Unified identification method of traffic conflicts on straight sections without distinguishing traffic conflict types

Abstract

The present invention proposes a unified identification method for traffic conflicts on straight road sections that does not distinguish between traffic conflict types. There is no need to pre-identify the conflict type, and there are no strict requirements on the driving direction, the number of lanes, and the number and type of motor vehicles. A unified traffic conflict identification model is constructed, and the potential collision time TU is calculated. Based on the vehicle status at each moment during the conflict process, a complete risk metric within the duration of the conflict is identified. The present invention can quickly and accurately estimate the risk level of collision between vehicles, greatly improving the speed and accuracy of traffic conflict identification, and creating a new direction for identifying traffic conflicts without pre-identifying the conflict type.

Description

Technical Field

[0001] The present application relates to the technical field of traffic safety risk identification, and in particular to a unified identification method for traffic conflicts on straight road sections that do not distinguish between traffic conflict types. Background Art

[0002] Commonly used traffic conflict identification methods in TCT (Traffic conflict technology) include TTC (Time to Collision), PET (Post Encroachment Time), and DRAC (Deceleration rate to avoid crash). These methods have good identification effects within their respective scopes of application, but their identification effects outside of their scopes need to be improved. As the scope of TCT application expands, the scenarios it faces are gradually shifting from single scenarios to complex scenarios such as merging areas and weaving areas. Complex scenarios frequently involve multiple types of conflicts, such as following vehicles, changing lanes, and merging. For conflict identification where multiple types of conflicts coexist, existing conflict identification methods urgently need to be expanded and their adaptability enhanced.

[0003] The current single method and combined method identification have certain defects:

[0004] (1) For multiple types of traffic conflicts in specific scenarios, a single method has different defects when identifying them. Methods such as PET, TTC, and DRAC are better at identifying following vehicle conflicts based on the time difference in passing through public areas, the time from the potential collision point, and the vehicle's own motion characteristics. However, they are not very accurate in identifying lane change conflicts. In particular, DRAC is limited by its definition and is almost only used for identifying following vehicle conflicts. The reason is that the collision conditions in the lane change state are more complex, and the accurate potential collision point is difficult to estimate;

[0005] (2) In order to identify multiple types of conflicts in complex scenarios, some scholars have used the advantages of a single method in identifying different types of conflicts and adopted a combination of multiple single methods to measure the risk level between vehicles. They directly use multiple single methods to identify traffic conflicts and comprehensively measure the risk based on the identification results of multiple single methods, such as using TTC to identify following conflicts and TDTC (Time Difference to Collision) to identify lane change conflicts. The combination method can retain the advantages of a single method, thus improving the effect of identifying multiple types of conflicts. However, there is no unified and clear distinction between following conflicts and lane change conflicts, and this superimposed combination method still needs to first identify the conflict type and adopt different methods for vehicles of different conflict types, resulting in inaccurate results.

[0006] Conventional superposition and combination methods only mitigate or even retain the shortcomings of a single method. However, due to the difficulty in distinguishing conflict types, conflict identification becomes more complex and difficult to apply universally. To achieve multi-type conflict identification in complex scenarios, a unified identification method based on different traffic conflict types is still needed. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to provide a unified identification method for traffic conflicts on straight road sections that does not distinguish between traffic conflict types in response to the above-mentioned problems. By constructing a unified traffic conflict identification model, traffic conflicts can be directly identified without pre-determining the conflict type.

[0008] The embodiment of the present application is implemented as follows:

[0009] The present invention provides a unified method for identifying traffic conflicts on straight road sections regardless of the type of traffic conflict, which includes the following steps:

[0010] Step a: Determine the collision conditions between the front vehicle A and the rear vehicle B:

[0011] The following, lane-changing, and crossing movements of vehicles on the road are described as planar motions of the vehicles in a two-dimensional coordinate system. Furthermore, the conflicting vehicles are projected onto the x-axis and y-axis of the coordinate system. When there is no potential collision between the conflicting vehicles, at least one of the projections on the x-axis and y-axis does not overlap. When there is a potential collision between the conflicting vehicles, the projections on both one-dimensional directions overlap. That is, the condition for a potential collision between the conflicting vehicles is described as the simultaneous overlap of the projections of the two vehicles on the x-axis and y-axis.

[0012] Step b: Identify the collision risk between vehicle A and vehicle B:

[0013] Step b1: Project the front vehicle A and the rear vehicle B onto the x and y axes:

[0014] The current positions of the vehicles are and The current speeds of the vehicles are , the decomposed velocity in the x-axis and y-axis directions is , the projection boundary points of vehicle A on the x-axis and y-axis can be obtained by projecting the vehicle. ,make 、 The four boundary points are respectively called the front and rear of the projection of car A on the x-axis, and the front and rear of the projection on the y-axis; similarly, the boundary points of the projection of car B on the x-axis and y-axis are ,make 、 , the four boundary points are respectively called the front and rear of car B projected on the x-axis, and the front and rear of car B projected on the y-axis;

[0015] Step b2: Determine the vehicle projection overlap parameters:

[0016] is the minimum displacement that the vehicle projection in the x-axis direction needs to overcome from the judgment moment to the start of overlap, The minimum displacement that needs to be overcome in the x-axis direction from the moment the vehicle projections begin to overlap until they separate again after overlapping; The distance between vehicles is reduced in the x-axis direction 、 the time required; is the minimum displacement that the vehicle projection in the y-axis direction needs to overcome from the judgment moment to the start of overlap, The minimum displacement that needs to be overcome in the y-axis direction from the moment the vehicle projections begin to overlap until they separate again after overlapping; The distance between vehicles is reduced in the y-axis direction 、 The time required; the above eight parameters are for identifying vehicle projection overlap parameters;

[0017] Step c: Determine whether the vehicle's projections on the x and y axes overlap at the same time:

[0018] based on The definition of , the time period when the projections of the two vehicles overlap in the x-axis direction is , the time period when the projections of the two vehicles overlap on the y-axis is The condition for a potential collision of conflicting vehicles is that the projections of the two vehicles on the x-axis and y-axis overlap at the same time, that is, the lower limit of the two time periods and None , and the two time periods and The intersection of is not an empty set; the intersection corresponds to the duration of a potential collision between two vehicles in theory. The potential collision time is the time required for a collision to occur. The potential collision time is TU is the lower limit of the intersection, and the conflict identification formula is shown as follows;

[0019] .

[0020] In some optional embodiments, step b2 The calculation process is as follows:

[0021] When the projections of the two vehicles overlap in the x-axis direction is 0; when the projections of the two vehicles do not overlap in the x-axis direction, is the distance from the front of the rear vehicle to the rear of the front vehicle in the x-axis direction, calculated using the projection boundary points , as follows:

[0022]

[0023] Where, is the distance from the front of vehicle A projected on the x-axis to the origin of the coordinate axis O, in meters; is the distance from the rear of car A projected on the x-axis to the origin of the coordinate axis O, in meters; is the distance from the front of vehicle B projected on the x-axis to the origin of the coordinate axis O, in meters; It is the distance from the rear of car B projected on the x-axis to the origin O of the coordinate axis, in meters.

[0024] In some optional embodiments, the step b2 The calculation process is as follows: According to The size of , the front-back relationship of vehicle coordinates and the size relationship of vehicle speed, There are four cases, as shown below:

[0025] .

[0026] In some optional embodiments, the step b2 The calculation process is as follows: it is affected by the positions of the two vehicles, whether the projections overlap at the current moment, and the speeds of the front and rear vehicles. It is divided into six cases, as shown below:

[0027] .

[0028] In some optional embodiments, the step b2 The calculation process is as follows:

[0029] The situation when there are non-infinite solutions is the same as The six cases involved are the same, as shown in the following formula:

[0030] .

[0031] In some optional embodiments, the step b2 The calculation formula is as follows:

[0032] .

[0033] In some optional embodiments, the step b2 The calculation formula is as follows:

[0034] .

[0035] In some optional embodiments, the step b2 The calculation formula is as follows:

[0036] .

[0037] In some optional embodiments, the step b2 The calculation formula is as follows:

[0038] .

[0039] In some optional embodiments, the lower limit of the intersection in step c must also be the lower limit of the two time periods. and One, based on the vehicle status at each moment during the conflict process, TU Identify the complete risk metric over the duration of the conflict as follows:

[0040] .

[0041] The beneficial effects of the present application are as follows: the present application provides a unified identification method for traffic conflicts on straight road sections that does not distinguish between traffic conflict types, which can better identify traffic conflicts, and the identification results are less affected by the pre-judgment of the conflict type, thereby being able to more accurately describe the risk level between vehicles and provide more appropriate guidance on the conflict type and risk avoidance behavior; at the same time, during the identification process, the unified identification method does not require pre-judgment of the conflict type, which reduces the complexity of multi-type conflict identification, makes risk identification simpler, and makes risk assessment faster; the present invention can improve the speed and accuracy of risk assessment of autonomous driving vehicles, thereby facilitating faster and more accurate decision-making in the trajectory and motion planning of autonomous driving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 This is a schematic diagram of the projection of the vehicle onto the x-axis and y-axis when no potential collision occurs in an embodiment of the present application;

[0044] Figure 2 This is a schematic diagram of the projection of a vehicle onto the x-axis and y-axis when a potential collision occurs in an embodiment of the present application;

[0045] Figure 3A schematic diagram of the coordinates and distances of projection boundary points in an embodiment of the present application;

[0046] Figure 4 For the embodiment of this application Schematic diagram of the future projection separation when the current vehicle projection overlaps;

[0047] Figure 5 For the embodiment of this application Schematic diagram of the separation of future projections when the current vehicle projections overlap. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0049] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application as claimed, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative effort shall fall within the scope of protection of the present application.

[0050] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not require further definition or explanation in subsequent drawings.

[0051] The features and performance of the present application are further described in detail below with reference to the embodiments.

[0052] This invention proposes a unified method for identifying traffic conflicts on straight sections, regardless of conflict type. This method is applicable to traffic conflict identification on straight sections, and has no strict requirements for conflict type, driving direction, number of lanes, or number and type of motor vehicles, making it highly universal. For example, if a basic straight section has several lanes and several motor vehicles, with following and lane-changing conflicts between them, the invention can quickly and accurately estimate the risk of collision between the vehicles, significantly improving the speed and accuracy of conflict identification. This method opens a new avenue for identifying traffic conflicts without prior identification of conflict type, and possesses extremely high scientific and practical value.

[0053] The specific steps include:

[0054] Step 1: Convert vehicle trajectory from two-dimensional to one-dimensional

[0055] This method describes the movement of vehicles on the road, such as following, changing lanes, and crossing, as planar motion of the vehicles in a two-dimensional coordinate system. Furthermore, the conflicting vehicles are projected onto the x-axis and y-axis of the coordinate system. For example, if A is the front vehicle and B is the rear vehicle, the specific conditions for identifying a collision are: when there is no potential collision between the conflicting vehicles, at least one of the projections on the x-axis and y-axis does not overlap, e.g. Figure 1 When a potential collision occurs between conflicting vehicles, the projections in both one-dimensional directions overlap, as shown in Figure 2 The condition for a potential collision of the conflicting vehicles is described as the simultaneous overlap of the projections of the two vehicles in the two one-dimensional directions of the x-axis and the y-axis.

[0056] Step 2: Identify the collision risk between vehicles A and B

[0057] 2.1 Projection of vehicles A and B onto the x and y axes

[0058] The current positions of the vehicles are and The current speeds of the vehicles are , the decomposed velocity in the x-axis and y-axis directions is , the projection boundary points of vehicle A on the x-axis and y-axis can be obtained by projecting the vehicle. ,make 、 The four boundary points are respectively called the front and rear of the projection of car A on the x-axis, and the front and rear of the projection on the y-axis; similarly, the boundary points of the projection of car B on the x-axis and y-axis are ,make 、 The four boundary points are called the front and rear of car B projected on the x-axis, and the front and rear of car B projected on the y-axis.

[0059] 2.2 Calculation of vehicle projection overlap parameters

[0060] is the minimum displacement that the vehicle projection in the x-axis direction needs to overcome from the judgment moment to the start of overlap, The minimum displacement that needs to be overcome in the x-axis direction from the moment the vehicle projections begin to overlap until they separate again after overlapping; The distance between vehicles is reduced in the x-axis direction 、 the time required; is the minimum displacement that the vehicle projection in the y-axis direction needs to overcome from the judgment moment to the start of overlap, The minimum displacement that needs to be overcome in the y-axis direction from the moment the vehicle projections begin to overlap until they separate again after overlapping; The distance between vehicles is reduced in the y-axis direction 、 The time required; the above eight parameters are the parameters for identifying vehicle projection overlap (see Figure 3 ).

[0061] 2.2.1 Calculation

[0062] When the projections of the two vehicles overlap in the x-axis direction is 0; when the projections of the two vehicles do not overlap in the x-axis direction, is the distance from the front of the rear vehicle to the rear of the front vehicle in the x-axis direction, calculated using the projection boundary points , as follows:

[0063]

[0064] Where, is the distance from the front of vehicle A projected on the x-axis to the origin of the coordinate axis O, in meters; is the distance from the rear of car A projected on the x-axis to the origin of the coordinate axis O, in meters; is the distance from the front of vehicle B projected on the x-axis to the origin of the coordinate axis O, in meters; It is the distance from the rear of car B projected on the x-axis to the origin O of the coordinate axis, in meters.

[0065] 2.2.2 Calculation

[0066] according to The size of , the front-back relationship of vehicle coordinates and the size relationship of vehicle speed, There are four cases, as shown below:

[0067] .

[0068] 2.2.3 Calculation

[0069] When the projections of the two vehicles overlap in the x-axis direction, There are two situations. One is that the speed of the rear car is greater than that of the front car, and the rear car will pass the front car. The distance from the rear of the following vehicle to the front of the preceding vehicle (see Figure 4 ); second, the speed of the rear car is lower than that of the front car, and the rear car will fall further behind the front car. The minimum distance required for the rear vehicle to completely lag behind the front vehicle, that is, the distance from the front of the rear vehicle to the rear of the front vehicle (see Figure 5 ). At this moment, the projections of the two vehicles on the x-axis do not overlap. is the distance from the front of the rear vehicle to the rear of the front vehicle. It can be divided into six cases depending on the positions of the two vehicles, whether the projections overlap at the current moment, and the speeds of the front and rear vehicles, as shown in the following formula:

[0070] .

[0071] 2.2.4 Calculation

[0072] is the minimum time required for the vehicle projections in the x-axis direction to separate again after overlapping, and the situation when it has a non-infinite solution is the same as The six cases involved are the same, as shown in the following formula:

[0073] .

[0074] 2.2.5 Calculation

[0075] The calculation formula is as follows:

[0076] .

[0077] 2.2.6 Calculation

[0078] The calculation formula is as follows:

[0079] .

[0080] 2.2.7 Calculation

[0081] The calculation formula is as follows:

[0082] .

[0083] 2.2.8 Calculation

[0084] The calculation formula is as follows:

[0085] .

[0086] Step 3: Determine whether the vehicle's projections on the x and y axes overlap at the same time

[0087] based on The definition of , the time period when the projections of the two vehicles overlap in the x-axis direction is , the time period when the projections of the two vehicles overlap on the y-axis is The condition for a potential collision of conflicting vehicles is that the projections of the two vehicles on the x-axis and y-axis overlap at the same time, that is, the lower limit of the two time periods and None , and the two time periods and The intersection of is not an empty set; the intersection corresponds to the duration of a potential collision between two vehicles in theory. The potential collision time is the time required for a collision to occur. The potential collision time is TU is the lower limit of the intersection, and the conflict identification formula is shown as follows;

[0088] .

[0089] Obviously, the lower limit of the intersection must also be one of the lower limits of the two time periods, so the above formula can be rewritten as follows:

[0090]

[0091] Based on the vehicle states at each moment during the conflict process, TU identifies the complete risk metric during the conflict duration.

Claims

1. A unified identification method for traffic conflicts on straight sections without distinguishing the types of traffic conflicts, characterized in that: The steps include: Step a, determine the collision conditions between the front vehicle A and the rear vehicle B: The following, lane changing and crossing movements of vehicles on the road are described as the planar movement of the vehicles in a two-dimensional coordinate system. The conflicting vehicles are further projected onto the x-axis and y-axis of the coordinate system respectively. When there is no potential collision between the conflicting vehicles, at least one of the projections on the x-axis and y-axis does not overlap. When there is a potential collision between the conflicting vehicles, the projections on both the x-axis and y-axis overlap. That is, the condition for the potential collision between the conflicting vehicles is described as the simultaneous overlap of the projections of the two vehicles on the x-axis and y-axis. Step b, identifying the collision risk between the front vehicle A and the rear vehicle B: Step b1, projection of the front vehicle A and the rear vehicle B onto the x and y axes: The current positions of the vehicles are and The current speeds of the vehicles are , the decomposed velocity in the x-axis and y-axis directions is , the projection boundary points of vehicle A on the x-axis and y-axis can be obtained by projecting the vehicle. ,make , The four boundary points are respectively called the front and rear of the projection of car A on the x-axis, and the front and rear of the projection on the y-axis; similarly, the projection boundary points of car B on the x-axis and y-axis are ,make , , the four boundary points are respectively called the front and rear of car B projected on the x-axis, and the front and rear of car B projected on the y-axis; Step b2, vehicle projection overlap parameters are determined: is the minimum displacement that the vehicle projection in the x-axis direction needs to overcome from the judgment moment to the start of overlap, The minimum displacement in the x-axis direction that needs to be overcome from the beginning of the overlap of the vehicle projections until the moment when the projections separate again after overlapping; The distance between vehicles is reduced in the x-axis direction , the time required; is the minimum displacement that the vehicle projection in the y-axis direction needs to overcome from the judgment moment to the start of overlap, The minimum displacement in the y-axis direction that needs to be overcome from the beginning of the overlap of the vehicle projections until the moment when the projections separate again after overlapping; The distance between vehicles is reduced in the y-axis direction , The time required; the above eight parameters are used to identify the vehicle projection overlap parameters; Step c: determine whether the projections of the vehicle on the x and y axes overlap at the same time: based on The definition of , the time period when the projections of the two vehicles overlap in the x-axis direction is , the time period when the projections of the two vehicles overlap on the y-axis direction is The condition for a potential collision between the conflicting vehicles is that the projections of the two vehicles on the x-axis and y-axis overlap at the same time, that is, the lower limit of the two time periods and None , and the two time periods and The intersection of is not an empty set; The intersection corresponds to the duration of a potential collision between two vehicles in theory. The potential collision time is the time required for a collision to occur. TU is the lower limit of the intersection, and the conflict identification formula is as follows; 。 2. The unified identification method for straight road section traffic conflict without distinguishing traffic conflict types according to claim 1, characterized in that: Step b2 The calculation process is as follows: When the projections of the two vehicles overlap on the x-axis is 0; when the projections of the two vehicles do not overlap in the x-axis direction, is the distance from the front of the rear vehicle to the rear of the front vehicle in the x-axis direction, calculated using the projection boundary points , as follows: , where is the distance from the front of vehicle A projected on the x-axis to the origin of the coordinate axis O, in meters; is the distance from the rear of car A projected on the x-axis to the origin of the coordinate axis O, in meters; is the distance from the front of vehicle B projected on the x-axis to the origin of the coordinate axis O, in meters; It is the distance from the rear of car B projected on the x-axis to the origin O of the coordinate axis, in meters.

3. The unified identification method for straight road section traffic conflict without distinguishing traffic conflict types according to claim 1 or 2, characterized in that: As described in step b2 The calculation process is as follows: According to The size of the vehicle coordinates and the relationship between the vehicle speed. It is divided into four cases, as shown in the following formula: 。 4. The unified identification method for straight road section traffic conflicts without distinguishing traffic conflict types according to claim 3, characterized in that: As described in step b2 The calculation process is as follows: it is affected by the positions of the two vehicles, whether the projections overlap at the current moment, and the speed of the front and rear vehicles. It is divided into six cases, as shown below: 。 5. The unified identification method for straight road section traffic conflict without distinguishing traffic conflict types according to claim 4, characterized in that: As described in step b2 The calculation process is as follows: The situation when there are non-infinite solutions is The six cases involved are the same, as shown in the following formula: 。 6. The unified identification method for straight road section traffic conflicts without distinguishing traffic conflict types according to claim 5, characterized in that: As described in step b2 The calculation formula is as follows: 。 7. The unified identification method for straight road section traffic conflicts without distinguishing traffic conflict types according to claim 5, characterized in that: As described in step b2 The calculation formula is as follows: 。 8. The unified identification method for straight road section traffic conflicts without distinguishing traffic conflict types according to claim 5, characterized in that: As described in step b2 The calculation formula is as follows: 。 9. The unified identification method for straight road section traffic conflicts without distinguishing traffic conflict types according to claim 5, characterized in that: As described in step b2 The calculation formula is as follows: 。 10. The unified identification method for straight road section traffic conflict without distinguishing traffic conflict types according to claim 5, characterized in that: The lower limit of the intersection in step c must also be the lower limit of the two time periods and One, based on the vehicle status at each moment during the conflict process, TU Identify the complete risk metric over the duration of the conflict as shown below: 。

Images