Expressway diversion area lane changing behavior risk assessment method and system based on safety margins

Abstract

The invention relates to the technical field of vehicle risk assessment, and discloses an expressway diversion area lane changing behavior risk assessment method and system based on safety margins, and the method comprises the steps: constructing a transport vehicle lane changing behavior track data set of an expressway diversion area according to the start time of a lane changing behavior; screening potential associated vehicles, and extracting track data of the associated vehicles before and after lane changing; and constructing a safety marginal index of vehicle lane change, constructing a transport vehicle lane change collision probability index and a vehicle lane change collision severity index, obtaining a safety risk index, and evaluating a vehicle lane change behavior risk value. According to the method, the lane changing intention starting time is obtained by adopting the hidden Markov chain model, the lane changing intention recognition stage is divided more reasonably, and the vehicle behavior intention is recognized more accurately; the exposure and severity indexes of the vehicle lane changing risk are considered; the method considers that the lane changing risk of vehicles in the shunting area of the expressway is a result of the interaction of risks in various aspects, and analyzes the complex association relationship among the influence factors.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle risk assessment, and particularly to a method and system for risk assessment of lane-changing behavior in a highway diversion area based on a safety margin. Background Art

[0002] The bifurcated section near the ramp in the highway diversion area is an important part of the urban highway. The intensive lane-changing operations in this area have a significant impact on the traffic operation of the entire section. Since some vehicles must change their running lanes to enter the ramp after entering the diversion area, this mandatory lane-changing behavior is the main cause of most vehicle conflicts and traffic accidents. Therefore, frequent lane-changing behaviors on the diversion section will generate traffic conflicts and increase the likelihood of traffic accidents, and even exacerbate the severity of vehicle collision accidents.

[0003] To address this problem, there are already some solutions in the current technology, such as using machine learning methods to predict and identify vehicle lane-changing behaviors. However, these technologies still have limitations. Especially for the identification of lane-changing intentions with high precision, the effect is not ideal. Most of the previous methods were based on empirical data, that is, the vehicle characteristics within 2 - 5 seconds before the lane-changing behavior occurred were used to judge the vehicle lane-changing intention, but this is not suitable for refined and proactive lane-changing safety risk early warning, lacking a highly reliable and persuasive time threshold for lane-changing intentions.

[0004] In addition, current drivers are often affected by the behaviors of the front and rear vehicles in the current lane and the target lane during the lane-changing process. Although some scholars have paid attention to the relationship between vehicle trajectory data and driving behaviors, the research on quantifying the safety risks of vehicle lane-changing behaviors in the highway diversion area based on high-precision trajectory data is still insufficient. Currently, the research on safety risk quantification indicators for lane-changing behaviors of transport vehicles in the highway diversion area and lane-changing safety risk prediction models is not in-depth. Therefore, there is an urgent need for a method to real-time monitor the safety risks of vehicle lane-changing behaviors in the highway diversion area, which is of great significance for improving road traffic safety. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a method for risk assessment of lane-changing behavior in a highway diversion area based on a safety margin to solve the above problems.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for risk assessment of lane-changing behavior in a highway diversion area based on a safety margin, including: Construct a trajectory dataset of the lane-changing behavior of transport vehicles in the highway diversion area according to the start time of the lane-changing behavior; Based on the lane-changing behavior trajectory dataset of the transportation vehicle, potential associated vehicles are screened, and then the trajectory data of the associated vehicles before and after lane-changing is extracted; Based on the trajectory data of the associated vehicles before and after lane-changing, a safety margin index for vehicle lane-changing is constructed, and an index for the collision probability of the transportation vehicle during lane-changing and an index for the severity of the vehicle lane-changing collision are constructed to obtain a safety risk index and evaluate the risk value of the vehicle lane-changing behavior.

[0007] As a preferred scheme of the method for evaluating the risk of lane-changing behavior in the highway diversion area based on the safety margin of the present invention, wherein: according to the start time of the lane-changing behavior, constructing a lane-changing behavior trajectory dataset of the transportation vehicle in the highway diversion area includes: According to the lateral coordinate of the vehicle, the lane position where the vehicle is located is determined. When more than 3 / 4 of the vehicle body is within a lane, the vehicle belongs to that lane; otherwise, the vehicle is in a state of straddling the lane line. The vehicles with lane-changing behavior are marked, and according to the lane data of the marked vehicles, the lane-changing trajectory of the vehicle is obtained. Taking the moment when the lane value of the vehicle changes from a positive integer to 0 as the starting point, search for the time interval where the lateral coordinate of the vehicle changes monotonically before and after, extract the interval trajectory as the lane-changing trajectory of the vehicle, construct a lane-changing behavior trajectory dataset of the vehicle, and record the starting lane and the target lane of the lane-changing trajectory.

[0008] As a preferred scheme of the method for evaluating the risk of lane-changing behavior in the highway diversion area based on the safety margin of the present invention, wherein: extracting the trajectory data of the associated vehicles before and after lane-changing includes: According to the spatio-temporal data of the lane-changing trajectory data, potential associated vehicles are screened according to the associated satisfaction conditions, and the associated satisfaction conditions are expressed as: ; Wherein, represents the original trajectory dataset, represents the lane-changing behavior trajectory dataset, represents the starting time of the lane-changing trajectory, represents the starting position of the lane-changing trajectory, 、 respectively represent the start time and end time of the vehicle trajectory in the original trajectory dataset, 、 respectively represent the start and end positions of the vehicle trajectory in the original trajectory dataset, represents the lane where the vehicle is located in the original trajectory dataset, 、 respectively represent the lane before the vehicle lane-changing behavior starts and the lane after the vehicle lane-changing behavior ends in the lane-changing behavior trajectory data set.

[0009] ​As a preferred solution of the freeway diverging area lane - changing behavior risk assessment method based on safety margin according to the present invention, wherein: Extracting the associated vehicle trajectory data before and after lane - changing further includes: Performing smoothing processing on the spatio - temporal data to obtain the position data and motion data of potential associated vehicles unified with the time stamps of the lane - changing trajectory, expressed as: ; ; wherein, represents the position of the potential associated vehicle, represents the position of the potential associated vehicle, represents the time stamp of the lane - changing trajectory, and respectively represent the two time stamps closest to in the time stamps of the potential associated vehicle, and are respectively the and position of the potential associated vehicle at the time stamps of position, and are respectively the and position of the potential associated vehicle at the time stamps of position; According to the condition of the mutual position of vehicles and the minimum distance from the lane - changing vehicle, screening and extracting the associated vehicle data of the lane - changing vehicle, that is, the front and rear vehicles before and after the lane - changing of the lane - changing vehicle, expressed as: ; wherein, represents the rear vehicle before lane - changing, and respectively represent the position of the lane - changing vehicle and the vehicle at the moment of , position, and represent the position of the lane - changing vehicle and the vehicle at the moment of to obtain the front vehicle before lane - changing, the rear vehicle after lane - changing, and the front vehicle after lane - changing.

[0010] As a preferred solution of the freeway diverging area lane - changing behavior risk assessment method based on safety margin according to the present invention, wherein: Constructing the safety margin index for vehicle lane - changing includes: Construct a safety margin index for vehicle lane change , and obtain a safety margin value, expressed as: ; Wherein, indicates the presence of the leading vehicle, represents the shortest distance between vehicles, and respectively represent the speeds of the leading vehicle and the following vehicle, and respectively represent the maximum deceleration of the leading vehicle and the following vehicle, represents the value of the collision - free risk safety condition.

[0011] As a preferred embodiment of the lane - changing behavior risk assessment method in the highway diversion area based on the safety margin according to the present invention, wherein: constructing a lane - changing collision probability index and a lane - changing collision severity index for transport vehicles includes: Based on the safety margin index of the vehicle, construct a lane - changing collision probability possibility index , and calculate the value between the target vehicle and the four surrounding vehicles, expressed as: ; Wherein, represents the collision probability between the target vehicle and the vehicle in front, , represents the driver's comfortable reaction time, represents the threshold value of the driver's comfortable reaction time, represents the duration when the value is lower than , is the duration of the lane - changing behavior, represents the presence of the vehicle in front; Based on the safety margin value of the vehicle, construct a lane - changing collision severity index , and calculate the maximum collision energy at the moment of the minimum when colliding with the vehicle in front, expressed as: ; Wherein, is the moment when is located, is the mass of the approaching vehicle, is the mass of the vehicle being approached, is the speed of the approaching vehicle, is the speed of the vehicle being approached, is the collision angle; Based on the maximum collision energy , construct a collision severity index , expressed as: ; Among them, represents the maximum collision energy.

[0012] As a preferred solution of the method for risk assessment of lane-changing behavior in the highway diversion area based on safety margin according to the present invention, among them: obtaining the safety risk index of the lane-changing vehicle includes: Based on the lane-changing collision probability index of the transportation vehicle and the lane-changing collision severity index of the vehicle, the safety risk index of the lane-changing vehicle is coupled through a fault tree , expressed as: ; Among them, OF, OB, TF, and TB respectively represent the vehicle in front in the original lane, the vehicle behind in the original lane, the vehicle in front after lane change, and the vehicle behind after lane change, and the collision risk index is expressed as: ; Among them, , , and respectively represent the safety risk values of the lane-changing vehicle and the vehicle in front in the original lane, the vehicle behind in the original lane, the vehicle in front after lane change, and the vehicle behind after lane change.

[0013] In the second aspect, the present invention provides a system for risk assessment of lane-changing behavior in the highway diversion area based on safety margin, including: An acquisition module for constructing a trajectory dataset of the lane-changing behavior of transportation vehicles in the highway diversion area according to the start time of the lane-changing behavior; An extraction module for screening potential associated vehicles based on the trajectory dataset of the lane-changing behavior of the transportation vehicle, and then extracting the trajectory data of the associated vehicles before and after lane change; A risk assessment module for constructing a safety margin index for vehicle lane change based on the trajectory data of the associated vehicles before and after lane change, and constructing a lane-changing collision probability index of the transportation vehicle and a lane-changing collision severity index of the vehicle, obtaining a safety risk index, and evaluating the risk value of the vehicle lane-changing behavior.

[0014] In the third aspect, the present invention provides an electronic device, including: A memory and a processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for risk assessment of lane-changing behavior in the highway diversion area based on safety margin are implemented.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions, which when executed by a processor, implement the steps of the method for risk assessment of lane-changing behavior in a highway diversion area based on safety margins.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: By considering the driver's own intention and the influence of surrounding environmental factors on the vehicle lane-changing behavior, the present invention uses a hidden Markov chain model to obtain the starting moment of the lane-changing intention, divides the lane-changing intention recognition stage more reasonably, and more accurately identifies the vehicle behavior intention; considers the exposure and severity indicators of vehicle lane-changing risks, and comprehensively considers vehicle lane-changing risks; considers that the vehicle lane-changing risk in the highway diversion area is the result of the interaction of various risks, and analyzes the complex correlation relationship between various influencing factors; the data collection and transmission are reliable, easy to implement, and have the advantages of low cost, repeatability, and easy acquisition of parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic diagram of the overall process of the method for risk assessment of lane-changing behavior in a highway diversion area based on safety margins according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the lane-changing process of the method for risk assessment of lane-changing behavior in a highway diversion area based on safety margins according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the risk moment of fault tree analysis of the method for risk assessment of lane-changing behavior in a highway diversion area based on safety margins according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to make the above-mentioned objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0020] Refer to Figures 1-3 , an embodiment of the present invention provides a method for risk assessment of lane-changing behavior in a highway diversion area based on safety margins, including: S100. Construct a trajectory dataset of the lane-changing behavior of transport vehicles in the freeway diviation area according to the start time of the lane-changing behavior; S200. Based on the trajectory dataset of the lane-changing behavior of transport vehicles, screen potential associated vehicles, and then extract the trajectory data of the associated vehicles before and after lane-changing; S300. Based on the trajectory data of the associated vehicles before and after lane-changing, construct a safety margin index for vehicle lane-changing, and construct an index for the probability of vehicle lane-changing collision and an index for the severity of vehicle lane-changing collision to obtain a safety risk index, and evaluate the risk value of vehicle lane-changing behavior.

[0021] In a preferred embodiment, constructing a trajectory dataset of the lane-changing behavior of transport vehicles in the freeway diviation area includes: Determine the lane position of the vehicle according to the lateral coordinate of the vehicle. When more than 3 / 4 of the vehicle body is within a lane, the vehicle belongs to that lane; otherwise, the vehicle is in a straddling state; Mark the vehicles with lane-changing behavior. According to the lane data of the marked vehicles, obtain the lane-changing trajectory of the vehicle. Starting from the moment when the lane value of the vehicle changes from a positive integer to 0, search for the time interval in which the lateral coordinate of the vehicle changes monotonically before and after, and extract the interval trajectory as the lane-changing trajectory of the vehicle, construct a trajectory dataset of the lane-changing behavior of the vehicle, and record the starting lane and the target lane of the lane-changing trajectory.

[0022] In an alternative embodiment, constructing a trajectory dataset of the lane-changing behavior of transport vehicles in the freeway diviation area is as follows: S101. Determine the lane position of the vehicle according to the lateral coordinate , and it is considered that when more than 3 / 4 of the vehicle body is within a lane, the vehicle belongs to that lane; otherwise, it is in a straddling state, so as to extract the running state of the vehicle in the lane. The calculation formula is as follows: ; Where is the floor function; is the lane width, generally 3.75 m; is the vehicle width; is a positive integer; S102. Based on the lane data of the marked vehicles, find the lane-changing trajectory of the vehicle. Considering the moment when the lane value of the vehicle changes from a positive integer to 0 as the starting point, search for the time interval in which the vehicle changes monotonically before and after, so as to extract the interval trajectory as the lane-changing trajectory of the vehicle through the change of the movement trajectory of the lateral coordinate, and construct a trajectory dataset of the lane-changing behavior of the vehicle, expressed as: ; Among them, represents the timestamp of the lane change moment; represents the minimum time window, which is related to the frequency of data recording; represents before the lane change moment at the moment of data, represents before the lane change moment at the moment of data, represents before the lane change moment at the moment of data, and a series of continuous timestamps that satisfy the formula are the lane change behavior trajectories, and the starting lane of the lane change trajectory and the target lane of the lane change are recorded and the target lane of the lane change .

[0023] In a preferred embodiment, extracting the associated vehicle trajectory data before and after the lane change includes: According to the spatio-temporal data of the lane change trajectory data, and according to the associated satisfaction conditions, potential associated vehicles are screened. Vehicles that meet the following conditions are considered potential associated vehicles. Through the vehicle position constraint conditions, the potential associated vehicles are screened to improve the efficiency of subsequent associated vehicles. The associated satisfaction conditions are expressed as: ; Among them, represents the original trajectory data set, represents the lane change behavior trajectory data set, represents the starting moment of the lane change trajectory, , , respectively represent the start time and end time of the lane change behavior, represents the starting position of the lane change trajectory, , , respectively represent the starting position and end position of the lane change trajectory, , respectively represent the start time and end time of the vehicle trajectory in the original trajectory data set, , respectively represent the start and end positions of the vehicle trajectory in the original trajectory data set, represents the lane where the vehicle is located in the original trajectory data set, , respectively represent the lane before the vehicle's lane change behavior starts and the lane after the end in the lane change behavior trajectory data set.

[0024] It should be noted that by recording and analyzing the data at the start time of the lane change behavior, the specific dynamic situation of the transport vehicle during the lane change operation in the diversion area can be accurately captured, providing solid basic data support for subsequent analysis and helping to precisely understand various variables in the lane change process.

[0025] In a preferred embodiment, extracting the associated vehicle trajectory data before and after the lane change further includes: To solve the problem that the timestamps in the trajectory data are not unified, the spatio-temporal data is smoothed to obtain the position data and motion data of the potential associated vehicles with the same timestamp as the lane change trajectory, so that the timestamp data between the lane-changing vehicle and the associated vehicles is aligned, expressed as: ; ; Wherein, represents the position of the potential associated vehicle, represents the position of the potential associated vehicle, represents the timestamp of the lane change trajectory, and respectively represent the two timestamps in the timestamp of the potential associated vehicle that are closest to , and are respectively the and positions of the potential associated vehicle at the timestamps of , and are respectively the and positions of the potential associated vehicle at the timestamps of ; Considering the vehicle contour to construct a risk index, according to the condition of the mutual position of the vehicles and the minimum distance from the lane-changing vehicle, the associated vehicle data of the lane-changing vehicle is screened and extracted, that is, the front and rear vehicles before and after the lane change of the lane-changing vehicle, expressed as: ; Wherein, represents the rear vehicle before the lane change, and respectively represent the of the lane-changing vehicle and the vehicle at the moment of position, and represent the of the lane-changing vehicle and the vehicle at the moment of the lane position, and the front vehicle before the lane change is obtained The vehicle behind after lane change The vehicle in front after lane change .

[0026] It should be noted that this step can identify all relevant vehicles that may interact with the target transport vehicle, so as to focus on the factors directly affecting the safety of lane-changing behavior. By carefully analyzing the behavior patterns of these associated vehicles, potential risk situations can be predicted more accurately.

[0027] In a preferred embodiment, the construction of the safety margin index for vehicle lane change includes: Construct the safety margin index for vehicle lane change , and obtain the safety margin value, expressed as: ; Wherein, Indicates the presence of the vehicle in front, 1 for presence and 0 for absence, Indicates the shortest distance between vehicles, And Respectively represent the speeds of the vehicle in front and the vehicle behind, And Respectively represent the ultimate deceleration of the vehicle in front and the vehicle behind, determined according to the braking sensitivity of different vehicles, Indicates the value of the collision-free risk safety condition.

[0028] Wherein, Is the target vehicle The shortest distance from the point on to the vehicle in front On, expressed as: ; Among them, the vehicle contour is rectangularized, and each vehicle is located using 6 points, namely the four vertices of the rectangle and the midpoints of the front and rear two sides.

[0029] In a preferred embodiment, the construction of the lane change collision probability index and the lane change collision severity index for transport vehicles includes: Based on the safety margin index of the vehicle, that is, the safety margin value of the vehicle, construct the vehicle lane change collision probability possibility index , considering the sudden deceleration of the vehicle, calculate the Value between the target vehicle and the four surrounding vehicles, expressed as: ; Wherein, Indicates the collision probability between the target vehicle and the vehicle in front , Indicates the comfortable reaction time of the driver, Represents the comfort reaction time threshold of the driver, Represents The value is lower than The duration of, Is the duration of the lane change behavior, Represents the presence of the vehicle ahead. When the comfort reaction time between the lane-changing vehicle and the surrounding vehicles at a certain moment Is less than the safety threshold At this time, mark this moment as a risk moment. If at a certain moment, the Between the lane-changing vehicle and the surrounding vehicles is greater than or equal to the safety threshold At this time, mark this moment as a safe moment; Based on the safety margin value of the vehicle, construct an index for the severity of vehicle lane change collisions , when the safety margin time is the smallest, the collision consequence at this time is the most serious. Calculate The maximum collision energy of the collision with the vehicle ahead at the moment when it is the smallest , expressed as: ; Among them, Is The moment where, Is the mass of the approaching vehicle, Is the mass of the vehicle being approached, Is the speed of the approaching vehicle, Is the speed of the vehicle being approached, Is the collision angle, that is, the direction included angle ; Based on the maximum collision energy , construct an index for the severity of the collision , considering The greater the value, the greater the severity of the collision. Therefore, use the sigmoid function to construct , the index for the severity of vehicle lane change collisions Is expressed as: ; Among them, Represents the maximum collision energy.

[0030] In a preferred embodiment, the obtained safety risk index of the lane-changing vehicle includes: Based on the index for the probability of vehicle lane change collisions and the index for the severity of vehicle lane change collisions, in order to combine the vehicle interactions during the lane change process, couple and associate the safety risk indices of the vehicle and the lane-changing vehicle through a fault tree , expressed as: ; Among them, OF, OB, TF, and TB respectively represent the vehicle in front in the original lane, the vehicle behind in the original lane, the vehicle in front after lane change, and the vehicle behind after lane change, and the collision risk index is expressed as: ; Among them, , , and respectively represent the safety risk values of the lane-changing vehicle with the vehicle in front in the original lane, the vehicle behind in the original lane, the vehicle in front after lane change, and the vehicle behind after lane change.

[0031] It should be noted that in the present invention, a safety margin index, a collision probability index, and a collision severity index are established, providing a quantitative method to evaluate the risks brought by lane-changing behaviors. It can not only help determine which lane-changing behaviors are the most dangerous, but also provide a basis for formulating effective risk management strategies, significantly improving the control ability of lane-changing behavior risks, and thus enhancing the overall safety of the highway diversion area.

[0032] By considering the driver's own intention and the influence of surrounding environmental factors on the vehicle lane-changing behavior, the present invention uses a hidden Markov chain model to obtain the starting moment of the lane-changing intention, more reasonably divides the lane-changing intention recognition stage, and more accurately identifies the vehicle behavior intention; considers the exposure and severity indicators of vehicle lane-changing risks, and comprehensively considers vehicle lane-changing risks; considers that the vehicle lane-changing risk in the highway diversion area is the result of the interaction of various risks, and analyzes the complex correlation relationships among various influencing factors; the data collection and transmission are reliable, easy to implement, and have the advantages of low cost, repeatability, and easy acquisition of parameters.

[0033] The above is a schematic solution of a method for evaluating lane-changing behavior risks in a highway diversion area based on a safety margin in this embodiment. It should be noted that the technical solution of the system for evaluating lane-changing behavior risks in a highway diversion area based on a safety margin belongs to the same concept as the above-mentioned method for evaluating lane-changing behavior risks in a highway diversion area based on a safety margin. For the details not described in the technical solution of the system for evaluating lane-changing behavior risks in a highway diversion area based on a safety margin in this embodiment, reference can be made to the description of the technical solution of the method for evaluating lane-changing behavior risks in a highway diversion area based on a safety margin.

[0034] A system for evaluating lane-changing behavior risks in a highway diversion area based on a safety margin in this embodiment includes: An acquisition module, configured to construct a lane-changing behavior trajectory data set of transport vehicles in the highway diversion area according to the starting moment of the lane-changing behavior; An extraction module, configured to screen potential associated vehicles based on the lane-changing behavior trajectory data set of transport vehicles, and then extract the trajectory data of associated vehicles before and after lane change; A risk assessment module, which is used to construct a safety margin index for vehicle lane change based on the trajectory data of associated vehicles before and after lane change, and construct a lane change collision probability index and a lane change collision severity index for transport vehicles to obtain a safety risk index, and evaluate the risk value of vehicle lane change behavior.

[0035] This embodiment also provides an electronic device, which is applicable to the situation of risk assessment of lane change behavior in the highway diversion area based on the safety margin, and includes: A memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for risk assessment of lane change behavior in the highway diversion area based on the safety margin as proposed in the above embodiment.

[0036] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for risk assessment of lane change behavior in the highway diversion area based on the safety margin as proposed in the above embodiment.

[0037] The storage medium proposed in this embodiment and the method for risk assessment of lane change behavior in the highway diversion area based on the safety margin proposed in the above embodiment belong to the same inventive concept. For the technical details not described in detail in this embodiment, reference can be made to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0038] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk, or an optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0039] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A risk assessment method for lane-changing behavior in a highway diverging area based on a safety margin, characterized in that: include: According to the lane-changing behavior start time, a lane-changing behavior trajectory dataset of transport vehicles in the highway diverging area is constructed; Based on the lane-changing behavior trajectory data set of the transport vehicle, potentially associated vehicles are screened, and then associated vehicle trajectory data before and after the lane-changing is extracted; Based on the associated vehicle trajectory data before and after the lane change, a safety margin index for the vehicle lane change is constructed, and a transport vehicle lane change collision probability index and a vehicle lane change collision severity index are constructed to obtain a safety risk index and evaluate the risk value of the vehicle lane change behavior.

2. A highway diverging area lane-changing behavior risk assessment method based on safety margin as claimed in claim 1, characterized in that: According to the start time of lane changing behavior, the trajectory dataset of lane changing behavior of transport vehicles in the highway divergence area is constructed, including: Determine the lane where the vehicle is located based on the vehicle's lateral coordinates. When more than 3 / 4 of the vehicle is in a lane, the vehicle belongs to that lane. Otherwise, the vehicle is in a lane-crossing state. The vehicle that changes lanes is marked, and the lane change trajectory of the vehicle is obtained based on the lane data of the marked vehicle. The moment when the value changes from a positive integer to 0 is taken as the starting point, and the time interval in which the lateral coordinate of the vehicle changes monotonically is searched forward and backward. The interval trajectory is extracted as the lane changing trajectory of the vehicle, and a vehicle lane changing behavior trajectory dataset is constructed. The lane changing start lane and lane changing target lane of the lane changing trajectory are recorded.

3. A highway diverging area lane-changing behavior risk assessment method based on safety margin as claimed in claim 1 or 2, characterized in that: Extracting the associated vehicle trajectory data before and after lane change includes: According to the spatiotemporal data of the lane-changing trajectory data, potential associated vehicles are screened according to the association satisfaction conditions. The association satisfaction conditions are expressed as: ； in, represents the original trajectory dataset, represents the lane-changing behavior trajectory dataset, represents the starting time of the lane-changing trajectory, Indicates the starting position of the lane change trajectory, , Respectively represent the start time and end time of the vehicle trajectory in the original trajectory dataset, , Respectively represent the starting and ending positions of the vehicle trajectory in the original trajectory dataset, represents the lane where the vehicle is located in the original trajectory dataset, , They respectively represent the lane before the vehicle lane change behavior starts and the lane after the vehicle lane change behavior in the lane change behavior trajectory data set.

4. A highway diverging area lane-changing behavior risk assessment method based on safety margin as claimed in claim 3, characterized in that: Extracting the associated vehicle trajectory data before and after the lane change also includes: The spatiotemporal data is smoothed to obtain the position data and motion data of the potential associated vehicle that are consistent with the lane change trajectory timestamp, expressed as: ； ； in, Indicates potential associated vehicles Location, Indicates potential associated vehicles Location, The timestamp representing the lane-changing trajectory, and They represent the timestamps of the potentially associated vehicles closest to Two timestamps of and The potential associated vehicles are and Timestamp Location, and The potential associated vehicles are and Timestamp Location; According to the conditions of the relative positions of the vehicles and the minimum distance between the vehicles and the lane-changing vehicle, the associated vehicle data of the lane-changing vehicle is screened and extracted, that is, the front and rear vehicles before and after the lane-changing vehicle, which is expressed as: ； in, Indicates the following vehicle before changing lanes. and Represents lane-changing vehicles and vehicles exist Moment Location, and Indicates a lane-changing vehicle and vehicles exist The lane position at the moment, get the front vehicle before changing lanes , The following vehicle after changing lanes , the vehicle ahead after changing lanes .

5. A highway diverging area lane-changing behavior risk assessment method based on safety margin as claimed in claim 4, characterized in that: The safety margin indicators for constructing vehicle lane change include: Constructing safety margin indicators for vehicle lane changing , and the safety margin value is obtained, which is expressed as: ； in, Indicates whether there is a preceding vehicle. represents the shortest distance between vehicles, and Represent the speeds of the front and rear vehicles respectively. and Represent the limit deceleration of the front vehicle and the rear vehicle respectively, A value representing the safety condition of no collision risk.

6. A highway diverging area lane-changing behavior risk assessment method based on safety margin as claimed in claim 5, characterized in that: The construction of the transport vehicle lane change collision probability index and the vehicle lane change collision severity index includes: Based on the vehicle's safety margin index, a vehicle lane change collision probability index is constructed , calculate the distance between the target vehicle and the four surrounding vehicles Value, expressed as: ； in, Represents the collision probability between the target vehicle and the vehicle in front , Indicates the driver's comfortable reaction time, represents the driver's comfortable reaction time threshold, express Value lower than duration, is the duration of the lane-changing behavior, Indicates the presence of a vehicle ahead; Construct a vehicle lane-changing collision severity index based on the vehicle's safety margin ,calculate The maximum collision energy when colliding with the vehicle in front at the minimum moment , expressed as: ； in, for The moment you are at, To approximate the vehicle mass, is the mass of the vehicle being approached, To approximate vehicle speed, is the speed of the approaching vehicle, is the collision angle; Based on the maximum collision energy , construct a collision severity index , expressed as: ； in, Represents the maximum collision energy.

7. A highway diverging area lane-changing behavior risk assessment method based on safety margin as claimed in claim 6, characterized in that: The safety risk indicators of lane-changing vehicles include: Based on the transport vehicle lane change collision probability index and the vehicle lane change collision severity index, the lane change vehicle safety risk index is coupled through the fault tree. , expressed as: ； Among them, OF, OB, TF, and TB represent the front vehicle in the original lane, the rear vehicle in the original lane, the front vehicle after lane change, and the rear vehicle after lane change, respectively. It is expressed as: ； in, , , as well as They respectively represent the safety risk values ​​of the lane-changing vehicle and the vehicle in front of it in the original lane, the vehicle behind it in the original lane, the vehicle in front after the lane change, and the vehicle behind it after the lane change.

8. A highway diverging area lane-changing behavior risk assessment system based on safety margin, using a highway diverging area lane-changing behavior risk assessment method based on safety margin as claimed in any one of claims 1 to 7, characterized in that: include, The acquisition module is used to construct a lane-changing behavior trajectory dataset of transport vehicles in the highway diverging area according to the start time of the lane-changing behavior; An extraction module, used to screen potential associated vehicles based on the lane-changing behavior trajectory data set of the transport vehicle, and then extract the associated vehicle trajectory data before and after the lane-changing; The risk assessment module is used to construct a safety margin indicator for vehicle lane changing based on the associated vehicle trajectory data before and after the lane changing, and to construct a transport vehicle lane changing collision probability indicator and a vehicle lane changing collision severity indicator to obtain a safety risk indicator and evaluate the risk value of the vehicle lane changing behavior.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of a highway diverging area lane changing behavior risk assessment method based on safety margin as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of a highway diverging area lane changing behavior risk assessment method based on safety margin as described in any one of claims 1 to 7.

Images