Vehicle conflict prediction method, device, equipment and storage medium for road intersections

Abstract

The present invention discloses a method, device, equipment and storage medium for predicting vehicle conflicts at road intersections. The method includes: obtaining vehicles at a road intersection as target vehicles; predicting the driving trajectories of the target vehicles to obtain predicted driving trajectories; generating dynamic interaction boxes for each of the target vehicles based on the predicted driving trajectories; and predicting vehicle conflicts based on the dynamic interaction boxes. By using this method, through the trajectory prediction method, the original rectangular box is changed to a curve box based on the predicted trajectory, which can not only better describe the complex steering behavior of vehicles during driving, but also take into account the expected driving behavior of vehicles to identify potential conflict objects in advance. At the same time, for the interaction situation at road intersections, a method for identifying conflicts is predicted from space and time, which reduces the amount of calculation while ensuring the accuracy of predicting vehicle conflicts.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical fields of intelligent driving and traffic safety, and particularly to a method, device, equipment and storage medium for predicting vehicle conflicts at road intersections. Background Art

[0002] As an important part of urban traffic, road intersections are where different directions and types of vehicles interact intensively, which is crucial for urban traffic operation and traffic safety. Therefore, scientific and reasonable management of road intersections is an effective way to relieve traffic congestion and reduce traffic accidents. Prediction of vehicle conflict scenarios is the prerequisite for scientific traffic control, which can analyze potential accident risks based on driving data and is of great significance for improving traffic efficiency and ensuring traffic safety. Summary of the Invention

[0003] The embodiments of the present invention provide a method, device, equipment and storage medium for predicting vehicle conflicts at road intersections, which can accurately predict vehicle conflicts at road intersections, thereby providing a reliable basis for relieving traffic congestion and reducing traffic accidents.

[0004] In a first aspect, the embodiments of the present invention provide a method for predicting vehicle conflicts at road intersections, the method comprising:

[0005] Obtaining a vehicle at a road intersection as a target vehicle;

[0006] Predicting the driving trajectory of the target vehicle to obtain a predicted driving trajectory;

[0007] Generating dynamic interaction boxes for each of the target vehicles in real time based on the predicted driving trajectory;

[0008] Predicting vehicle conflicts based on the dynamic interaction boxes.

[0009] In a second aspect, the embodiments of the present invention further provide a device for predicting vehicle conflicts at road intersections, the device comprising:

[0010] A target vehicle acquisition module, configured to obtain a vehicle at a road intersection as a target vehicle;

[0011] A driving trajectory prediction module, configured to predict the driving trajectory of the target vehicle to obtain a predicted driving trajectory;

[0012] An interaction box generation module, configured to generate dynamic interaction boxes for each of the target vehicles in real time based on the predicted driving trajectory;

[0013] A vehicle conflict prediction module, configured to predict vehicle conflicts based on the dynamic interaction boxes.

[0014] In a third aspect, embodiments of the present disclosure further provide an electronic device, including:

[0015] One or more processors;

[0016] A storage device for storing one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle conflict prediction method for road intersections provided by the embodiments of the present disclosure.

[0018] In a fourth aspect, embodiments of the present disclosure further provide a storage medium containing computer-executable instructions, which are used to execute the vehicle conflict prediction method for road intersections provided by the embodiments of the present disclosure when executed by a computer processor.

[0019] The present invention discloses a vehicle conflict prediction method, device, equipment and storage medium for road intersections. The method includes: obtaining vehicles at a road intersection as target vehicles; predicting the driving trajectories of the target vehicles to obtain predicted driving trajectories; generating dynamic interaction boxes for each of the target vehicles in real time based on the predicted driving trajectories; and predicting vehicle conflicts based on the dynamic interaction boxes. Through the trajectory prediction method, the original rectangular box is changed to a curve box based on the predicted trajectory, which can not only better describe the complex steering behaviors of vehicles during driving, but also take into account the expected driving behaviors of vehicles to identify potential conflict objects in advance. At the same time, for the interaction situation at road intersections, a conflict identification method that predicts conflicts in space and time reduces the amount of calculation while ensuring the accuracy of predicting vehicle conflicts. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the original elements and elements are not necessarily drawn to scale.

[0021] Figure 1 It is a flowchart of a vehicle conflict prediction method for road intersections provided by an embodiment of the present disclosure;

[0022] Figure 2 It is an example diagram of the road intersection range of a vehicle conflict prediction method for road intersections provided by an embodiment of the present disclosure;

[0023] Figure 3 It is an example diagram of following and identifying a leading vehicle of a vehicle conflict prediction method for road intersections provided by an embodiment of the present disclosure;

[0024] Figure 4 Schematic diagram of a dynamic interaction box for a vehicle conflict prediction method at a road intersection provided by an embodiment of the present disclosure;

[0025] Figure 5 Schematic diagram of a trajectory-based dynamic interaction box for a vehicle conflict prediction method at a road intersection provided by an embodiment of the present disclosure;

[0026] Figure 6 Schematic diagram of intersection conflicts in a left-turn dedicated phase for a vehicle conflict prediction method at a road intersection provided by an embodiment of the present disclosure;

[0027] Figure 7 Schematic diagram of conflict judgment in space for a vehicle conflict prediction method at a road intersection provided by an embodiment of the present disclosure;

[0028] Figure 8 Schematic diagram of conflict judgment in time for a vehicle conflict prediction method at a road intersection provided by an embodiment of the present disclosure;

[0029] Figure 9 Schematic diagram of a psychological-physical risk field for a vehicle conflict prediction method at a road intersection provided by an embodiment of the present disclosure;

[0030] Figure 10 Schematic diagram of the structure of a vehicle conflict prediction device at a road intersection provided by an embodiment of the present disclosure;

[0031] Figure 11 Schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0032] Embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0033] It should be understood that the various steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0034] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0035] It should be noted that the concepts such as "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0036] It should be noted that the modifications of "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly specified in the context, it should be understood as "one or more".

[0037] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0038] It can be understood that before using the technical solutions disclosed in the embodiments of this disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0039] For example, when responding to receiving an active request from the user, a prompt message is sent to the user to clearly prompt the user that the operation requested by it will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operations of the technical solutions of this disclosure according to the prompt message.

[0040] As an optional but non-limiting implementation manner, when responding to receiving an active request from the user, the manner of sending a prompt message to the user can be, for example, in the form of a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0041] It can be understood that the above process of notifying and obtaining the user's authorization is only illustrative and does not limit the implementation manners of this disclosure. Other manners that meet relevant laws and regulations can also be applied to the implementation manners of this disclosure.

[0042] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of data) should comply with the requirements of corresponding laws, regulations and related provisions.

[0043] Embodiment 1

[0044] Figure 1 The figure is a flowchart of vehicle conflict prediction at a road intersection provided by an embodiment of the present disclosure. The embodiments of the present disclosure are applicable to the situation where vehicle conflicts at road intersections can be accurately predicted. This method can be executed by a vehicle conflict prediction device at a road intersection, and the device can be implemented in the form of software and / or hardware. Optionally, it is implemented by an electronic device, and the electronic device can be a mobile terminal, a PC or a server, etc.

[0045] As Figure 1 shown, a method for predicting vehicle conflicts at a road intersection provided by an embodiment of the present disclosure may specifically include the following steps:

[0046] S110. Obtain the vehicles at the road intersection as target vehicles.

[0047] Specifically, it should be noted that the positioning devices in all vehicles upload the real-time trajectory data of their own vehicles to the service platform, and the service platform can be a traffic management platform, etc. In order to focus more on the vehicle conflict behavior in the internal area of the road intersection, it is necessary to screen the vehicle trajectories by range. Considering that conflicts generally occur at the intersection and at the exit lanes of the intersection, a certain range with the intersection center as the midpoint is intercepted as the intersection range. If the actual trajectory point of the vehicle at the current moment is within the set intersection range or the actual trajectory point will be within the set intersection range within a certain time, then the vehicle is used as a target vehicle. Among them, the certain time can be 5s or 10s, etc., and can be set according to the actual situation.

[0048] Exemplarily, Figure 2 is an example diagram of the range of a road intersection provided by an embodiment of the present disclosure; as Figure 2 shown, taking the intersection center as the midpoint, four straight lines 10m away from the exit lanes in each direction and parallel to the exit lanes are used as the boundary lines, and the rectangular range enclosed is the intersection range. The vehicles within the intersection range or those that will be within the intersection range within a certain time are used as target vehicles.

[0049] Based on the above embodiments, the embodiments of the present disclosure for obtaining the vehicles at the road intersection as target vehicles may specifically include the following steps:

[0050] a1) Obtain the actual trajectory point of the vehicle at the current moment.

[0051] b1) If the actual trajectory point is within the set intersection range, the vehicle is at a road intersection, and the vehicle is determined as the target vehicle.

[0052] Specifically, obtain the actual trajectory point of the vehicle. If the actual trajectory point of the vehicle at the current moment is within the set intersection range or the actual trajectory point will be within the set intersection range within a certain period of time, then the vehicle is used as the target vehicle. Among them, the certain period of time can be 5s or 10s, etc., and can be set according to the actual situation.

[0053] S120. Predict the driving trajectory of the target vehicle to obtain the predicted driving trajectory.

[0054] In this embodiment, to predict the driving trajectory of the target vehicle, the Bidirectional Long Short-Term Memory (Bi-LSTM) network method can be selected to predict the future trajectory of the vehicle. The trajectory prediction model based on the Bi-LSTM network mainly consists of three parts: the input layer, the Bi-LSTM layer, and the output layer. The historical trajectory input information is input by the input layer, the prediction result is obtained through prediction by the Bi-LSTM layer, and then the prediction result is output by the output layer. Specifically, according to the trajectory prediction method, the trajectory points of the vehicle are predicted, and then the trajectory points are curve-fitted to obtain the predicted trajectory. Finally, the distance between two adjacent trajectory points is calculated according to the time interval of the vehicle trajectory points, and the trajectory distances corresponding to the time intervals are accumulated, which is the length of the real trajectory curve.

[0055]

[0056] In the formula, S is the length of the real trajectory curve, N is the ratio of the time period length to the time interval, s i is the trajectory length of the i-th segment, x i+1 / x i the x-axis coordinate of the (i + 1) / i-th trajectory point, y i+1 / y i the y-axis coordinate of the (i + 1) / i-th trajectory point.

[0057] S130. Based on the predicted driving trajectory, dynamically generate interaction frames for each target vehicle in real time.

[0058] Among them, the dynamic interaction frame can be a curve frame, which takes the current trajectory point of the target vehicle as the reference point, expands to both sides with the vehicle body width as the expansion width, and extends a certain length along the future trajectory curve of the vehicle according to the above predicted driving trajectory, and is used for subsequent prediction of vehicle conflicts.

[0059] Based on the above embodiments, the embodiments of the present disclosure can include the following steps when dynamically generating interaction frames for each of the target vehicles in real time according to the predicted driving trajectory:

[0060] a2) Generate a static interaction box based on the vehicle width and driving direction of the target vehicle, and generate a vehicle body area box based on the center point and vehicle width of the target vehicle.

[0061] b2) For the current target vehicle, determine the leading vehicle in following distance of the current target vehicle based on the static interaction box of the current target vehicle and the vehicle body area boxes of other target vehicles.

[0062] c2) Generate a dynamic interaction box of the current target vehicle based on the driving data and predicted driving trajectory of the current target vehicle and the leading vehicle in following distance.

[0063] Specifically, Figure 3 is an example diagram for identifying the leading vehicle in following distance of a vehicle conflict prediction method at a road intersection provided by an embodiment of the present disclosure; as Figure 3 shown, for the target vehicle at any moment, draw a rectangular interaction box with the vehicle body width as the width, an initial length (e.g., 50 m), and along the driving direction of the target vehicle. For the surrounding vehicles, draw circles with the coordinate points as the centers and a radius (e.g., the width of a general vehicle is 1.6 - 2 m, the lane is 3 m, so the radius can be set to 1 m, that is, the radius can take half of the maximum vehicle width). This circular area is the vehicle body area box. The vehicle closest to the target vehicle among the intersections of all vehicle body area boxes and the interaction box is identified as the leading vehicle in following distance of the target vehicle. Then, taking the current trajectory point of the target vehicle as the reference point, expand it to both sides with the vehicle body width as the expansion width, and use the minimum value of the safety distance and the actual distance as the length of the trajectory curve, and draw a dynamic interaction box along the future trajectory curve of the vehicle.

[0064] Based on the above embodiments, the embodiments of the present disclosure can specifically include the following steps for determining the leading vehicle in following distance of the current target vehicle according to the static interaction box of the current target vehicle and the vehicle body area boxes of other target vehicles:

[0065] b21) Determine the other target vehicles whose vehicle body area boxes have intersections with the static interaction box as the leading vehicles of the current target vehicle.

[0066] b22) Determine the leading vehicle in following distance as the vehicle closest to the current target vehicle.

[0067] Specifically, if the above vehicle body area box of other target vehicles has an intersection with the static interaction box, it is considered that the vehicle is in front of the target vehicle. Among them, the vehicle closest to the target vehicle is regarded as the leading vehicle in following distance of the target vehicle.

[0068] Based on the above embodiments, the embodiments of the present disclosure can specifically include the following steps for generating a dynamic interaction box of the current target vehicle according to the driving data and predicted driving trajectory of the current target vehicle and the leading vehicle in following distance:

[0069] c21) Determine the safe distance between the current target vehicle and the following leading vehicle based on the driving data, and obtain the actual distance between the current target vehicle and the following leading vehicle.

[0070] c22) Use the minimum value between the safe distance and the actual distance as the extension length of the dynamic interaction box, and use the vehicle width of the current target vehicle as the extension width of the dynamic interaction box.

[0071] c23) Calculate the predicted driving trajectory using the infinitesimal method to generate a trajectory curve with the extension length.

[0072] c24) Generate a dynamic interaction box based on the two trajectory curves and the extension width; among them, the dynamic interaction box extends forward from the vehicle head.

[0073] Specifically, the safe distance is defined as the minimum safe distance between the host vehicle and the leading vehicle, which is the distance that can still avoid collision under the worst conditions.

[0074] As Figure 4 shown, the initial dynamic interaction box can be: a rectangular interaction box drawn along the forward direction of the host vehicle, with the vehicle width as the extension width of the interaction box and the minimum value between the safe distance d min and the actual distance d real as the extension length of the dynamic interaction box.

[0075] As Figure 5 shown, taking the current trajectory point of the target vehicle as the reference point, expanding to both sides with the vehicle body width as the extension width, using the minimum value between the safe distance and the actual distance as the length of the trajectory curve, calculating the predicted driving trajectory using the infinitesimal method to generate a trajectory curve with the extension length, and drawing a dynamic interaction box along the future trajectory curve of the vehicle. Among them, the dynamic interaction box extends forward from the vehicle head.

[0076] Optionally, when the vehicle turns, adjust the curve length of the dynamic curve box. In this embodiment, it is necessary to increase the curve length of the dynamic curve box. The advantage of doing this is to ensure that the straight-line distance between the body of the own vehicle and the body of the leading vehicle is greater than or equal to the safe distance.

[0077] S140. Predict vehicle conflicts based on the dynamic interaction box.

[0078] Specifically, to determine whether there is a conflict between all target vehicles, it should be judged from two dimensions: space and time. First, judge whether there is an intersection between the dynamic interaction boxes of any two vehicles. This intersection is the conflict area in the physical space of the two vehicles. If there is an intersection, then calculate the time when the two vehicles reach this conflict area respectively based on the trajectory prediction results, and calculate the time difference to judge whether the two vehicles are potential conflict objects. If the time difference is less than the preset threshold, there is a vehicle conflict between these two target vehicles.

[0079] Based on the above embodiments, the embodiments of the present disclosure can predict vehicle conflicts for dynamic interaction boxes, which specifically may include the following steps:

[0080] a3) Determine two dynamic interaction boxes with an intersection area, which are respectively a first dynamic interaction box and a second dynamic interaction box; wherein, the first dynamic interaction box corresponds to a first target vehicle, and the second dynamic interaction box corresponds to a second target vehicle.

[0081] b3) Determine a first duration and a second duration for the first target vehicle and the second target vehicle to reach the intersection area respectively starting from the current moment.

[0082] c3) If the difference between the first duration and the second duration is less than a set threshold, there is a vehicle conflict between the first target vehicle and the second target vehicle.

[0083] Specifically, pairwise judgment is performed on the target vehicles according to the calculated prediction results. As Figure 7 shown,[[]]

[0084]

[0085] In the formula, I space is a discriminant function for whether there is a conflict in space, 1 represents there is a conflict, and 0 represents there is no conflict; S1 is the first dynamic interaction box, and S2 is the second dynamic interaction box. As Figure 7 shown, if they intersect, it is considered that there is a conflict in space between the two vehicles, and the intersection surface is the conflict area between the two vehicles. For the vehicle pairs with a conflict in space above, according to the intersection surface of each two vehicles obtained by spatial recognition, the time points when the vehicles reach this intersection surface are calculated respectively using the trajectory prediction results, and are denoted as the first duration and the second duration. As Figure 8 shown,[[]]

[0086]

[0087] In the formula, I time is a discriminant function for whether there is a conflict in time, 1 represents there is a conflict, and 0 represents there is no conflict; T1 is the first duration, and T2 is the second duration. If the difference between the arrival time points of the two vehicles is less than a set time threshold, for example, 3s, it is considered that there is also a conflict in time between the two vehicles, and they are potential conflict objects.

[0088] Specifically, first, calculate the dynamic interaction box for each moment of the vehicle. Based on the calculated prediction results, pairwise judge different vehicles traveling in different directions that may have conflicts to determine whether the interaction boxes of the two vehicles intersect. If they intersect, it is considered that there is a conflict between the two vehicles in space, and the intersection area is the conflict area between the two vehicles. According to the intersection area of each pair of vehicles obtained by spatial recognition, calculate the time points when the vehicles reach this intersection area respectively using the trajectory prediction results. If the difference in the arrival time points of the two vehicles is less than the time threshold, for example, 3s, it is considered that there is also a conflict in time between the two vehicles, and they are potential conflict objects.

[0089] In this embodiment, when there are different signal light settings at the intersection, only possible conflict types can be judged. Exemplarily, as Figure 6 shown, taking an intersection with a dedicated left-turn phase as an example, there are two types of conflicts, namely straight - right-turn conflict and left - right-turn conflict.

[0090] In this technical solution, when there are different signal light settings at the intersection, by only judging possible conflict types, the purpose of further reducing the calculation amount is achieved.

[0091] The embodiment of the present disclosure provides a method for predicting vehicle conflicts at a road intersection. The method includes: acquiring vehicles at the road intersection as target vehicles; predicting the driving trajectories of the target vehicles to obtain predicted driving trajectories; generating dynamic interaction boxes for each of the target vehicles in real time based on the predicted driving trajectories; predicting vehicle conflicts based on the dynamic interaction boxes. Through the trajectory prediction method, the original rectangular box is changed to a curve box based on the predicted trajectory, which can not only better describe the complex steering behavior of the vehicle during driving but also take into account the expected driving behavior of the vehicle to identify potential conflict objects in advance. At the same time, for the interaction situation at the road intersection, a method for identifying conflicts is predicted from space and time. This method reduces the calculation amount while ensuring the accuracy of predicting vehicle conflicts.

[0092] Based on the above embodiment, after predicting vehicle conflicts based on the dynamic interaction box, the embodiment of the present disclosure may specifically include the following steps:

[0093] a4) For target vehicles with risk conflicts, acquire the physical risk information and psychological risk information of the target vehicles.

[0094] b4) Integrate the physical risk information and psychological risk information to obtain target risk information.

[0095] c4) Determine the risk level of the target vehicle according to the target risk information..

[0096] Specifically, human drivers perceive and evaluate driving risks from two perspectives, namely physical risks and psychological risk expectations (or subjective and objective risks), resulting in different risk perceptions and risk tolerances for each driver in dangerous driving situations. Physically, drivers capture real-time driving risks based on the kinematic characteristics of potential risk sources. This solution measures the degree of danger in conflict scenarios through a psycho-physical risk metric framework. First, considering the heterogeneous attention and perception abilities of human drivers in different directions, an elliptical psycho-physical risk field is established; then, for the main interacting objects in the field, their risk field force values are calculated from both physical and psychological risk perspectives; finally, the comprehensive risk metric value is obtained by calculating the resultant field force of the target vehicle.

[0097] Among them, the psycho-physical risk field is considered from two aspects: the heterogeneity of human drivers' risk perception abilities in different directions and the responsibility safety-sensitive model to avoid collisions with the following vehicle and the vehicle cutting in from the front. An elliptical driver psycho-physical risk field model is proposed, where the elliptical line is the equipotential line, and the field strength value is the standard field strength of the main vehicle's psycho-physical risk field.

[0098] As Figure 9 shown, the psycho-physical risk field model is a double-elliptical model, which is a combination of semi-ellipses with the vehicle's centroid as the common center. This combination is defined by the risk field definition axis d = [d1, d2, d3], where d1 is the forward major axis, d2 is the backward major axis, and d3 is the minor axis in the vehicle's lateral direction. The risk field definition axis is determined by the physical risk component and the psychological risk component jointly. The expression for the risk field definition axis is:

[0099]

[0100] Optionally, the way to obtain the physical risk information of the target vehicle can be: obtain the first longitudinal speed of the target vehicle, the second longitudinal speed of the risk vehicle, and the relative lateral speed between the risk vehicle and the target vehicle; where the risk vehicle is a vehicle with a risk conflict with the target vehicle; determine the forward risk component and the backward risk component according to the first longitudinal speed and the second longitudinal speed; determine the lateral risk component according to the relative lateral speed and the lane width; the forward risk component, the backward risk component, and the lateral risk component constitute the physical risk information.

[0101] Specifically, for the calculation of physical motion risks, risks can be classified into three categories: forward, backward, and lateral risks in terms of physical kinematics. and represent forward and backward risks respectively, which are related to the distance that the following vehicle reacts and brakes when the leading vehicle suddenly brakes. The specific expressions are as follows:

[0102]

[0103]

[0104]

[0105]

[0106] In the formula, refers to the longitudinal speed of the risk source (mainly potential interacting vehicles); refers to the longitudinal speed of the host vehicle; is the safety distance calculation function; t dec refers to the minimum reaction time of the driver, generally taken as 1 s; γ2 refers to the maximum deceleration of the vehicle, generally taken as 4 m / s 2 .

[0107] In terms of lateral risk, considering that the driver generally does not require a large lateral gap, the lateral gap can be simplified to:

[0108]

[0109] In the formula, LW is the lane width; is the lateral speed of the risk source α relative to the host vehicle, where a positive value indicates approaching; γ3, γ4 are fixed coefficients, with values of 0.5 and 2.

[0110] Optionally, the way to obtain the psychological risk information of the target vehicle can be: obtaining the component of the driving behavior expectation factor, the component of the individual characteristic factor, and the anisotropic characteristic component of the risk perception in different directions of the driver of the target vehicle; and forming the psychological risk information from the component of the driving behavior expectation factor, the component of the individual characteristic factor, and the anisotropic characteristic component of the risk perception in different directions.

[0111] Specifically, in the calculation of psychological motion risk, different drivers have different perceptions of the current driving risk when facing the same traffic conditions, and the physiological factors of the driver will affect the driver's perception and decision-making. Therefore, the psychological risk can be defined as:

[0112]

[0113] In the formula, P α is the driving behavior expectation factor; D s represents the individual characteristic factor of the host vehicle driver; μ is the anisotropic characteristic vector representing the driver's risk perception in different directions, with a value of [1, 0.8, 0.5].

[0114] Specifically, when there are multiple risk sources, the total risk is calculated using the superimposed risk vector at this time.

[0115] In this technical solution, the risk level of the target vehicle is determined based on physical risk information and psychological risk information, which not only considers the attention and perception capabilities of human drivers, but also takes into account the physical kinematic state of the vehicle and the psychological expectations of other traffic participants. It can evaluate the driving risks in two-dimensional area scenarios such as intersection conflicts in real time, which is of great significance for the research on vehicle safety at intersections.

[0116] Embodiment 2

[0117] Figure 10 This invention embodiment also provides a structural schematic diagram of a vehicle conflict prediction device for a road intersection, as Figure 10 shown. The device includes: a target vehicle acquisition module 210, a driving trajectory prediction module 220, an interaction box generation module 230, and a vehicle conflict prediction module 240.

[0118] The target vehicle acquisition module 210 is used to acquire the vehicle at the road intersection as the target vehicle;

[0119] The driving trajectory prediction module 220 is used to predict the driving trajectory of the target vehicle to obtain a predicted driving trajectory;

[0120] The interaction box generation module 230 is used to generate dynamic interaction boxes for each target vehicle in real time based on the predicted driving trajectory;

[0121] The vehicle conflict prediction module 240 is used to predict vehicle conflicts based on the dynamic interaction boxes.

[0122] The technical solution provided by this public embodiment uses this method. Through the trajectory prediction method, the original rectangular box is changed to a curve box based on the predicted trajectory, which can not only better describe the complex steering behavior of the vehicle when driving, but also take into account the expected driving behavior of the vehicle to identify potential conflict objects in advance. At the same time, for the interaction situation at the road intersection, a method for identifying conflicts from spatial and temporal predictions reduces the calculation amount while ensuring the accuracy of predicting vehicle conflicts.

[0123] Further, the target vehicle acquisition module 210 can be used to:

[0124] Acquire the actual trajectory points of the vehicle at the current moment;

[0125] If the actual trajectory points are within the set intersection range, then the vehicle is at the road intersection, and the vehicle is determined as the target vehicle.

[0126] Further, the interaction box generation module 230 can be used to:

[0127] Generate a static interaction box based on the vehicle width and driving direction of the target vehicle, and generate a vehicle body area box based on the center point and vehicle width of the target vehicle;

[0128] For the current target vehicle, determine the following vehicle in the following distance of the current target vehicle according to the static interaction box of the current target vehicle and the vehicle body area boxes of other target vehicles;

[0129] Generate a dynamic interaction box of the current target vehicle according to the driving data of the current target vehicle and the following vehicle in the following distance and the predicted driving trajectory.

[0130] Furthermore, the interaction box generation module 230 can also be used for:

[0131] Determine other target vehicles whose vehicle body area boxes have intersections with the static interaction box as the leading vehicles of the current target vehicle;

[0132] Determine the following vehicle in the following distance as the following vehicle in the following distance of the current target vehicle.

[0133] Furthermore, the interaction box generation module 230 can also be used for:

[0134] Determine the safety distance between the current target vehicle and the following vehicle in the following distance according to the driving data, and obtain the actual distance between the current target vehicle and the following vehicle in the following distance;

[0135] Take the minimum value of the safety distance and the actual distance as the extension length of the dynamic interaction box, and take the vehicle width of the current target vehicle as the extension width of the dynamic interaction box;

[0136] Perform calculations on the predicted driving trajectory using the infinitesimal element method to generate a trajectory curve of the extension length;

[0137] Generate a dynamic interaction box according to two such trajectory curves and the extension width; wherein, the dynamic interaction box extends forward from the vehicle head.

[0138] Furthermore, the vehicle conflict prediction module 240 can be used for:

[0139] Determine two dynamic interaction boxes with an intersection area, which are respectively a first dynamic interaction box and a second dynamic interaction box; wherein, the first dynamic interaction box corresponds to a first target vehicle, and the second dynamic interaction box corresponds to a second target vehicle;

[0140] Determine the first time duration and the second time duration for the first target vehicle and the second target vehicle to reach the intersection area respectively starting from the current moment;

[0141] If the difference between the first duration and the second duration is less than a set threshold, there is a vehicle conflict between the first target vehicle and the second target vehicle.

[0142] Further, after predicting vehicle conflicts based on the dynamic interaction box, the embodiment of the present invention may further include: a risk level determination module.

[0143] Further, the risk level determination module may be used to:

[0144] For a target vehicle with a risk conflict, obtain the physical risk information and psychological risk information of the target vehicle;

[0145] Fuse the physical risk information and the psychological risk information to obtain target risk information;

[0146] Determine the risk level of the target vehicle according to the target risk information.

[0147] Further, the risk level determination module may also be used to:

[0148] Obtain the first longitudinal speed of the target vehicle, the second longitudinal speed of the risk vehicle, and the relative lateral speed between the risk vehicle and the target vehicle; wherein, the risk vehicle is a vehicle having a risk conflict with the target vehicle;

[0149] Determine a forward risk component and a backward risk component according to the first longitudinal speed and the second longitudinal speed;

[0150] Determine a lateral risk component according to the relative lateral speed and the lane width;

[0151] The forward risk component, the backward risk component, and the lateral risk component constitute the physical risk information.

[0152] Further, the risk level determination module may also be used to:

[0153] Obtain the driving behavior expectation factor component, the individual characteristic factor component, and the anisotropic characteristic component of the driver of the target vehicle for risk perception in different directions;

[0154] The driving behavior expectation factor component, the individual characteristic factor component, and the anisotropic characteristic component of risk perception in different directions constitute the psychological risk information.

[0155] The above device can execute the methods provided in all the foregoing embodiments of the present invention, and has corresponding functional modules and beneficial effects for executing the above methods. For technical details not described in detail in this embodiment, reference may be made to the methods provided in all the foregoing embodiments of the present invention.

[0156] Embodiment III

[0157] Figure 11 Shown is a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0158] As Figure 11 , the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0159] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0160] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the vehicle conflict prediction method at a road intersection.

[0161] In some embodiments, the vehicle conflict prediction method at a road intersection can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by the processor 11, one or more steps of the vehicle conflict prediction method at a road intersection described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the vehicle conflict prediction method by any other suitable means (e.g., by means of firmware).

[0162] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0163] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0164] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0165] For purposes of providing interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0166] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0167] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0168] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0169] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A vehicle conflict prediction method for road intersections, characterized in that Including: Obtain the vehicles at the road intersection as target vehicles; Predict the driving trajectories of the target vehicles to obtain predicted driving trajectories; Generate dynamic interaction boxes for each of the target vehicles in real time based on the predicted driving trajectories; Predict vehicle conflicts based on the dynamic interaction boxes; Among them, generating dynamic interaction boxes for each of the target vehicles in real time based on the predicted driving trajectories includes: Generate a static interaction box according to the vehicle width and driving direction of the target vehicle, and generate a vehicle body area box according to the center point and vehicle width of the target vehicle; For the current target vehicle, determine the following vehicle following the current target vehicle according to the static interaction box of the current target vehicle and the vehicle body area boxes of other target vehicles; Generate the dynamic interaction box of the current target vehicle according to the driving data of the current target vehicle and the following vehicle and the predicted driving trajectory; Among them, generating the dynamic interaction box of the current target vehicle according to the driving data of the current target vehicle and the following vehicle and the predicted driving trajectory includes: Determine the safe distance between the current target vehicle and the following vehicle according to the driving data, and obtain the actual distance between the current target vehicle and the following vehicle; Take the minimum value of the safe distance and the actual distance as the extension length of the dynamic interaction box, and take the vehicle width of the current target vehicle as the extension width of the dynamic interaction box; Calculate the predicted driving trajectory using the infinitesimal method to generate a trajectory curve of the extension length; Generate a dynamic interaction box according to the two trajectory curves and the extension width; among them, the dynamic interaction box extends forward from the vehicle head; The method further includes: when the vehicle turns, increase the curve length of the dynamic interaction box.

2. The method according to claim 1, characterized in that, Obtain the vehicles at the road intersection as target vehicles, including: Obtain the actual trajectory points of the vehicle at the current moment; If the actual trajectory points are within the set intersection range, the vehicle is at the road intersection, and the vehicle is determined as a target vehicle.

3. The method according to claim 1, wherein Determine the following vehicle of the current target vehicle according to the static interaction box of the current target vehicle and the vehicle body area boxes of other target vehicles, including: Determine other target vehicles whose vehicle body area boxes have intersections with the static interaction box as the preceding vehicles of the current target vehicle; Determine the preceding vehicle closest to the current target vehicle as the following vehicle.

4. The method according to claim 1, wherein Predict vehicle conflicts based on the dynamic interaction box, including: Determine two dynamic interaction boxes with an intersection area, which are the first dynamic interaction box and the second dynamic interaction box respectively; among them, the first dynamic interaction box corresponds to the first target vehicle, and the second dynamic interaction box corresponds to the second target vehicle; Determine the first duration and the second duration for the first target vehicle and the second target vehicle to reach the intersection area respectively starting from the current moment; If the difference between the first duration and the second duration is less than the set threshold, there is a vehicle conflict between the first target vehicle and the second target vehicle.

5. The method according to claim 1, characterized in that, After predicting vehicle conflicts based on the dynamic interaction box, it further includes: For a target vehicle with risk conflicts, obtain the physical risk information and psychological risk information of the target vehicle; Fuse the physical risk information and the psychological risk information to obtain target risk information; Determine the risk level of the target vehicle according to the target risk information.

6. The method according to claim 5, wherein Obtain the physical risk information of the target vehicle, including: Obtain the first longitudinal speed of the target vehicle, the second longitudinal speed of the risk vehicle, and the relative lateral speed between the risk vehicle and the target vehicle; wherein, the risk vehicle is a vehicle having a risk conflict with the target vehicle; Determine the forward risk component and the backward risk component according to the first longitudinal speed and the second longitudinal speed; Determine the lateral risk component according to the relative lateral speed and the lane width; The forward risk component, the backward risk component, and the lateral risk component constitute the physical risk information.

7. The method according to claim 5, wherein Obtain the psychological risk information of the target vehicle, including: Obtain the driving behavior expectation factor component, the individual characteristic factor component of the driver of the target vehicle, and the anisotropic characteristic component of the risk perception in different directions; The driving behavior expectation factor component, the individual characteristic factor component, and the anisotropic characteristic component of the risk perception in different directions constitute the psychological risk information.

8. A vehicle conflict prediction device for a road intersection, characterized in that, Include: A target vehicle acquisition module, configured to acquire a vehicle at a road intersection as a target vehicle; A driving trajectory prediction module, configured to predict the driving trajectory of the target vehicle to obtain a predicted driving trajectory; An interaction box generation module, configured to generate dynamic interaction boxes of each target vehicle in real time based on the predicted driving trajectory; A vehicle conflict prediction module, configured to predict vehicle conflicts based on the dynamic interaction boxes; Wherein, the interaction box generation module is specifically configured to: Generate a static interaction box according to the vehicle width and driving direction of the target vehicle, and generate a vehicle body area box according to the center point and the vehicle width of the target vehicle; For the current target vehicle, determine the leading vehicle following the current target vehicle according to the static interaction box of the current target vehicle and the vehicle body area boxes of other target vehicles; Generate a dynamic interaction box of the current target vehicle according to the driving data of the current target vehicle and the leading vehicle following it and the predicted driving trajectory; The interaction box generation module is further configured to: Determine the safety distance between the current target vehicle and the leading vehicle following it according to the driving data, and obtain the actual distance between the current target vehicle and the leading vehicle following it; Use the minimum value of the safety distance and the actual distance as the extension length of the dynamic interaction box, and use the vehicle width of the current target vehicle as the extension width of the dynamic interaction box; Calculate the predicted driving trajectory using the infinitesimal method to generate a trajectory curve of the extension length; Generate a dynamic interaction box according to the two trajectory curves and the extension width; wherein, the dynamic interaction box extends forward from the vehicle head; The interaction box generation module is further configured to: When the vehicle turns, increase the curve length of the dynamic interaction box.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, enables the at least one processor to execute the vehicle conflict prediction method for a road intersection according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, implements the vehicle conflict prediction method for a road intersection according to any one of claims 1-7.

Images