CN114881384A

CN114881384A - Traffic risk assessment method and device

Info

Publication number: CN114881384A
Application number: CN202110162564.5A
Authority: CN
Inventors: 王建强; 黄荷叶; 许庆; 李克强; 关口隆昭; 耿璐
Original assignee: Tsinghua University; Hitachi Ltd
Current assignee: Tsinghua University; Hitachi Ltd
Priority date: 2021-02-05
Filing date: 2021-02-05
Publication date: 2022-08-09

Abstract

The invention 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 the traffic scene by operating the design domain elements, and determining the type of the traffic scene according to the characteristics of the traffic scene; determining traffic participants in a traffic scene according to the type of the traffic scene; acquiring the motion information of the traffic participants, and respectively calculating the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants according to the motion information of the traffic participants; and calculating a dynamic expected safety index according to the complexity of the traffic scene element and the potential collision degree of the traffic participants. The invention can evaluate traffic risk and improve road traffic safety.

Description

Traffic risk assessment method and device

Technical Field

The invention relates to the field of intelligent traffic, in particular to a traffic risk assessment method and a traffic risk assessment device.

Background

Along with the rapid development of urbanization and the realization of road motorized progress, the life of people is more convenient. Meanwhile, the explosive growth of motor vehicles brings a series of social security problems such as traffic jam and traffic accidents. According to the "global road safety situation report" published in 2015 by the world health organization, every year, road traffic accidents cause about 130 million deaths worldwide, 2000 to 5000 million people suffer non-fatal injuries. Road traffic accidents are a major cause of death in all age groups. Therefore, the future traffic accident risk can be accurately and effectively predicted, and a safer scheme and route can be selected for personal travel.

Disclosure of Invention

The invention aims to provide a traffic risk assessment method and a traffic risk assessment device, which can evaluate traffic risks and improve road traffic safety.

To solve the above technical problem, embodiments of the present invention provide the following technical solutions:

in one aspect, an embodiment of the present invention provides a traffic risk assessment method, including:

describing the characteristics of the traffic scene by operating the design domain elements, and determining the type of the traffic scene according to the characteristics of the traffic scene;

determining traffic participants in a traffic scene according to the type of the traffic scene;

acquiring the motion information of the traffic participants, and respectively calculating the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants according to the motion information of the traffic participants;

and calculating a dynamic expected safety index according to the complexity of the traffic scene element and the potential collision degree of the traffic participants.

In some embodiments, the method further comprises:

and when the dynamic expected safety index is larger than or smaller than a preset threshold value, reminding the traffic participants to avoid.

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

In some embodiments, the method further comprises obtaining a traffic risk assessment benchmark value in a benchmark traffic scene;

the calculating the dynamic expected safety index according to the complexity of the traffic scene element and the potential collision degree of the traffic participants comprises the following steps:

calculating a traffic risk assessment value under the current traffic scene according to the element complexity of the traffic scene and the potential collision degree of the traffic participants;

and calculating a dynamic expected safety index according to the traffic risk assessment reference value and the traffic risk assessment value.

In some embodiments, the complexity E is based on traffic scene elements _D And potential collision degree E of traffic participants _f Calculating traffic risk assessment value E under current traffic scene _s The method comprises the following steps:

calculate E using the following formula _s 、E _D And E _f ：

E _s ＝E _D +E _f

Wherein d is _ij Representing the ith traffic participant O in the traffic scene _i With the jth traffic participant O _j Coupling relationship between d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，v _xj ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _j 、y _j Are respectively traffic participants O _j Transverse and longitudinal road positions on a laneV. position of _xi 、v _yi Are respectively traffic participants O _i Transverse and longitudinal velocities, v, under the constraint of satisfying maximum dynamics and traffic regulations _xj 、v _yj Are respectively traffic participants O _j The transverse speed and the longitudinal speed under the condition of meeting the maximum dynamic constraint and the traffic regulation limit, m represents the types and the number of different traffic participants in the traffic scene, n is the number of the traffic participants,

representing the number of traffic participants of the same type, F _ij Representing the jth traffic participant O in a traffic scene _j With the ith traffic participant O _i To the force of (c).

In some embodiments, the following formula is used to calculate the forces F between different participants _ij ：

Wherein x is _ji ，y _ji Respectively represent the jth traffic participant O _j With the ith traffic participant O _i In the transverse and longitudinal directions, r _max For free-flow vehicle spacing, k _x，0 ，k _y，0 Gradient adjustment coefficients, r, in the transverse and longitudinal directions, respectively ₀ Is the radius of the driver's focus, v _j ，v _i Respectively represent the jth traffic participant O _j With the ith traffic participant O _i M, speed of movement of _j Represents the jth traffic participant O _j The quality of (c).

In some embodiments, a benchmark value is assessed based on the traffic risk

And the traffic risk assessment value E _s Calculating the dynamic expected safety index includes calculating the dynamic expected safety index R using the following formula _s ：

On the other hand, the embodiment of the invention also provides a traffic risk assessment device, which comprises:

the first processing module is used for describing the characteristics of the traffic scene by operating the design domain elements and determining the type of the traffic scene according to the characteristics of the traffic scene;

the second processing module is used for determining traffic participants in the traffic scene according to the type of the traffic scene;

the motion information acquisition module is used for acquiring the motion information of the traffic participants;

the first calculation module is used for respectively calculating the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants according to the motion information of the traffic participants;

and the second calculation module is used for calculating the dynamic expected safety index according to the complexity of the traffic scene element and the potential collision degree of the traffic participant.

In some embodiments, the apparatus further comprises:

and the reminding module is used for reminding the traffic participants to avoid when the dynamic expected safety index is greater than or less than a preset threshold value.

In some embodiments, the apparatus further comprises:

the acquisition module is used for acquiring a traffic risk assessment reference value in a reference traffic scene;

the second calculation module is specifically used for calculating a traffic risk assessment value under the current traffic scene according to the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants; and calculating a dynamic expected safety index according to the traffic risk assessment reference value and the traffic risk assessment value.

In some embodiments, the second calculation module is specifically configured to calculate the traffic risk assessment value E in the current traffic scene by using the following formula _s ：

E _s ＝E _D +E _f ；

The first calculationThe module is specifically configured to calculate the traffic scene element complexity E using the following formula _D And potential collision degree E of traffic participants _f ：

Wherein d is _ij Representing the ith traffic participant O in the traffic scene _i With the jth traffic participant O _j Coupling relationship between d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，vx _j ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _j 、y _j Are respectively traffic participants O _j Lateral and longitudinal road positions on the lane, v _xi 、v _yi Are respectively traffic participants O _i Transverse and longitudinal velocities, v, under the constraint of satisfying maximum dynamics and traffic regulations _xj 、v _yj Are respectively traffic participants O _j The transverse speed and the longitudinal speed under the condition of meeting the maximum dynamic constraint and the traffic regulation limit, m represents the types and the number of different traffic participants in the traffic scene, n is the number of the traffic participants,

In some embodiments, the first calculation module is specifically configured to calculate the force F between different traffic participants using the following formula _ij ：

Wherein x is _ji ，y _ji Respectively represent the jth traffic participant O _j With the ith traffic participant O _i In the transverse and longitudinal directions, r _max For free-flow inter-vehicle distance, k _x，0 ，k _y，0 Gradient adjustment coefficients, r, in the transverse and longitudinal directions, respectively ₀ Is the radius of the driver's focus, v _j ，v _i Respectively represent the jth traffic participant O _j With the ith traffic participant O _i M, speed of movement of _j Represents the jth traffic participant O _j The quality of (c).

In some embodiments, the second calculation module is specifically configured to calculate the dynamic expected safety index R using the following formula _s ：

Wherein E is _s For the traffic risk assessment value in the current traffic scenario,

and evaluating a reference value for the traffic risk in the reference traffic scene.

An embodiment of the present invention further provides a traffic risk assessment apparatus, including:

a processor; and

a memory having computer program instructions stored therein,

wherein the computer program instructions, when executed by the processor, cause the processor to perform the steps of the traffic risk assessment method as described above.

Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the processor is caused to execute the steps in the traffic risk assessment method as described above.

The embodiment of the invention has the following beneficial effects:

according to the scheme, the characteristics of the traffic scene are described by operating the design domain elements, the type of the traffic scene is determined according to the characteristics of the traffic scene, the traffic participants in the traffic scene are determined according to the type of the traffic scene, then the motion information of all the traffic participants including pedestrians and vehicles can be obtained, the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants are respectively calculated according to the motion information of the traffic participants, the dynamic expected safety index is calculated according to the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants, the safety condition in the traffic scene can be rapidly evaluated, the vehicle route planning is valuable, and traffic managers can be helped to reasonably plan traffic and predict intervention; through two indexes of the complexity of elements of a traffic scene and the potential collision degree of traffic participants, the influence possibly generated by the interaction of danger, vulnerability and exposure level is considered, and the risk of a traffic area is measured. Through the technical scheme of this embodiment, can carry out the long time domain risk assessment of traffic scene under the restriction of operation design domain, promote the further development of autopilot vehicle and networking environment, improve road traffic safety nature.

Drawings

FIG. 1 is a schematic flow chart of a traffic risk assessment method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of the domain elements of the operational design of an embodiment of the present invention;

FIG. 3 is a block diagram of a system for traffic risk assessment according to an embodiment of the present invention;

FIG. 4 is a schematic illustration of different types of traffic scenarios;

FIG. 5 is a schematic illustration of locations of traffic participants in a traffic scene;

FIG. 6 is a schematic flow chart illustrating a traffic risk assessment method according to another embodiment of the present invention;

FIG. 7 is a block diagram of a traffic risk assessment apparatus according to an embodiment of the present invention;

fig. 8 is a schematic composition diagram of a traffic risk assessment apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the technical problems, technical solutions and advantages to be solved by the embodiments of the present invention clearer, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.

With the rapid development of the internet technology, the intelligent traffic system can realize the prediction and analysis of road hazards and avoid possible hazards by arranging various sensors, communication systems and control systems. However, the autonomous vehicles, which are main traffic participants in the intelligent traffic system, operate in a wide and complex dynamic environment, and the interaction between different road users in the traffic environment will easily cause decision conflict, thereby bringing about potential traffic accidents. Therefore, to implement a truly safe intelligent transportation system, all overlapping conditions, use cases, limitations, and scenarios that may be encountered by autonomous vehicles, the primary transportation participants thereof, need to be defined in detail. Meanwhile, traffic data sets in traffic environments contain rich information, but how to extract relevant information and associate the data with risks is a technical problem to be solved. In addition, the action relationship considered in the related art in evaluating the traffic risk is limited to the inter-vehicle relation, and the action relationship of the vehicle and other traffic participants is not sufficiently considered.

In consideration of the safety of the intelligent traffic system and the operation conditions of automatic driving, in a dynamic change environment, the automatic driving vehicle needs to be fully ensured to be always within the operation design domain range, and the traffic system is ensured to be always at a safety threshold value through risk study and judgment analysis in a long time domain.

The embodiment of the invention provides a traffic risk assessment method and device, which can accurately evaluate traffic risks.

Example one

An embodiment of the present invention provides a traffic risk assessment method, as shown in fig. 1, including:

step 101: describing the characteristics of the traffic scene by operating the design domain elements, and determining the type of the traffic scene according to the characteristics of the traffic scene;

as shown in fig. 2 and fig. 3, in the present embodiment, an architecture of an Operational Design Domain (ODD) is defined. The operational design domain primarily details all overlapping conditions, use cases, limitations and scenarios, and even marginal cases, that may be encountered by a traffic participant, such as an autonomous vehicle. The operational design domain defines not only the functional requirements of the subsystem components responsible for performing Dynamic Driving Task (DDT) and dynamic driving task support (DDT Fallback), but also the functional requirements of the subsystem components responsible for operational design domain monitoring. For any road traffic system, the traffic scene of the running of the vehicles can be limited by defining the running design domain architecture of the traffic environment.

S11, in this embodiment, the characteristics of the traffic scene are described by operating the design domain elements, as shown in table 1, the operating the design domain elements at least include:

TABLE 1 run design Domain elements

Wherein, the traffic participants comprise vehicles, pedestrians, cyclists, animals and the like; the infrastructure comprises navigation auxiliary identification, traffic management equipment, an isolation area and special road use rules; the road environment terrain on the current and predicted paths comprises lane types and the related road types, gradients, camber, curvature, inclination, road friction coefficients, road structures, lane speed limit information, road surface roughness and air density position elements; 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, among others.

After the characteristics of the system operation environment are described by using the operation design domain elements, according to the actual traffic scene, traffic participants such as automatic driving vehicles and the like not only need to normally run in a typical highway scene, but also need to safely operate in a complex environment and danger, and meanwhile, the complex system forming the automatic driving vehicles also needs to ensure the safety when the system fails. Therefore, as shown in fig. 4, according to the complexity level of the ODD elements, the traffic scene may be divided into a typical traffic scene, a dangerous traffic scene and an edge case scene, although the type of the traffic scene is not limited thereto, and may further include more types of traffic scenes, and the embodiment is only described by taking the example that the traffic scene includes the typical traffic scene, the dangerous traffic scene and the edge case scene. In this embodiment, a typical traffic scene may be a typical highway scene, a dangerous traffic scene may be a traffic scene in which a traffic accident occurs, and an intersection may be an edge case scene.

Step 102: determining traffic participants in a traffic scene according to the type of the traffic scene;

after the type of the actual traffic scene is determined, the operation design domain elements under the actual traffic scene are classified and extracted, and the operation design domain boundary including the traffic participants in the traffic scene can be determined. For example, in a typical traffic scenario, traffic participants in a typical traffic scenario may include only vehicles, as pedestrians, animals, cyclists, etc. are not typically present on highways; in the edge case scenario, the traffic participants in the edge case scenario include pedestrians, animals, cyclists, vehicles, as pedestrians, animals, cyclists, vehicles may all be present at the intersection.

Step 103: acquiring the motion information of the traffic participants, and respectively calculating the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants according to the motion information of the traffic participants;

the method comprises the steps of constructing an optimal arrangement scheme of traffic environment roadside sensors with low cost and global perception coverage in advance under the framework of a running design domain, and acquiring motion information of traffic participants in a traffic scene through a vehicle-mounted sensor and the roadside sensors, wherein the roadside sensors can be roadside cameras, and the vehicle-mounted sensors comprise radars and vehicle-mounted cameras. As shown in fig. 2, the requirements for sensors within the sensing subsystem may be: detecting traffic objects within a range of 50 m; the roadside sensor full coverage traffic scene is realized; for the vehicle-mounted sensor, a left-direction radar, a right-direction radar and a forward-direction radar are collocated.

In this embodiment, the execution object of the traffic risk assessment may be a vehicle, such as an autonomous vehicle, or may be a traffic monitoring platform.

When the object of execution of the traffic risk assessment is a vehicle, the vehicle should prioritize the entities at risk of collision, which, as shown in fig. 2, include dynamic objects (e.g. features of (vulnerable) road users and corresponding movements), static instances (e.g. road boundaries, traffic guidance and communication signals) and obstacles. The traffic participants concerned by the vehicle may only include the traffic participants around the vehicle, because the traffic participants may cause a risk to the driving of the vehicle, the vehicle only needs to acquire the motion information of the surrounding traffic participants, the vehicle may acquire the motion information of the surrounding traffic participants by the road side sensors and other vehicle-mounted sensors through the internet technology, and may also acquire the motion information of the surrounding traffic participants through the vehicle-mounted sensors. The distance between the traffic participants around the vehicle and the vehicle is smaller than a preset value, and the value of the preset value can be adjusted according to different traffic scenes, for example, the preset value can be 500m in a typical traffic scene, and the preset value can be 200m in an edge case scene.

When the object of execution of the traffic risk assessment is a traffic monitoring platform, the traffic monitoring platform should prioritize entities at risk of collision, which include dynamic objects (e.g. road users (vulnerable) and characteristics of the corresponding movements), static instances (e.g. road borders, traffic guidance and communication signals) and obstacles, as shown in fig. 2. The traffic participants concerned by the traffic monitoring platform can be the traffic participants in the whole traffic scene, and the traffic monitoring platform can obtain the motion information of the traffic participants in the whole traffic scene through the network connection technology by acquiring the roadside sensors and the vehicle-mounted sensors.

The motion information of the traffic participant includes, but is not limited to, a position, a speed, an acceleration, a distance from other traffic participants, and the like.

The roadside sensor can shoot effective motion information of a traffic participant, management of an operation design domain is supported, potential regions possibly containing shielding objects need to be considered, and in a certain range, installation parameters of the roadside sensor have certain influence on the perception performance of the roadside sensor. And the operation design domain management can put forward different requirements on the sensing performance of the roadside sensor under different conditions, and analyze the detection range, the detection reliability, the accuracy and the precision, the false positive and the false negative and the sensing delay of the roadside sensor. Secondly, the perception performance under specific environment and scene can be further analyzed according to the scene that the deployed roadside sensor can cover.

For example, in a typical traffic scene, due to high dynamic and strong randomness of a highway, when the motion states of other surrounding vehicles change, if the own vehicle does not respond correctly in a short time, an accident is easily caused. Therefore, in the driving process, the motion information of surrounding vehicles is acquired in real time, and after the current driving risk is accurately evaluated (according to the dynamic traffic information of the highway), corresponding decision-making actions (such as acceleration and deceleration) are made, so that the driving safety can be effectively ensured. Therefore, it is necessary to make demands according to the mapping relationship between the operating design domain elements and the perception subsystem demands.

The information required by the expressway scene can be acquired in real time through the road side sensor and the vehicle-mounted sensor on the own vehicle through a traffic monitoring visual angle or a vehicle-mounted visual angle, the longitudinal and transverse speeds, the longitudinal and transverse coordinates and the wheel (steering wheel) rotation angle information of the own vehicle and the surrounding vehicles, and part of acquired information tables are shown in table 2.

TABLE 2 respective start and end status information

The definition of the operation design domain elements mainly comprises the following steps: road structure (terrain and associated location features), ambient weather conditions (surface temperature, air temperature, wind, visibility, lighting, etc.), traffic participants (pedestrians, motor vehicles, cyclists, animals, etc.), infrastructure (navigation aids, traffic management devices, etc.), etc. According to the operation design domain elements, the requirements for the perception subsystem comprise: 1) the detection range is within 50m, 2) the left-direction radar, the right-direction radar and the forward-direction radar are matched, and 3) the roadside sensor fully covers traffic scenes and the like. Whereas the main concern object collision risk entity requirements mainly include two categories: 1) characteristics of dynamic object (vulnerable) road users and corresponding movements; 2) static examples (road boundaries, traffic guidance and communication signals) and obstacles, etc.

Step 104: and calculating a dynamic expected safety index according to the complexity of the traffic scene element and the potential collision degree of the traffic participants.

The evaluation indexes of the dynamic expected safety index comprise:

evaluation index 1: the complexity of the elements of the operation design domain in the traffic scene, that is, the complexity of the elements of the traffic scene, can be understood as the difficulty and complexity of identifying the coupling information between the traffic participants and the surrounding environment due to dynamic changes under specific conditions. Traffic data sets contain rich information, with the location, time, and other environmental factors of the traffic participants in the area changing the risk. Thus extracting relevant information and associating these data with risks. The present embodiment may propose to analyze the vehicle driving data using a risk level set based on natural driving data, such as data sets like highD, NGSIM, Interaction dataset, etc., and extract relevant parameters to calculate the risk online.

Evaluation index 2: the potential collision degree of the traffic participant in the traffic scene can also be the potential injury degree of the traffic participant. The risk degree of the traffic scene needs to be analyzed from the statistical perspective by adding additional statistical data and external sources within a long time domain range, and the probability of occurrence of the traffic accident and the severity of the accident are analyzed.

The consideration of the environment dynamic complexity is due to the complexity change of the running design domain caused by the diversity and difference of the interrelations between different nodes and the uncertainty in the dynamic running process. Thus, a major factor affecting the complexity of the dynamically operating design domain is the nodal relationships of the different traffic participants between the traffic subsystems, i.e., the connections between abstract nodes. The embodiment converts the measurement of the element complexity of the dynamic operation design domain intoThe measurement of the connection between the nodes is changed, the two evaluation indexes are comprehensively considered, and the dynamic expected safety index is used

To characterize long-term comprehensive risks of traffic scenarios, wherein,

evaluation of the reference value for the traffic risk, E _s Is a traffic risk assessment value.

Based on the evaluation index 1, the complexity of the elements of the operation design domain in the traffic scene is judged as shown in table 3:

TABLE 3 run design Domain element complexity differentiation

As shown in fig. 5, based on the evaluation index 1 defined above, all traffic participants in the traffic environment are treated as a single traffic participant O in consideration of the interaction of all traffic participants in the traffic scene with the environment _i The position is set as (x) _i ，y _i ) X is a position in a direction perpendicular to the lane (lateral direction), and y is a position in a direction parallel to the lane (longitudinal direction). Considering the traffic scenario I, for any traffic participant O in the traffic scenario I _i I ∈ {1, 2., n }, all satisfy O _i E.g. I. The dynamics information of any traffic participant is considered, and the participants are modeled by adopting double-integral dynamics, so that the following requirements are met:

wherein v is _xi ，v _yi Are respectively an object O _i Transverse and longitudinal speeds of a _xi ，a _yi Are respectively an object O _i Lateral and longitudinal acceleration of (a). In this embodiment, the speed and the acceleration of the traffic participant both satisfy the maximum dynamic constraint limit, and meanwhile, the speed of the traffic participant should also satisfy the limit of the traffic rule, for example, satisfy the limit of the lane to the lowest speed and the highest speed.

It is assumed that all traffic participants are self-protected, i.e. as long as there is sufficient braking distance, one traffic participant stops to avoid a collision with another traffic participant. Meanwhile, the cost of each traffic participant on the road and the complexity of the whole road environment operation design domain are calculated, so that the risk of each vehicle is evaluated at each point in the data set. The characteristics adopted by the embodiment for traffic risk assessment include: the lateral road location (such as the lane in which it is located), the longitudinal and lateral speed, the relative distance between the participants, and the type of participants in the traffic zone. These features are typically used for behavior and maneuver classification of vehicles, and thus traffic risks and potential relationships between these features need to be considered. In summary, the index of the element complexity of the operation design domain can be characterized as follows:

wherein m represents the number of types of different traffic participants i in the traffic scene,

representing the number of traffic participants j of the same type, i and j representing different traffic participants, H _D Entropy values representing the complexity of the elements of the run design domain.

When there is an interaction between two traffic participants, for example, there is a coupling relationship d between the ith traffic participant and the jth traffic participant _ij The more coupling relationships, the more complex the traffic system operational design domain, and thus, the coupling relationships can be used to measure the complexity of the traffic system operational design domain, where d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，v _xj ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _i 、y _j Are respectively traffic participants O _i Lateral and longitudinal road positions on the lane, v _xi 、v _yi Are respectively traffic participants O _i Lateral and longitudinal velocities under maximum dynamic constraints and traffic regulation limits are satisfied.

Based on the above defined evaluation index 2, the severity of injury/collision of the traffic participant in the traffic scene can be measured by the definition of the field strength. In order to evaluate the safety state of the traffic environment, traffic system risks are defined as the interaction between the research objects based on the driving safety field, and the evaluation index 2 is output by analyzing the injury/collision severity of the traffic participants and analyzing the relation between force work and energy conversion in the collision process. Wherein forces F between different traffic participants _ij Can be described as:

wherein x is _ji ，y _ji Respectively represent the jth traffic participant O _j With the ith traffic participant O _i In the transverse and longitudinal directions, r _max For the free-flow inter-vehicle distance, to represent the maximum impact range of the risk, r is defined according to the road traffic manual _max In this embodiment, r can be set _max 15 m. Wherein k is _x，0 ，k _y，0 The present embodiment can set both of these values to 1 for the gradient adjustment coefficients in the lateral direction and the longitudinal direction, respectively. r is ₀ Is the radius of the driver's focus, which is related to the distance between the driver and the vehicle in the line of sight,this embodiment can be set to 8 m. v. of _j ，v _i Respectively represent the jth traffic participant O _j With the ith traffic participant O _i M, speed of movement of _j Represents the jth traffic participant O _j The larger the mass of the moving object is, and the larger the moving speed is, the larger the acting force is.

Of course, the forces F between different traffic participants _ji In addition to the above, other forms of description in the prior art may be used.

And (3) comprehensively considering the complexity of the elements of the traffic system operation design domain and the injury/collision severity of the traffic participants based on the evaluation indexes 1 and 2 defined above, and representing the long-time domain comprehensive risk of the traffic scene by using a dynamic expected safety index.

Firstly, the complexity E of the elements of the running design domain under any condition is obtained _D And stress situation of traffic participants E _f And running design domain element complexity under baseline conditions

And stress situation of traffic participants

Respectively setting as follows:

E _s ＝E _D +E _f

wherein the content of the first and second substances,

is E in the case of reference _s I.e. long time domain traffic risk assessment expectation in the baseline case. The traffic scene under the reference condition has the same road structure with the actual traffic scene, including the same terrain and related position characteristics, but the traffic scene under the reference condition has clear weather, flat road conditions and free flow of multiple vehicles. For example, for a typical traffic scene, the weather is clear, the road condition is flat, and the situation of free flow of multiple vehicles is taken as a reference under a standard highway scene.

Based on the above formula, the output of the result of the dynamic risk assessment for the traffic scene can be described as:

wherein E is _s Evaluating expected value, R, for long-term traffic risk in actual traffic scene _s For a dynamic desired safety index in real traffic scenarios,

evaluating expected value for long-term traffic risk in reference traffic scene, if R is _s The higher the risk level of the traffic system.

Of course, R may also be _s Is described as

And E _s Other forms of relevance.

After obtaining the dynamic desired security index, as shown in fig. 6, the method further comprises:

step 105: and when the dynamic expected safety index is larger than or smaller than a preset threshold value, reminding the traffic participants to avoid.

Wherein, if

And when the dynamic expected safety index is smaller than a preset threshold value, reminding the traffic participants to avoid. The preset threshold value can be set according to actual conditions and can be in different classesThe preset thresholds corresponding to the traffic scenes of the types are different.

When the execution object of the traffic risk assessment is a vehicle, the vehicle-mounted system can remind a driver of avoiding, including detour, speed reduction and the like, after obtaining the dynamic expected safety index and judging that the dynamic expected safety index is greater than or less than a preset threshold value; when the execution object of the traffic risk assessment is the traffic monitoring platform, the traffic monitoring platform can remind traffic participants in a traffic scene to avoid the situation including detour, speed reduction and the like after obtaining the dynamic expected safety index and judging that the dynamic expected safety index is larger than or smaller than a preset threshold value, for example, the traffic monitoring platform can send information to a vehicle-mounted system to remind a driver of a vehicle.

In the embodiment, the traffic information can be acquired in real time by arranging the sensors, the long-time-domain traffic state can be counted in real time, the safety situation change can be judged, and finally the long-time-domain risk level of the intelligent traffic environment can be output.

The method comprises the steps of describing characteristics of a traffic scene by operating design domain elements, determining the type of the traffic scene according to the characteristics of the traffic scene, determining traffic participants in the traffic scene according to the type of the traffic scene, then obtaining motion information of all the traffic participants including pedestrians and vehicles, respectively calculating complexity of the elements of the traffic scene and potential collision degree of the traffic participants according to the motion information of the traffic participants, calculating a dynamic expected safety index according to the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants, rapidly evaluating safety conditions in the traffic scene, and not only having great value for vehicle route planning, but also helping traffic controllers to reasonably carry out traffic planning and predict when to intervene; through two indexes of the complexity of elements of a traffic scene and the potential collision degree of traffic participants, the influence possibly generated by the interaction of danger, vulnerability and exposure level is considered, and the risk of a traffic area is measured. Through the technical scheme of this embodiment, can carry out the long time domain risk assessment of traffic scene under the restriction of operation design domain, promote the further development of autopilot vehicle and networking environment, improve road traffic safety nature.

Example two

An embodiment of the present invention further provides a traffic risk assessment apparatus, as shown in fig. 7, including:

the first processing module 21 is used for describing the characteristics of the traffic scene by operating the design domain elements and determining the type of the traffic scene according to the characteristics of the traffic scene;

a second processing module 22, configured to determine a traffic participant in a traffic scene according to the type of the traffic scene;

the motion information acquisition module 23 is used for acquiring motion information of the traffic participants;

the first calculation module 24 is used for calculating the complexity of the traffic scene element and the potential collision degree of the traffic participant according to the motion information of the traffic participant;

and a second calculating module 25, configured to calculate a dynamic expected safety index according to the complexity of the traffic scene element and the potential collision degree of the traffic participant.

In some embodiments, the apparatus further comprises:

E _s ＝E _D +E _f ；

The first calculation module is specifically used for calculating the complexity E of the traffic scene element by adopting the following formula _D Potential collision with traffic participantsDegree of impact E _f ：

Wherein d is _ij Representing the ith traffic participant O in the traffic scene _i With the jth traffic participant O _i Coupling relationship between d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，v _xj ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _j 、y _j Are respectively traffic participants O _j Lateral and longitudinal road positions on the lane, v _xi 、v _yi Are respectively traffic participants O _i Transverse and longitudinal velocities, v, under the constraint of satisfying maximum dynamics and traffic regulations _xi 、v _yj Are respectively traffic participants O _j The transverse speed and the longitudinal speed under the condition of meeting the maximum dynamic constraint and the traffic regulation limit, m represents the types and the number of different traffic participants in the traffic scene, n is the number of the traffic participants,

Wherein x is _ji ，y _ji Respectively represent the jth traffic participant O _j With the ith traffic participant O _i Transverse and longitudinal directions ofA distance of (a) r _max For free-flow vehicle spacing, k _x，0 ，k _y，0 Gradient adjustment coefficients, r, in the transverse and longitudinal directions, respectively ₀ Is the radius of the driver's focus, v _j ，v _i Respectively represent the jth traffic participant O _j With the ith traffic participant O _i M, speed of movement of _j Represents the jth traffic participant O _j The quality of (c).

In the embodiment, the characteristics of a traffic scene are described by operating design domain elements, the type of the traffic scene is determined according to the characteristics of the traffic scene, traffic participants in the traffic scene are determined according to the type of the traffic scene, then motion information of all the traffic participants including pedestrians and vehicles can be obtained, the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants are respectively calculated according to the motion information of the traffic participants, a dynamic expected safety index is calculated according to the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants, the safety condition in the traffic scene can be quickly evaluated, the vehicle route planning is valuable, and traffic managers can be helped to reasonably plan traffic and predict when to intervene; through two indexes of the complexity of elements of a traffic scene and the potential collision degree of traffic participants, the influence possibly generated by the interaction of danger, vulnerability and exposure level is considered, and the risk of a traffic area is measured. Through the technical scheme of this embodiment, can carry out the long time domain risk assessment of traffic scene under the restriction of operation design domain, promote the further development of autopilot vehicle and networking environment, improve road traffic safety nature.

EXAMPLE III

An embodiment of the present invention further provides a traffic risk assessment apparatus 30, as shown in fig. 8, including:

a processor 32; and

a memory 34, in which memory 34 computer program instructions are stored,

wherein the computer program instructions, when executed by the processor, cause the processor 32 to perform the steps of:

In the embodiment, the characteristics of a traffic scene are described by operating design domain elements, the type of the traffic scene is determined according to the characteristics of the traffic scene, traffic participants in the traffic scene are determined according to the type of the traffic scene, then the motion information of all the traffic participants including pedestrians and vehicles can be obtained, the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants are respectively calculated according to the motion information of the traffic participants, a dynamic expected safety index is calculated according to the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants, the safety condition in the traffic scene can be rapidly evaluated, the vehicle route planning is valuable, and traffic managers can be helped to reasonably plan traffic and predict intervention; through two indexes of the complexity of elements of a traffic scene and the potential collision degree of traffic participants, the influence possibly generated by the interaction of danger, vulnerability and exposure level is considered, and the risk of a traffic area is measured. Through the technical scheme of this embodiment, can carry out the long time domain risk assessment of traffic scene under the restriction of operation design domain, promote the further development of autopilot vehicle and networking environment, improve road traffic safety nature.

Further, as shown in fig. 8, the traffic risk assessment apparatus 30 further includes a network interface 31, an input apparatus 33, a hard disk 35, and a display apparatus 36.

The various interfaces and devices described above may be interconnected by a bus architecture. A bus architecture may be any architecture that may include any number of interconnected buses and bridges. Various circuits of one or more Central Processing Units (CPUs), represented in particular by processor 32, and one or more memories, represented by memory 34, are coupled together. The bus architecture may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like. It will be appreciated that a bus architecture is used to enable communications among the components. The bus architecture includes a power bus, a control bus, and a status signal bus, in addition to a data bus, all of which are well known in the art and therefore will not be described in detail herein.

The network interface 31 may be connected to a network (e.g., the internet, a local area network, etc.), and may acquire relevant data from the network, such as data of a roadside sensor and data of an on-board sensor, and may store the relevant data in the hard disk 35.

The input device 33 can receive various commands input by the operator and send the commands to the processor 32 for execution. The input device 33 may comprise a keyboard or a pointing device (e.g., a mouse, a trackball (trackball), a touch pad or a touch screen, etc.

The display device 36 may display the results of the instructions executed by the processor 32.

The memory 34 is used for storing programs and data necessary for operating the operating system, and data such as intermediate results in the calculation process of the processor 32.

It will be appreciated that memory 34 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. The memory 34 of the apparatus and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some embodiments, memory 34 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof: an operating system 341 and application programs 342.

The operating system 341 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application 342 includes various applications, such as a Browser (Browser), and the like, for implementing various application services. A program implementing the method of an embodiment of the present invention may be included in the application 342.

The processor 32, when invoking and executing the application program and data stored in the memory 34, may specifically describe characteristics of a traffic scene by running design domain elements, and determine the type of the traffic scene according to the characteristics of the traffic scene; determining traffic participants in a traffic scene according to the type of the traffic scene; acquiring the motion information of the traffic participants, and respectively calculating the complexity of the elements of the traffic scene and the potential collision degree of the traffic participants according to the motion information of the traffic participants; and calculating a dynamic expected safety index according to the complexity of the traffic scene element and the potential collision degree of the traffic participants.

The methods disclosed in the above embodiments of the present invention may be implemented in the processor 32 or by the processor 32. The processor 32 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 32. The processor 32 may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, configured to implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 34, and the processor 32 reads the information in the memory 34 and completes the steps of the method in combination with the hardware thereof.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the processing units may be implemented within 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, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.

For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.

Specifically, the processor 32 is further configured to prompt the traffic participant to avoid when the dynamic expected safety index is greater than or less than a preset threshold.

Specifically, the processor 32 is further configured to obtain a traffic risk assessment benchmark value in a benchmark traffic scene; calculating a traffic risk assessment value under the current traffic scene according to the element complexity of the traffic scene and the potential collision degree of the traffic participants; and calculating a dynamic expected safety index according to the traffic risk assessment reference value and the traffic risk assessment value.

Specifically, processor 32 calculates E using the following equation _s 、E _D And E _f ：

E _s ＝E _D +E _f

Wherein d is _ij Representing the ith traffic participant O in the traffic scene _i With the jth traffic participant O _i Coupling relationship between d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，v _xj ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _j 、y _j Are respectively traffic participants O _j Lateral and longitudinal road positions on the lane, v _xi 、v _yi Are respectively traffic participants O _i Transverse and longitudinal velocities, v, under the constraint of satisfying maximum dynamics and traffic regulations _xj 、v _yj Are respectively traffic participants O _j The transverse speed and the longitudinal speed under the condition of meeting the maximum dynamic constraint and the traffic regulation limit, m represents the types and the number of different traffic participants in the traffic scene, n is the number of the traffic participants,

Specifically, processor 32 calculates forces F between the various participants using the following equation _ij ：

Specifically, processor 32 calculates a dynamic expected safety index R using the following equation _s ：

Example four

An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the processor is caused to execute the following steps:

Further, the computer program, when executed by a processor, further causes the processor to perform the steps of:

acquiring a traffic risk assessment reference value in a reference traffic scene;

calculate E using the following formula _s 、E _D And E _f ：

E _s ＝E _D +E _f

Wherein d is _ij Representing the ith traffic participant O in the traffic scene _i With the jth traffic participant O _i Coupling relationship between d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，v _xj ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _j 、y _j Are respectively traffic participants O _j Lateral and longitudinal road positions on the lane, v _xi 、v _yi Are respectively traffic participants O _i Transverse and longitudinal velocities, v, under the constraint of satisfying maximum dynamics and traffic regulations _xj 、v _yj Are respectively traffic participants O _j Transverse and longitudinal speeds under the constraint of satisfying maximum dynamics and traffic regulations, m represents the types of different traffic participants in the traffic sceneThe number n is the number of the traffic participants,

the following formula is adopted to calculate the acting force F between different traffic participants _ij ：

the dynamic expected safety index R is calculated by adopting the following formula _s ：

The foregoing is a preferred embodiment of the present invention, and it should be noted that it is obvious to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and these modifications and improvements should be construed as the protection scope of the present invention.

Claims

1. A traffic risk assessment method, comprising:

2. The traffic risk assessment method according to claim 1, further comprising:

3. The traffic risk assessment method according to claim 1, wherein said operating design domain elements comprise: road structure, traffic participants, infrastructure, environmental and weather conditions.

4. The traffic risk assessment method according to claim 1, further comprising obtaining a traffic risk assessment reference value in a reference traffic scene;

5. The traffic risk assessment method according to claim 4, wherein the complexity E is determined according to the traffic scene element _D And potential collision degree E of traffic participants _f Calculating traffic risk assessment value E under current traffic scene _s The method comprises the following steps:

calculate E using the following formula _s 、E _D And E _f ：

E _s ＝E _D +E _f

Wherein d is _ij Representing the ith traffic participant O in the traffic scene _i With the jth traffic participant O _j Coupling relationship between d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，v _xj ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _j 、y _j Are respectively traffic participants O _j Lateral and longitudinal road positions on the lane, v _xi 、v _yi Are respectively traffic participants O _i Transverse and longitudinal velocities, v, under the constraint of satisfying maximum dynamics and traffic regulations _xj 、v _yj Are respectively traffic participants O _j The transverse speed and the longitudinal speed under the condition of meeting the maximum dynamic constraint and the traffic regulation limit, m represents the types and the number of different traffic participants in the traffic scene, n is the number of the traffic participants,

representing the number of traffic participants of the same type, F _ij Representing the jth traffic participant O in a traffic scene _j With the ith traffic participant O _i To the force of the other.

6. The traffic risk assessment method according to claim 5, characterized in that the following formula is used to calculate the forces F between different traffic participants _ij ：

7. The traffic risk assessment method according to claim 4, characterized in that, the traffic risk assessment reference value is based on

8. A traffic risk assessment apparatus, comprising:

9. The traffic risk assessment device according to claim 8, further comprising:

10. The traffic risk assessment device according to claim 8, further comprising:

11. The traffic risk assessment device according to claim 10, wherein said second calculation module is specifically configured to calculate the traffic risk assessment value E under the current traffic scene by using the following formula _s ：

E _s ＝E _D +E _f ；

The first calculation module is specifically used for calculating the complexity E of the traffic scene element by adopting the following formula _D And potential collision degree E of traffic participants _f ：

Wherein d is _ij Representing the ith traffic participant O in the traffic scene _i With the jth traffic participant O _j Coupling relationship between d _ij Is dependent on (x) _i ，y _i ，v _xi ，v _yi ) And (x) _j ，y _j ，v _xj ，v _yj )，x _i 、y _i Are respectively traffic participants O _i Transverse and longitudinal road positions on the lane, x _j 、y _j Are respectively traffic participants O _j Lateral and longitudinal road positions on the lane, v _xi 、v _yi Are respectively traffic participants O _i Transverse and longitudinal velocities, v, at the maximum kinetic and traffic regulation limits _xj 、v _yj Are respectively traffic participants O _j Meet the maximum dynamic constraint and crossAccording to the transverse speed and the longitudinal speed under the regulation limit, m represents the types and the number of different traffic participants in the traffic scene, n is the number of the traffic participants,

12. The traffic risk assessment device according to claim 11, wherein said first calculation module is specifically configured to calculate the force F between different traffic participants using the following formula _ij ：

13. The traffic risk assessment device according to claim 10, wherein said second calculation module is specifically configured to calculate the dynamic desired safety index R using the following formula _s ：

Wherein E is _s For the current transactionThe traffic risk assessment value in the general scene,