full coverage of the traffic scene by roadside sensors. The main focus on collision risk entities includes two categories: 1) dynamic objects (vulnerable road users) and their corresponding motion characteristics; and 2) static instances (road boundaries, traffic guidance, and communication signals) and obstacles.

[0093] Step 104: Calculate the dynamic expected safety index based on the complexity of traffic scene elements and the potential collision level of traffic participants.

[0094] The evaluation indicators for the dynamic expected safety index include:

[0095] Evaluation Metric 1: The complexity of operational design domain elements in a traffic scenario, also known as the complexity of traffic scenario elements, can be understood as the difficulty and complexity of identifying the coupled information between traffic participants and their surrounding environment due to dynamic changes under specific circumstances. Traffic datasets contain rich information; the location, time, and other environmental factors of traffic participants within the area all alter the risk. Therefore, it is crucial to extract relevant information and link this data with risk. This embodiment can be based on natural driving data, such as highD, NGSIM, and Interaction datasets, proposing the use of risk level sets to analyze vehicle driving data and extract relevant parameters for online risk calculation.

[0096] Evaluation Indicator 2: The potential collision level of traffic participants in a traffic scenario, or the potential injury level of traffic participants. The risk level of a traffic scenario over a long time domain needs to be analyzed from a statistical perspective, by adding additional statistical data and external sources to analyze the probability and severity of traffic accidents.

[0097] The dynamic complexity of the environment arises from the diversity and differences in the relationships between different nodes, as well as the uncertainties inherent in the dynamic operation process, leading to variations in the complexity of the operational design domain. Therefore, the primary factor influencing the complexity of the dynamic operational design domain is the node relationships between different traffic participants within the traffic subsystems, i.e., the connections between abstract nodes. This embodiment transforms the measurement of the complexity of dynamic operational design domain elements into a measurement of the connections between nodes. By comprehensively considering the above two evaluation indicators, a dynamic expected safety index is used. To characterize the long-term comprehensive risk of traffic scenarios, among which, As a benchmark value for traffic risk assessment, This is a traffic risk assessment value.

[0098] Based on evaluation index 1, the complexity of elements in the operation design domain in the traffic scenario is judged as shown in Table 3:

[0099] Table 3. Distinction of Complexity of Operational Design Domain Elements

[0100]

[0101] like Figure 5 As shown, based on the evaluation index 1 defined above, considering the interaction between all traffic participants and the environment in a traffic scenario, all traffic participants in the traffic environment are regarded as single traffic participants. Its position is set to , Position in the direction perpendicular to the lane (lateral direction). This refers to the position in the longitudinal direction parallel to the lane. Consider this traffic scenario. For traffic scenarios Any traffic participant All are satisfied Considering the dynamic information of any traffic participant, a double-integral dynamics model is used to model the participant, satisfying:

[0102]

[0103]

[0104] in, Each is an object lateral and longitudinal velocities, Each is an object The lateral and longitudinal accelerations. In this embodiment, the speed and acceleration of traffic participants both satisfy the maximum dynamic constraints. At the same time, the speed of traffic participants should also meet the restrictions of traffic rules, such as the lane's minimum and maximum speed restrictions.

[0105] Assuming all traffic participants are self-protective, meaning that given sufficient braking distance, one participant will stop to avoid a collision with another, the system calculates the costs incurred by each participant on the road and the complexity of the overall road environment's operational design domain to assess the risk of each vehicle at every point in the dataset. The features used in this embodiment for traffic risk assessment include: each participant's lateral road position (e.g., lane), longitudinal and lateral speeds, relative distances between participants, and participant types within the traffic area. These features are commonly used for vehicle behavior and maneuver classification; therefore, the potential relationship between traffic risk and these features needs to be considered. In summary, the operational design domain element complexity can be characterized as:

[0106]

[0107] in, Representing different traffic participants in a traffic scenario The number of types, Indicates the same type of traffic participants The number of and Indicates different traffic participants, The entropy value represents the complexity of the elements in the design domain.

[0108] When there is an interaction between two traffic participants, such as the first... The traffic participant and the first There is a coupling relationship between traffic participants. The more coupling relationships there are, the more complex the traffic system operation design domain becomes. Therefore, coupling relationships can be used to measure the complexity of the traffic system operation design domain. and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants Lateral and longitudinal speeds are subject to maximum dynamic constraints and traffic rule limits.

[0109] Based on the aforementioned evaluation index 2, in traffic scenarios, the severity of injury / collision to traffic participants can be measured using the definition of field strength. To assess the safety status of the traffic environment, based on the driving safety field, the risk of the traffic system is defined as the interaction of fields between various research objects. Evaluation index 2 is output by analyzing the severity of injury / collision to traffic participants and the relationship between work done by forces and energy conversion during the collision process. Among these, the forces between different traffic participants... It can be described as:

[0110]

[0111] in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, Free-flow vehicle spacing, used to represent the area of ​​maximum risk impact, is defined according to the road traffic manual. In this embodiment, it can be set .in, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. In this embodiment, both values ​​can be set to 1. It is the radius of the driver's focal point, which is related to the distance between the driver and the vehicle within their line of sight. In this embodiment, it can be set to... . , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The greater the mass and speed of a moving object, the greater the force exerted on it.

[0112] Of course, the forces between different traffic participants In addition to the above description methods, other description forms in the prior art can also be used.

[0113] Based on the evaluation indicators 1 and 2 defined above, and taking into account the complexity of the elements in the traffic system operation design domain and the severity of injury / collision to traffic participants, the dynamic expected safety index is used to characterize the long-term comprehensive risk of this traffic scenario.

[0114] First, calculate the complexity of the design domain elements under any given condition. Forces experienced by traffic participants and the complexity of design domain elements under baseline conditions. Forces experienced by traffic participants Let them be set as follows:

[0115]

[0116]

[0117]

[0118]

[0119]

[0120]

[0121] in, For the baseline case This refers to the expected value of long-term traffic risk assessment under the baseline scenario. The traffic scenario under the baseline scenario has the same road structure as the actual traffic scenario, including the same terrain and related location features, but the traffic scenario under the baseline scenario has sunny weather, flat road conditions, and free flow of multiple vehicles. For example, for a typical traffic scenario, the baseline is based on the standard highway scenario with sunny weather, flat road conditions, and free flow of multiple vehicles.

[0122] Based on the above formula, the output of dynamic risk assessment results for traffic scenarios can be described as follows:

[0123]

[0124] in, This represents the expected value for long-term traffic risk assessment in real-world traffic scenarios. This represents the dynamic expected safety index in real-world traffic scenarios. As the expected value of long-term traffic risk assessment under the baseline traffic scenario, if The higher the value, the higher the risk level of the transportation system.

[0125] Of course, you can also Described as and Other related forms.

[0126] After obtaining the dynamic expected safety index, such as Figure 6 As shown, the method further includes:

[0127] Step 105: When the dynamic expected safety index is greater than or less than the preset threshold, remind traffic participants to take evasive action.

[0128] Among them, if If the dynamic expected safety index is lower than a preset threshold, traffic participants will be alerted to take evasive action. The preset threshold can be set according to actual conditions, and different preset thresholds correspond to different types of traffic scenarios.

[0129] When the target of traffic risk assessment is a vehicle, the on-board system, after obtaining the dynamic expected safety index and determining whether the dynamic expected safety index is greater than or less than a preset threshold, can remind the driver to take evasive action, including taking a detour or reducing speed. When the target of traffic risk assessment is a traffic monitoring platform, the traffic monitoring platform, after obtaining the dynamic expected safety index and determining whether the dynamic expected safety index is greater than or less than a preset threshold, can remind traffic participants in the traffic scenario to take evasive action, including taking a detour or reducing speed. For example, the traffic monitoring platform can send information to the on-board system to remind the driver of the vehicle.

[0130] In this embodiment, traffic information can be acquired in real time by deploying sensors, the long-term traffic status can be statistically analyzed, changes in the safety situation can be judged, and finally the long-term risk level of the intelligent transportation environment can be output.

[0131] This embodiment describes the characteristics of traffic scenarios through operational design domain elements, determines the type of traffic scenario based on these characteristics, identifies traffic participants within the scenario based on the scenario type, and then acquires the motion information of all traffic participants, including pedestrians and vehicles. Based on this motion information, the complexity of traffic scenario elements and the potential collision level of traffic participants are calculated. A dynamic expected safety index is then calculated based on these two indicators, enabling rapid assessment of safety conditions in traffic scenarios. This is valuable not only for vehicle route planning but also for traffic controllers to rationally plan traffic and predict when to intervene. By considering the interaction of hazard, vulnerability, and exposure levels through the two key indicators of traffic scenario element complexity and potential collision level, the risk of traffic areas is measured. This embodiment's technical solution enables long-term risk assessment of traffic scenarios within the constraints of the operational design domain, promoting the further development of autonomous vehicles and connected environments, and improving road traffic safety.

[0132] Example 2

[0133] This invention also provides a traffic risk assessment device, such as... Figure 7 As shown, it includes:

[0134] The first processing module 21 is used to describe the characteristics of the traffic scene by running design domain elements, and to determine the type of traffic scene based on the characteristics of the traffic scene.

[0135] The second processing module 22 is used to determine traffic participants in the traffic scene according to the type of the traffic scene;

[0136] The motion information acquisition module 23 is used to acquire motion information of traffic participants;

[0137] The first calculation module 24 is used to calculate the complexity of traffic scene elements and the potential collision degree of traffic participants based on the motion information of traffic participants.

[0138] The second calculation module 25 is used to calculate the dynamic expected safety index based on the complexity of traffic scene elements and the potential collision degree of traffic participants.

[0139] In some embodiments, the apparatus further includes:

[0140] The alert module is used to remind traffic participants to take evasive action when the dynamic expected safety index is greater than or less than a preset threshold.

[0141] In some embodiments, the apparatus further includes:

[0142] The acquisition module is used to acquire benchmark values ​​for traffic risk assessment under a baseline traffic scenario.

[0143] The second calculation module is specifically used to calculate the traffic risk assessment value under the current traffic scenario based on the complexity of traffic scenario elements and the potential collision degree of traffic participants; and to calculate the dynamic expected safety index based on the traffic risk assessment benchmark value and the traffic risk assessment value.

[0144] In some embodiments, the second calculation module is specifically used to calculate the traffic risk assessment value under the current traffic scenario using the following formula. :

[0145] ;

[0146] The first calculation module is specifically used to calculate the complexity of traffic scene elements using the following formula. Potential collision level with traffic participants :

[0147]

[0148]

[0149] in, In the traffic scenario, the first Traffic participants With the Traffic participants The coupling relationship between them and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. This indicates the number of different types of traffic participants in a traffic scenario. The number of traffic participants. This indicates the number of traffic participants of the same type. Indicating the first in a traffic scenario Traffic participants With the Traffic participants The forces between them.

[0150] In some embodiments, the first calculation module is specifically used to calculate the interaction forces between different traffic participants using the following formula. :

[0151]

[0152] in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, For free-flowing vehicle spacing, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. It is the radius of the driver's focal point. , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The quality.

[0153] In some embodiments, the second calculation module is specifically used to calculate the dynamic expected security index using the following formula. :

[0154] .

[0155] in, This represents the traffic risk assessment value under the current traffic scenario. This serves as the benchmark value for traffic risk assessment in the baseline traffic scenario.

[0156] In this embodiment, the characteristics of a traffic scenario are described by elements of the operational design domain. The type of traffic scenario is determined based on these characteristics, and the traffic participants within the scenario are identified based on the scenario type. Motion information for all traffic participants, including pedestrians and vehicles, is then acquired. Based on this motion information, the complexity of traffic scenario elements and the potential collision level of traffic participants are calculated. A dynamic expected safety index is then calculated based on these two indicators, enabling rapid assessment of the safety situation in a traffic scenario. This is valuable not only for vehicle route planning but also for traffic controllers to rationally plan traffic and predict when to intervene. By considering the interaction of hazard, vulnerability, and exposure levels through the two key indicators of traffic scenario element complexity and potential collision level, the risk of a traffic area is measured. This embodiment's technical solution enables long-term risk assessment of traffic scenarios within the constraints of the operational design domain, promoting the further development of autonomous vehicles and connected environments, and improving road traffic safety.

[0157] Example 3

[0158] This invention also provides a traffic risk assessment device 30, such as... Figure 8 As shown, it includes:

[0159] Processor 32; and

[0160] Memory 34, in which computer program instructions are stored.

[0161] When the computer program instructions are executed by the processor, the processor 32 performs the following steps:

[0162] The characteristics of a traffic scenario are described by running design domain elements, and the type of traffic scenario is determined based on the characteristics of the traffic scenario.

[0163] The traffic participants in the traffic scenario are determined based on the type of traffic scenario.

[0164] Obtain motion information of traffic participants, and calculate the complexity of traffic scene elements and the potential collision degree of traffic participants based on the motion information of traffic participants;

[0165] The dynamic expected safety index is calculated based on the complexity of traffic scene elements and the potential collision levels of traffic participants.

[0166] In this embodiment, the characteristics of a traffic scenario are described by elements of the operational design domain. The type of traffic scenario is determined based on these characteristics, and the traffic participants within the scenario are identified based on the scenario type. Motion information for all traffic participants, including pedestrians and vehicles, is then acquired. Based on this motion information, the complexity of traffic scenario elements and the potential collision level of traffic participants are calculated. A dynamic expected safety index is then calculated based on these two indicators, enabling rapid assessment of the safety situation in a traffic scenario. This is valuable not only for vehicle route planning but also for traffic controllers to rationally plan traffic and predict when to intervene. By considering the interaction of hazard, vulnerability, and exposure levels through the two key indicators of traffic scenario element complexity and potential collision level, the risk of a traffic area is measured. This embodiment's technical solution enables long-term risk assessment of traffic scenarios within the constraints of the operational design domain, promoting the further development of autonomous vehicles and connected environments, and improving road traffic safety.

[0167] Furthermore, such as Figure 8 As shown, the traffic risk assessment device 30 also includes a network interface 31, an input device 33, a hard disk 35, and a display device 36.

[0168] The various interfaces and devices described above can be interconnected via a bus architecture. The bus architecture can include any number of interconnecting buses and bridges. Specifically, various circuits representing one or more central processing units (CPUs), represented by processor 32, and one or more memories, represented by memory 34, are connected together. The bus architecture can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. It is understood that the bus architecture is used to implement communication between these components. In addition to the data bus, the bus architecture also includes a power bus, a control bus, and a status signal bus, all of which are well known in the art and will not be described in detail herein.

[0169] The network interface 31 can be connected to a network (such as the Internet, local area network, etc.) to obtain relevant data from the network, such as data from roadside sensors and vehicle-mounted sensors, and can be stored in the hard disk 35.

[0170] The input device 33 can receive various instructions input by the operator and send them to the processor 32 for execution. The input device 33 may include a keyboard or a clicking device (e.g., a mouse, trackball, touchpad, or touchscreen).

[0171] The display device 36 can display the results obtained by the processor 32 executing instructions.

[0172] The memory 34 is used to store programs and data necessary for the operation of the operating system, as well as intermediate results and other data during the calculation process of the processor 32.

[0173] It is understood that the memory 34 in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. The memory 34 of the apparatus and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0174] In some implementations, memory 34 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating system 341 and application programs 342.

[0175] The operating system 341 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 342 includes various applications, such as a browser, used to implement various application functions. Programs implementing the methods of this embodiment of the invention can be included in the application program 342.

[0176] The processor 32, when calling and executing the application program and data stored in the memory 34, can specifically describe the characteristics of the traffic scene by running design domain elements, determine the type of traffic scene based on the characteristics of the traffic scene, determine the traffic participants in the traffic scene based on the type of traffic scene, obtain the motion information of the traffic participants, calculate the complexity of traffic scene elements and the potential collision degree of traffic participants based on the motion information of the traffic participants, and calculate the dynamic expected safety index based on the complexity of traffic scene elements and the potential collision degree of traffic participants.

[0177] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 32. Processor 32 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 32 or by instructions in software form. The processor 32 may be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 34, and processor 32 reads the information in memory 34 and completes the steps of the above method in combination with its hardware.

[0178] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0179] For software implementation, the techniques described herein can be achieved through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented within the processor or externally.

[0180] Specifically, the processor 32 is also used to remind traffic participants to take evasive action when the dynamic expected safety index is greater than or less than a preset threshold.

[0181] Specifically, the processor 32 is also used to obtain the traffic risk assessment benchmark value under the benchmark traffic scenario; calculate the traffic risk assessment value under the current traffic scenario based on the complexity of traffic scenario elements and the potential collision degree of traffic participants; and calculate the dynamic expected safety index based on the traffic risk assessment benchmark value and the traffic risk assessment value.

[0182] Specifically, processor 32 calculates using the following formula , and :

[0183]

[0184]

[0185]

[0186] in, In the traffic scenario, the first Traffic participants With the Traffic participants The coupling relationship between them and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. This indicates the number of different types of traffic participants in a traffic scenario. The number of traffic participants. This indicates the number of traffic participants of the same type. Indicating the first in a traffic scenario Traffic participants With the Traffic participants The forces between them.

[0187] Specifically, the processor 32 uses the following formula to calculate the interaction forces between different traffic participants. :

[0188]

[0189] in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, For free-flowing vehicle spacing, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. It is the radius of the driver's focal point. , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The quality.

[0190] Specifically, processor 32 uses the following formula to calculate the dynamic expected security index. :

[0191] .

[0192] Example 4

[0193] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0194] The characteristics of a traffic scenario are described by running design domain elements, and the type of traffic scenario is determined based on the characteristics of the traffic scenario.

[0195] The traffic participants in the traffic scenario are determined based on the type of traffic scenario.

[0196] Obtain motion information of traffic participants, and calculate the complexity of traffic scene elements and the potential collision degree of traffic participants based on the motion information of traffic participants;

[0197] The dynamic expected safety index is calculated based on the complexity of traffic scene elements and the potential collision levels of traffic participants.

[0198] Furthermore, when the computer program is run by the processor, it causes the processor to perform the following steps:

[0199] When the dynamic expected safety index is greater than or less than a preset threshold, traffic participants are reminded to take evasive action.

[0200] Furthermore, when the computer program is run by the processor, it causes the processor to perform the following steps:

[0201] Obtain the baseline value for traffic risk assessment under the benchmark traffic scenario;

[0202] The traffic risk assessment value under the current traffic scenario is calculated based on the complexity of traffic scenario elements and the potential collision level of traffic participants;

[0203] The dynamic expected safety index is calculated based on the traffic risk assessment benchmark and the traffic risk assessment value.

[0204] Furthermore, when the computer program is run by the processor, it causes the processor to perform the following steps:

[0205] Calculate using the following formula , and :

[0206]

[0207]

[0208]

[0209] in, In the traffic scenario, the first Traffic participants With the Traffic participants The coupling relationship between them and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. This indicates the number of different types of traffic participants in a traffic scenario. The number of traffic participants. This indicates the number of traffic participants of the same type. Indicating the first in a traffic scenario Traffic participants With the Traffic participants The forces between them.

[0210] Furthermore, when the computer program is run by the processor, it causes the processor to perform the following steps:

[0211] The following formula is used to calculate the interaction forces between different traffic participants. :

[0212]

[0213] in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, For free-flowing vehicle spacing, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. It is the radius of the driver's focal point. , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The quality.

[0214] Furthermore, when the computer program is run by the processor, it causes the processor to perform the following steps:

[0215] The dynamic expected safety index is calculated using the following formula. :

[0216] .

[0217] In this embodiment, the characteristics of a traffic scenario are described by elements of the operational design domain. The type of traffic scenario is determined based on these characteristics, and the traffic participants within the scenario are identified based on the scenario type. Motion information for all traffic participants, including pedestrians and vehicles, is then acquired. Based on this motion information, the complexity of traffic scenario elements and the potential collision level of traffic participants are calculated. A dynamic expected safety index is then calculated based on these two indicators, enabling rapid assessment of the safety situation in a traffic scenario. This is valuable not only for vehicle route planning but also for traffic controllers to rationally plan traffic and predict when to intervene. By considering the interaction of hazard, vulnerability, and exposure levels through the two key indicators of traffic scenario element complexity and potential collision level, the risk of a traffic area is measured. This embodiment's technical solution enables long-term risk assessment of traffic scenarios within the constraints of the operational design domain, promoting the further development of autonomous vehicles and connected environments, and improving road traffic safety.

[0218] The above are preferred embodiments of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles described in the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A traffic risk assessment method, characterized in that, include: The characteristics of a traffic scenario are described by running design domain elements, and the type of traffic scenario is determined based on the characteristics of the traffic scenario. The traffic participants in the traffic scenario are determined based on the type of traffic scenario. Obtain motion information of traffic participants, and calculate the complexity of traffic scene elements based on the motion information of traffic participants. Potential collision level with traffic participants ; Based on the complexity of traffic scene elements Potential collision level with traffic participants Calculate the dynamic expected security index ; The method further includes obtaining traffic risk assessment benchmark values ​​under a benchmark traffic scenario. ; The complexity of traffic scene elements Potential collision level with traffic participants Calculate the dynamic expected security index include: Based on the complexity of traffic scene elements Potential collision level with traffic participants Calculate the traffic risk assessment value under the current traffic scenario. ; Based on the aforementioned traffic risk assessment benchmark and the aforementioned traffic risk assessment value Calculate the dynamic expected security index ; Among them, based on the complexity of traffic scene elements Potential collision level with traffic participants Calculate the traffic risk assessment value under the current traffic scenario. include: Calculate using the following formula , and : in, In the traffic scenario, the first Traffic participants With the Traffic participants The coupling relationship between them and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. This indicates the number of different types of traffic participants in a traffic scenario. The number of traffic participants. This indicates the number of traffic participants of the same type. Indicating the first in a traffic scenario Traffic participants With the Traffic participants The forces between them.

2. The traffic risk assessment method according to claim 1, characterized in that, Also includes: The dynamic expected security index If the value is greater than or less than a preset threshold, traffic participants will be alerted to take evasive action.

3. The traffic risk assessment method according to claim 1, characterized in that, The operational design domain elements include: road structure, traffic participants, infrastructure, environmental and weather conditions.

4. The traffic risk assessment method according to claim 1, characterized in that, The following formula is used to calculate the interaction forces between different traffic participants. : in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, For free-flowing vehicle spacing, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. It is the radius of the driver's focal point. , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The quality.

5. The traffic risk assessment method according to claim 1, characterized in that, Based on the aforementioned traffic risk assessment benchmark and the aforementioned traffic risk assessment value Calculate the dynamic expected security index This includes calculating the dynamic expected security index using the following formula. : 。 6. A traffic risk assessment device, characterized in that, include: The first processing module is used to describe the characteristics of traffic scenarios by running design domain elements, and to determine the type of traffic scenario based on the characteristics of the traffic scenario. The second processing module is used to determine the traffic participants in the traffic scene according to the type of the traffic scene. The motion information acquisition module is used to acquire motion information of traffic participants; The first calculation module is used to calculate the complexity of traffic scene elements based on the motion information of traffic participants. Potential collision level with traffic participants ; The second calculation module is used to calculate the complexity of traffic scene elements. Potential collision level with traffic participants Calculate the dynamic expected security index ; The traffic risk assessment device further includes: The acquisition module is used to obtain the traffic risk assessment benchmark value under the benchmark traffic scenario. ; The second calculation module is specifically used to calculate the complexity of traffic scene elements. Potential collision level with traffic participants Calculate the traffic risk assessment value under the current traffic scenario. Based on the aforementioned traffic risk assessment benchmark value and the aforementioned traffic risk assessment value Calculate the dynamic expected security index ; Specifically, the second calculation module is used to calculate the traffic risk assessment value under the current traffic scenario using the following formula. : ； The first calculation module is specifically used to calculate the complexity of traffic scene elements using the following formula. Potential collision level with traffic participants : in, In the traffic scenario, the first Traffic participants With the Traffic participants The coupling relationship between them and , , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal road positions on the lanes , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. , For traffic participants The lateral and longitudinal velocities are subject to maximum dynamic constraints and traffic rule limitations. This indicates the number of different types of traffic participants in a traffic scenario. The number of traffic participants. express The number of traffic participants of the same type Indicating the first in a traffic scenario Traffic participants With the Traffic participants The forces between them.

7. The traffic risk assessment device according to claim 6, characterized in that, Also includes: The reminder module is used to dynamically adjust the expected security index. If the value is greater than or less than a preset threshold, traffic participants will be alerted to take evasive action.

8. The traffic risk assessment device according to claim 6, characterized in that, The first calculation module is specifically used to calculate the interaction forces between different traffic participants using the following formula. : in, , They represent the first Traffic participants With the Traffic participants The horizontal and vertical distances, For free-flowing vehicle spacing, , These are the gradient adjustment coefficients for the horizontal and vertical directions, respectively. It is the radius of the driver's focal point. , They represent the first Traffic participants With the Traffic participants The speed of movement, Indicates the first Traffic participants The quality.

9. The traffic risk assessment device according to claim 6, characterized in that, The second calculation module is specifically used for: based on the traffic risk assessment benchmark value and the aforementioned traffic risk assessment value The dynamic expected security index is calculated using the following formula. : 。

Images