Dynamic judgment method and device for vehicle collision risk

Abstract

The invention relates to the technical field of data analysis, and discloses a vehicle collision risk dynamic discrimination method and device, and the method comprises the steps: determining a target driving scene corresponding to a vehicle; according to the target driving scene, based on a positioning technology and pre-acquired map data, determining a target monitoring lane; acquiring traffic data corresponding to the target monitoring lane and real-time driving data of the vehicle; the traffic data comprises lane road condition data and / or motion data of adjacent objects; and judging whether the vehicle has a collision risk according to the traffic data and the real-time driving data to obtain a risk judgment result. It can be seen that whether the collision risk exists or not at present can be judged in real time based on the road condition and the vehicle driving data, the judgment timeliness and judgment accuracy of the vehicle collision risk can be improved, and therefore risk response measures can be taken in time, and driving safety can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and device for dynamically determining vehicle collision risk. Background Art

[0002] In driving scenarios (such as driving tests / driving training scenarios), vehicles are traveling in complex and changing traffic environments, and it is necessary to judge the risk of vehicle collision during driving in real time so that the driver can respond to emergencies safely and promptly.

[0003] In actual driving, the determination of vehicle collision risk usually relies on manual judgment. However, manual judgment needs to rely on the driver's driving experience and intuitive perception to assess the collision risk. When the driver is inexperienced, reacts slowly, makes subjective judgment errors, or the traffic environment changes suddenly, the manual judgment result is easily disturbed, making it difficult to continuously, accurately, and comprehensively capture the potential risks in the traffic environment, and there are still hidden dangers to driving safety.

[0004] Therefore, it is particularly important to propose a technical solution that can improve the timeliness and accuracy of vehicle collision risk determination to improve driving safety. Summary of the invention

[0005] The present invention provides a method and device for dynamically distinguishing vehicle collision risks, which can improve the timeliness and accuracy of distinguishing vehicle collision risks and help improve driving safety.

[0006] In order to solve the above technical problems, the first aspect of the present invention discloses a dynamic determination method of vehicle collision risk, the method comprising:

[0007] Determine the target driving scenario corresponding to the vehicle;

[0008] According to the target driving scenario, based on positioning technology and pre-acquired map data, determine the target monitoring lane;

[0009] Acquire traffic data corresponding to the target monitoring lane and real-time driving data of the vehicle; the traffic data includes lane road condition data and / or motion data of adjacent objects;

[0010] Based on the traffic data and the real-time driving data, it is determined whether the vehicle has a collision risk, and a risk determination result is obtained.

[0011] As an optional implementation, in the first aspect of the present invention, determining the target monitoring lane according to the target driving scene based on positioning technology and pre-acquired map data includes:

[0012] When the target driving scenario includes a driving test and training scenario, analyzing the test and training item currently being assessed in the driving test and training scenario; determining a first target lane corresponding to the test and training item based on the positioning technology and pre-acquired map data according to the test and training item; the first target lane includes at least one lane that the vehicle needs to pass through / enter in the test and training item;

[0013] When the target driving scenario includes a traffic environment scenario, determining a risk factor type corresponding to the traffic environment scenario; determining a second target lane according to the risk factor type based on the positioning technology and the map data; the second target lane includes at least one adjacent lane corresponding to the vehicle;

[0014] The current lane and the target lane where the vehicle is located are determined as the target monitoring lane corresponding to the vehicle; the target lane includes the first target lane and / or the second target lane.

[0015] As an optional implementation manner, in the first aspect of the present invention, judging whether the vehicle has a collision risk based on the traffic data and the real-time driving data to obtain a risk judgment result includes:

[0016] Calculate the traffic flow parameters corresponding to the target monitoring lane according to the traffic data and the real-time driving data; the traffic flow parameters include a combination of one or more of the average vehicle speed, vehicle flow density, traffic flow and time index within the target area of ​​the target monitoring lane;

[0017] Calculating the risk parameter corresponding to the vehicle based on the traffic data and the real-time driving data and a predetermined traffic flow analysis model;

[0018] Based on the determined collision risk assessment algorithm, judging whether there is any of the neighboring objects whose distance to the vehicle is less than or equal to a preset distance within a first preset time period after the current moment according to the traffic flow parameter and the risk parameter;

[0019] When it is determined that the distance between any of the neighboring objects and the vehicle within the first preset time period is less than or equal to the preset distance, determining that the vehicle is at risk of collision;

[0020] When it is determined that there is no adjacent object whose distance to the vehicle is less than or equal to the preset distance within the first preset time period, it is determined that there is no collision risk for the vehicle.

[0021] As an optional implementation, in the first aspect of the present invention, when the risk judgment result is used to indicate that the vehicle has the collision risk, the method further includes:

[0022] generating at least one driving adjustment guide in the form of guidance regarding the collision risk; the driving adjustment guide is used to prompt the driver to adjust the driving operation for the vehicle;

[0023] Determining whether the driver is detected to have performed a driving adjustment operation corresponding to the driving adjustment instruction within a second preset time period and whether a matching degree between the driving adjustment operation and the driving adjustment instruction is higher than or equal to a preset matching degree;

[0024] When it is determined that the driver is not detected performing the driving adjustment operation corresponding to the driving adjustment instructions within the second preset time period or the matching degree between the driving adjustment operation and the driving adjustment instructions is lower than the preset matching degree, based on the assisted driving function corresponding to the vehicle, the vehicle is controlled to perform the assisted driving operation corresponding to the driving adjustment instructions.

[0025] As an optional implementation, in the first aspect of the present invention, when the risk judgment result is used to indicate that the vehicle has the collision risk, the method further includes:

[0026] When the target driving scenario includes a driving test and training scenario and the vehicle is in an assessment state, according to the collision risk, the driving adjustment operation and the traffic data, extending a preset assessment time of the vehicle for a current assessment item to obtain a target assessment time;

[0027] detecting a first driving performance of the driver on the vehicle within the target assessment time;

[0028] A first assessment result of the driver on the current assessment item is evaluated based on the target assessment duration and the first driving performance.

[0029] As an optional implementation manner, in the first aspect of the present invention, extending a preset assessment time of the vehicle for a current assessment item according to the collision risk, the driving adjustment operation and the traffic data to obtain a target assessment time comprises:

[0030] Assessing the risk level of the collision risk and determining a risk level coefficient corresponding to the risk level;

[0031] According to the traffic data, evaluating the road condition complexity level corresponding to the target monitoring lane, and determining the road condition complexity coefficient corresponding to the road condition complexity level;

[0032] evaluating an emergency response coefficient of the driver according to the driver's reaction time to the driving adjustment operation;

[0033] detecting a driving intervention situation corresponding to the driving assistance function, and determining a driving intervention coefficient corresponding to the driving intervention situation;

[0034] Based on the determined extension formula, the target assessment duration is determined according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment duration of the current assessment item.

[0035] As an optional implementation manner, in the first aspect of the present invention, the target assessment duration is determined based on the determined extension formula according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment duration of the current assessment item, including:

[0036] Based on the determined extension formula, the extended assessment time corresponding to the current assessment item is calculated according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment time of the current assessment item;

[0037] Determine whether the extended assessment duration is less than or equal to a preset maximum duration threshold;

[0038] When it is determined that the extended assessment duration is less than or equal to the maximum duration threshold, the extended assessment duration is determined as the target assessment duration;

[0039] When it is determined that the extended assessment duration is greater than the maximum duration threshold, the maximum duration threshold is determined as the target assessment duration.

[0040] A second aspect of the present invention discloses a dynamic determination device for vehicle collision risk, the device comprising:

[0041] A determination module, used to determine a target driving scenario corresponding to the vehicle;

[0042] The determination module is further used to determine a target monitoring lane according to the target driving scenario based on positioning technology and pre-acquired map data;

[0043] An acquisition module, used to acquire traffic data corresponding to the target monitoring lane and real-time driving data of the vehicle; the traffic data includes lane road condition data and / or motion data of adjacent objects;

[0044] The judgment module is used to judge whether the vehicle has a collision risk based on the traffic data and the real-time driving data, and obtain a risk judgment result.

[0045] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the target monitoring lane according to the target driving scene, based on positioning technology and pre-acquired map data includes:

[0046] When the target driving scenario includes a driving test and training scenario, analyzing the test and training item currently being assessed in the driving test and training scenario; determining a first target lane corresponding to the test and training item based on the positioning technology and pre-acquired map data according to the test and training item; the first target lane includes at least one lane that the vehicle needs to pass through / enter in the test and training item;

[0047] When the target driving scenario includes a traffic environment scenario, determining a risk factor type corresponding to the traffic environment scenario; determining a second target lane according to the risk factor type based on the positioning technology and the map data; the second target lane includes at least one adjacent lane corresponding to the vehicle;

[0048] The current lane and the target lane where the vehicle is located are determined as the target monitoring lane corresponding to the vehicle; the target lane includes the first target lane and / or the second target lane.

[0049] As an optional implementation, in the second aspect of the present invention, the judgment module judges whether the vehicle has a collision risk based on the traffic data and the real-time driving data, and a specific method of obtaining the risk judgment result includes:

[0050] Calculate the traffic flow parameters corresponding to the target monitoring lane according to the traffic data and the real-time driving data; the traffic flow parameters include a combination of one or more of the average vehicle speed, vehicle flow density, traffic flow and time index within the target area of ​​the target monitoring lane;

[0051] Calculating the risk parameter corresponding to the vehicle based on the traffic data and the real-time driving data and a predetermined traffic flow analysis model;

[0052] Based on the determined collision risk assessment algorithm, judging whether there is any of the neighboring objects whose distance to the vehicle is less than or equal to a preset distance within a first preset time period after the current moment according to the traffic flow parameter and the risk parameter;

[0053] When it is determined that the distance between any of the neighboring objects and the vehicle within the first preset time period is less than or equal to the preset distance, determining that the vehicle is at risk of collision;

[0054] When it is determined that there is no adjacent object whose distance to the vehicle is less than or equal to the preset distance within the first preset time period, it is determined that there is no collision risk for the vehicle.

[0055] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0056] a generating module, configured to generate at least one driving adjustment guide in the form of a guide regarding the collision risk when the risk judgment result indicates that the vehicle has the collision risk; the driving adjustment guide is configured to prompt the driver to adjust the driving operation for the vehicle;

[0057] The judgment module is further used to judge whether the driver is detected to perform the driving adjustment operation corresponding to the driving adjustment instruction within a second preset time period and whether the matching degree between the driving adjustment operation and the driving adjustment instruction is higher than or equal to a preset matching degree;

[0058] A control module is used to control the vehicle to perform the assisted driving operation corresponding to the driving adjustment guideline based on the assisted driving function corresponding to the vehicle when the judgment module determines that the driver is not detected to perform the driving adjustment operation corresponding to the driving adjustment guideline within the second preset time period or the matching degree between the driving adjustment operation and the driving adjustment guideline is lower than the preset matching degree.

[0059] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0060] A duration extension module, configured to, when the risk judgment result indicates that the vehicle has the collision risk, when the target driving scenario includes a driving test and training scenario and the vehicle is in an assessment state, extend the preset assessment duration of the vehicle for the current assessment item according to the collision risk, the driving adjustment operation and the traffic data to obtain a target assessment duration;

[0061] A detection module, configured to detect a first driving performance of the driver on the vehicle within the target assessment duration;

[0062] An evaluation module is used to evaluate the first evaluation result of the driver on the current evaluation item according to the target evaluation time and the first driving performance.

[0063] As an optional implementation, in the second aspect of the present invention, the duration extension module extends the preset assessment duration of the vehicle for the current assessment item according to the collision risk, the driving adjustment operation and the traffic data, and the specific manner of obtaining the target assessment duration includes:

[0064] Assessing the risk level of the collision risk and determining a risk level coefficient corresponding to the risk level;

[0065] According to the traffic data, evaluating the road condition complexity level corresponding to the target monitoring lane, and determining the road condition complexity coefficient corresponding to the road condition complexity level;

[0066] evaluating an emergency response coefficient of the driver according to the driver's reaction time to the driving adjustment operation;

[0067] detecting a driving intervention situation corresponding to the driving assistance function, and determining a driving intervention coefficient corresponding to the driving intervention situation;

[0068] Based on the determined extension formula, the target assessment duration is determined according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment duration of the current assessment item.

[0069] As an optional implementation, in the second aspect of the present invention, the duration extension module determines the target assessment duration based on the determined extension formula, according to the risk level coefficient, the road complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment duration of the current assessment item. The specific method includes:

[0070] Based on the determined extension formula, the extended assessment time corresponding to the current assessment item is calculated according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment time of the current assessment item;

[0071] Determine whether the extended assessment duration is less than or equal to a preset maximum duration threshold;

[0072] When it is determined that the extended assessment duration is less than or equal to the maximum duration threshold, the extended assessment duration is determined as the target assessment duration;

[0073] When it is determined that the extended assessment duration is greater than the maximum duration threshold, the maximum duration threshold is determined as the target assessment duration.

[0074] The third aspect of the present invention discloses another dynamic determination device for vehicle collision risk, the device comprising:

[0075] A memory storing executable program code;

[0076] a processor coupled to the memory;

[0077] The processor calls the executable program code stored in the memory to execute part or all of the steps of the dynamic determination method of vehicle collision risk disclosed in the first aspect of the present invention.

[0078] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps of the dynamic determination method of vehicle collision risk disclosed in the first aspect of the present invention.

[0079] Compared with the prior art, the present invention has the following beneficial effects:

[0080] In the present invention, the target driving scene corresponding to the vehicle is determined; according to the target driving scene, the target monitoring lane is determined based on the positioning technology and the pre-acquired map data; the traffic data corresponding to the target monitoring lane and the real-time driving data of the vehicle are obtained; the traffic data includes the road condition data of the lane and / or the motion data of the neighboring objects; according to the traffic data and the real-time driving data, it is judged whether the vehicle has a collision risk, and a risk judgment result is obtained. It can be seen that the implementation of the present invention can determine the target monitoring lane according to the target driving scene corresponding to the determined vehicle, and based on the positioning technology and the map data, and then obtain the traffic data of the target monitoring lane and the real-time driving data of the vehicle, so as to judge whether the vehicle has a collision risk according to the traffic data and the real-time driving data, and can realize comprehensive and accurate monitoring of the vehicle driving state, so as to be able to judge whether there is a collision risk in real time based on the road condition and the vehicle driving data, improve the timeliness and accuracy of the judgment of the vehicle collision risk, and be conducive to timely discovery of potential collision risks and subsequent timely risk response measures, thereby helping to improve driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0082] Figure 1 It is a flow chart of a method for dynamically distinguishing vehicle collision risk disclosed in an embodiment of the present invention;

[0083] Figure 2 It is a flow chart of another method for dynamically distinguishing vehicle collision risk disclosed in an embodiment of the present invention;

[0084] Figure 3 It is a schematic diagram of a scenario to which a dynamic determination method of vehicle collision risk disclosed in an embodiment of the present invention is applicable;

[0085] Figure 4 It is a structural schematic diagram of a dynamic determination device for vehicle collision risk disclosed in an embodiment of the present invention;

[0086] Figure 5 It is a structural schematic diagram of another dynamic determination device for vehicle collision risk disclosed in an embodiment of the present invention;

[0087] Figure 6 It is a structural schematic diagram of another dynamic determination device for vehicle collision risk disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0088] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0089] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0090] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0091] The present invention discloses a method and device for dynamically distinguishing vehicle collision risks, which can determine the target monitoring lane according to the target driving scene corresponding to the determined vehicle, based on positioning technology and map data, and then obtain the traffic data of the target monitoring lane and the real-time driving data of the vehicle, so as to judge whether the vehicle has a collision risk according to the traffic data and the real-time driving data, and can realize comprehensive and accurate monitoring of the vehicle driving state, so as to judge whether there is a collision risk in real time based on the road conditions and the vehicle driving data, improve the timeliness and accuracy of the judgment of the vehicle collision risk, and be conducive to timely discovery of potential collision risks and subsequent timely risk response measures, thereby helping to improve driving safety. The following are detailed descriptions.

[0092] Embodiment 1

[0093] See also Figure 1 , Figure 1 : is a flow chart of a method for dynamically determining vehicle collision risk disclosed in an embodiment of the present invention. Figure 1 The described method for dynamic identification of vehicle collision risk can be applied to a dynamic identification device for vehicle collision risk, which may include a dynamic identification device, a dynamic identification terminal, a dynamic identification system and a server, wherein the server includes a local server or a cloud server, which is not limited in the embodiments of the present invention; the device can be applied to a vehicle or a control system capable of controlling the driving of a vehicle, and optionally, the vehicle can be a driving training vehicle or a driving test vehicle, or other vehicles, which is not limited in the embodiments of the present invention. Figure 1 As shown, the dynamic determination method of vehicle collision risk may include the following operations:

[0094] 101. Determine a target driving scenario corresponding to the vehicle.

[0095] In an embodiment of the present invention, the target driving scenario corresponding to the vehicle may include a driving purpose scenario and / or a traffic environment scenario; optionally, the driving purpose scenario may include a driving test and training scenario (for example, a driving test scenario, a driving training scenario), a driving work scenario (for example, a freight driver driving scenario), a road inspection scenario, and a road cleaning scenario, which is not limited in the embodiment of the present invention; optionally, the traffic environment scenario may include a highway scenario and / or an urban road scenario. Exemplarily, the highway scenario may include a highway following vehicle driving scenario, and the urban road scene may include a lane changing scenario or an intersection scene, which is not limited in the embodiment of the present invention.

[0096] In the embodiment of the present invention, optionally, the target driving scene corresponding to the vehicle can be obtained by analyzing the sensor data collected by the sensor corresponding to the vehicle (for example, image data collected by the camera), or the target driving scene corresponding to the vehicle can be obtained by analyzing the instructions received by the vehicle (for example, driving test instructions), which is not limited to the embodiment of the present invention.

[0097] 102. According to the target driving scenario, based on positioning technology and pre-acquired map data, determine the target monitoring lane.

[0098] In the embodiment of the present invention, optionally, the positioning technology may be RTK (Real-Time Kinematic, real-time dynamic positioning technology) positioning technology, or may be other types of positioning technology, which is not limited in the embodiment of the present invention.

[0099] 103. Obtain traffic data corresponding to the target monitoring lane and real-time driving data of the vehicle.

[0100] In an embodiment of the present invention, traffic data corresponding to the target monitoring lane includes lane condition data and / or motion data of neighboring objects; wherein, optionally, lane condition data may include a combination of one or more of lane width, curve spurt, lane accident conditions, and lane congestion conditions, which is not limited in the embodiment of the present invention; optionally, neighboring objects may include neighboring vehicles and / or neighboring pedestrians, which is not limited in the embodiment of the present invention; motion data of neighboring objects may include a combination of one or more of movement direction, movement speed, and distance between the vehicle and the neighboring object, which is not limited in the embodiment of the present invention. Optionally, the lane condition data is collected by the sensor corresponding to the vehicle, or it may be determined based on the road condition broadcast data received by the vehicle, which is not limited in the embodiment of the present invention.

[0101] In an embodiment of the present invention, the real-time driving data of the vehicle may include a combination of one or more of driving direction, driving speed, steering wheel angle, throttle mileage, braking mileage, and vehicle heading angle, which is not limited in the embodiment of the present invention.

[0102] 104. Based on traffic data and real-time driving data, determine whether the vehicle has a collision risk and obtain a risk judgment result.

[0103] It can be seen that the method described in the embodiment of the present invention can determine the target monitoring lane according to the target driving scenario corresponding to the determined vehicle and based on positioning technology and map data, and then obtain the traffic data of the target monitoring lane and the real-time driving data of the vehicle, so as to judge whether the vehicle has a collision risk based on the traffic data and the real-time driving data, and can realize comprehensive and accurate monitoring of the vehicle's driving status, so as to be able to judge whether there is a collision risk in real time based on road conditions and vehicle driving data, improve the timeliness and accuracy of the judgment of vehicle collision risk, facilitate timely discovery of potential collision risks and subsequent timely risk response measures, and thus facilitate improving driving safety.

[0104] In an optional embodiment, according to the target driving scenario, based on the positioning technology and pre-acquired map data, determining the target monitoring lane may include the following operations:

[0105] When the target driving scenario includes a driving test and training scenario, analyzing the test and training item currently being assessed in the driving test and training scenario; determining a first target lane corresponding to the test and training item based on the positioning technology and pre-acquired map data according to the test and training item; the first target lane includes at least one lane that the vehicle needs to pass through / need to enter in the test and training item;

[0106] When the target driving scenario includes a traffic environment scenario, determining a risk factor type corresponding to the traffic environment scenario; determining a second target lane based on the risk factor type and positioning technology and map data; the second target lane includes at least one adjacent lane corresponding to the vehicle;

[0107] The current lane and the target lane where the vehicle is located are determined as the target monitoring lanes corresponding to the vehicle; the target lanes include the first target lane and / or the second target lane.

[0108] The test and training item may be any item in a driving test and / or driving training, and the embodiment of the present invention does not limit this.

[0109] Among them, the risk factor type may include an environmental factor type (e.g., bad weather factors, narrow lane factors) and / or a complex scenario factor type (e.g., highway scenario factors, intersection scenario factors), which are not limited in the embodiments of the present invention. Exemplarily, when the risk factor type includes an environmental factor type, the second target lane may include one / two adjacent lanes in the direction of travel of the vehicle, and when the risk factor type includes an intersection scenario factor type in the complex scenario factor type, the second target lane may include one / two adjacent lanes in the direction of travel of the vehicle and / or a lane in another direction of the intersection other than the direction of travel of the vehicle, which are not limited in the embodiments of the present invention.

[0110] It can be seen that this optional embodiment can determine the first target lane corresponding to the test and training item according to the currently assessed test and training item when the target driving scenario includes a driving test and training scenario; and determine the second target lane according to the risk factor type corresponding to the traffic environment scenario when the target driving scenario includes a traffic environment scenario, and determine the current lane and target lane where the vehicle is located as the target monitoring lanes corresponding to the vehicle, which can improve the analysis accuracy and analysis flexibility of the target driving scenario, is conducive to improving the determination flexibility and determination accuracy of the target lane, and further is conducive to improving the determination accuracy of the target monitoring lane.

[0111] In this optional embodiment, optionally, according to the test and training project, based on the positioning technology and pre-acquired map data, determining the first target lane corresponding to the test and training project may include the following operations:

[0112] When the test and training project is a vehicle merging project / vehicle lane changing project, the merging direction / lane changing direction of the vehicle is identified, and according to the merging direction / lane changing direction, based on the positioning technology and pre-acquired map data, the required path of the lane with respect to the merging direction / lane changing direction and / or the first lane to be entered is determined as the first target lane;

[0113] When the test and training project is a vehicle merging project, based on positioning technology and map data, the path required for the vehicle to turn around and / or the second lane required to enter is determined as the first target lane.

[0114] It can be seen that this optional embodiment can also determine the path / entry lane required for the training content of the training project as the first target lane according to different training projects, which can further improve the determination accuracy of the first target lane, which is conducive to further improving the determination accuracy of the target monitoring lane.

[0115] In this optional embodiment, optionally, judging whether the vehicle has a collision risk based on the traffic data and the real-time driving data and obtaining the risk judgment result may include the following operations:

[0116] Calculate the traffic flow parameters corresponding to the target monitoring lane according to the traffic data and the real-time driving data; the traffic flow parameters include one or more combinations of average vehicle speed, vehicle flow density, traffic flow and time index within the target area of ​​the target monitoring lane;

[0117] According to traffic data and real-time driving data, based on a predetermined traffic flow analysis model, the risk parameters corresponding to the vehicle are calculated;

[0118] Based on the determined collision risk assessment algorithm, according to the traffic flow parameters and the risk parameters, it is determined whether there is any neighboring object whose distance to the vehicle is less than or equal to a preset distance within a first preset time period after the current moment;

[0119] When it is determined that the distance between any neighboring object and the vehicle within the first preset time period is less than or equal to the preset distance, determining that the vehicle is at risk of collision;

[0120] When it is determined that there is no adjacent object whose distance to the vehicle is less than or equal to the preset distance within the first preset time period, it is determined that there is no collision risk for the vehicle.

[0121] Among them, optionally, the average vehicle speed can be obtained by calculating the average speed of all vehicles in the target area, the traffic density can be obtained by calculating the number of vehicles in the target monitoring lane and dividing it by the lane length, and the traffic flow can be obtained by counting the number of vehicles passing a certain point in unit time. The time indicator is used to synchronize the vehicle system time, and the embodiment of the present invention is not limited.

[0122] Optionally, the traffic flow analysis model may include a GM following model and / or a safety spacing model; wherein the GM following model may be used to simulate the influence of the leading vehicle on the driving state of the following vehicle, especially in high-speed driving and dense traffic. The model includes the relationship between acceleration and the speed difference of the leading vehicle, spacing and other factors, specifically:

[0123] a n (t) = λΔv n (t)+γΔx n (t)

[0124] Among them, a n (t) is the acceleration of the nth vehicle at time t, Δv n (t) is the speed difference between the nth vehicle and the preceding vehicle, Δx n (t) is the distance between the nth vehicle and the preceding vehicle, and λ and γ are model parameters.

[0125] Among them, the safety distance model can be used to ensure that vehicles maintain a sufficient safety distance to avoid collisions. Specifically:

[0126]

[0127] Among them, d safe is the required safety distance, v is the current speed, t react is the reaction time, a drc is the maximum deceleration.

[0128] Among them, the risk parameter may include at least one parameter involved in the above model, which is not limited in the embodiment of the present invention.

[0129] Among them, optionally, the collision risk assessment algorithm may include an assessment method for a single target object and / or a deterministic assessment method; among them, the assessment method for a single target object mainly starts from the trajectory of the main vehicle (i.e., the vehicle being assessed) and other traffic participants (such as pedestrians, other vehicles, etc.), and assesses the risk through collision detection; the deterministic assessment method: uses a simplified physical model to describe the movement of traffic participants and selects a certain indicator to characterize the risk. When the calculated result of the indicator exceeds a certain threshold, it is considered that there is a risk. Further optionally, the indicators adopted by the deterministic evaluation method may include a combination of one or more of the time difference indicator (collision warning time TTC), headway time (Time Headway, THW), time to lane crossing (Time to Lane Crossing, TLC) and minimum safety distance (Minimal Safety Margin, MSM), which is not limited in the embodiment of the present invention; wherein, collision warning time TTC = distance between two vehicles / (speed of rear vehicle-speed of front vehicle); headway time is the maximum reaction time of the driver of the rear vehicle when the front vehicle brakes in a vehicle queue traveling on the same lane by measuring the time difference between the front and rear vehicles passing the same place; the lane crossing remaining time refers to the time it takes for the vehicle to deviate from the current position to the lane, which is used to evaluate whether the vehicle can take timely measures before lane deviation; the minimum safety distance to be maintained between vehicles can be calculated based on the braking performance and current speed of the vehicle, which is not limited in the embodiment of the present invention.

[0130] Further optionally, the collision risk assessment algorithm can be determined in the following manner: a preset collision risk assessment algorithm matching the target driving scenario is selected from all preset collision risk assessment algorithms as the above-mentioned collision risk assessment algorithm, which is not limited in the embodiment of the present invention. For example, when following a vehicle on a highway, the headway time (THW) and the collision warning time (TTC) may be more critical; while in complex scenarios such as lane changes or intersections, the remaining time across lanes (TLC) and the minimum safe distance (MSM) may be more important, which is not limited in the embodiment of the present invention.

[0131] Among them, optionally, the preset distance can be a pre-set safe distance; illustratively, when it is predicted that any adjacent vehicle may enter an unsafe distance within the next few seconds (such as: 3 seconds), it is determined that the vehicle is at risk of collision, which is not limited in the embodiments of the present invention.

[0132] It can be seen that this optional embodiment can also first calculate the traffic flow parameters corresponding to the target monitoring lane and the risk parameters corresponding to the vehicle based on the traffic data and real-time driving data, and then based on the collision risk assessment algorithm, according to the traffic flow parameters and the risk parameters, determine whether there is any neighboring object whose distance from the vehicle is less than or equal to the preset distance within the first preset time period after the current moment. If the judgment result is yes, it is determined that the vehicle is at risk of collision, otherwise it is determined that the vehicle is not at risk of collision. This can improve the analysis flexibility and accuracy of traffic data and real-time driving data, thereby helping to improve the accuracy of determining traffic flow parameters and risk parameters, and further help to improve the accuracy of judging whether the distance between the neighboring object and the vehicle is within the preset range, thereby improving the accuracy and reliability of the risk judgment results.

[0133] In this optional embodiment, optionally, the method may further include the following operations:

[0134] The traffic conditions corresponding to the target monitoring lane are evaluated based on the traffic flow parameters; the traffic conditions include traffic flow and / or road congestion.

[0135] Among them, optionally, the average vehicle speed can be used to evaluate the traffic smoothness of the target monitoring lane, and the vehicle flow density can be used to evaluate the congestion level of the target monitoring lane, which is not limited in the embodiment of the present invention.

[0136] Embodiment 2

[0137] See also Figure 2 , Figure 2 : is a flow chart of a method for dynamically determining vehicle collision risk disclosed in an embodiment of the present invention. Figure 2 The described method for dynamic identification of vehicle collision risk can be applied to a dynamic identification device for vehicle collision risk, which may include a dynamic identification device, a dynamic identification terminal, a dynamic identification system and a server, wherein the server includes a local server or a cloud server, which is not limited in the embodiments of the present invention; the device can be applied to a vehicle or a control system capable of controlling the driving of a vehicle, and optionally, the vehicle can be a driving training vehicle or a driving test vehicle, or other vehicles, which is not limited in the embodiments of the present invention. Figure 2 As shown, the dynamic determination method of vehicle collision risk may include the following operations:

[0138] 201. Determine a target driving scenario corresponding to the vehicle.

[0139] 202. According to the target driving scenario, based on the positioning technology and pre-acquired map data, the target monitoring lane is determined.

[0140] 203. Obtain traffic data corresponding to the target monitoring lane and real-time driving data of the vehicle.

[0141] In the embodiment of the present invention, the traffic data includes road condition data and / or motion data of neighboring objects.

[0142] 204. Based on the traffic data and real-time driving data, determine whether the vehicle has a collision risk and obtain a risk judgment result.

[0143] 205. When the risk judgment result is used to indicate that the vehicle has a collision risk, generate at least one form of driving adjustment guidance regarding the collision risk.

[0144] In an embodiment of the present invention, driving adjustment guidance is used to prompt the driver to adjust the driving operation of the vehicle; optionally, the guidance form may include a combination of one or more of sound and light warning forms, voice prompt forms, and visual image / text prompt forms, and may also include other guidance forms, which are not limited in the embodiment of the present invention.

[0145] 206. Determine whether it is detected that the driver performs a driving adjustment operation corresponding to the driving adjustment guideline within a second preset time period and whether a matching degree between the driving adjustment operation and the driving adjustment guideline is higher than or equal to a preset matching degree.

[0146] In an embodiment of the present invention, when the judgment result of step 206 is no, that is, step 206 judges that the driver is not detected to perform the driving adjustment operation corresponding to the driving adjustment guidance within the second preset time period or the matching degree between the driving adjustment operation and the driving adjustment guidance is lower than the preset matching degree, the operation of step 207 is executed; optionally, when the judgment result of step 206 is yes, that is, step 206 judges that the driver is detected to perform the driving adjustment operation corresponding to the driving adjustment guidance within the second preset time period and the matching degree between the driving adjustment operation and the driving adjustment guidance is higher than or equal to the preset matching degree, the operation of step 204 can be re-executed to continue to judge in real time whether the vehicle has a collision risk, which is not limited in the embodiment of the present invention.

[0147] In the embodiment of the present invention, optionally, the matching degree between the driving adjustment operation and the driving adjustment instruction can be determined in the following manner:

[0148] Determine the time difference between the execution time of the driving adjustment operation and the guidance time corresponding to the driving adjustment instructions; determine the first matching degree between the operation sequence of the driving adjustment operation and the guidance sequence corresponding to the driving adjustment instructions; determine the second matching degree between the operation parameters of the driving adjustment operation (such as: a combination of one or more of the steering wheel angle, throttle mileage, brake mileage, and vehicle heading angle) and the guidance operation parameters corresponding to the driving adjustment instructions; determine the matching degree between the driving adjustment operation and the driving adjustment instructions based on the time difference, the first matching degree and the second matching degree, which is not limited in the embodiments of the present invention.

[0149] 207. Based on the assisted driving function corresponding to the vehicle, control the vehicle to execute the assisted driving operation corresponding to the driving adjustment guide.

[0150] In an embodiment of the present invention, optionally, the assisted driving function corresponding to the vehicle can be any assisted driving function in ADAS (Advanced Driving Assistance System) or any assisted driving function in other assisted driving systems, which is not limited in the embodiment of the present invention; exemplarily, the assisted driving function can include at least one of an automatic braking function, a speed reduction function, an automatic lane changing function, and an automatic U-turn function, which is not limited in the embodiment of the present invention.

[0151] In the embodiment of the present invention, for other detailed descriptions of steps 201 to 204, please refer to the detailed description of steps 101 to 104 in the first embodiment, which will not be described in detail in the embodiment of the present invention.

[0152] It can be seen that the method described in the embodiment of the present invention can determine the target monitoring lane according to the target driving scene corresponding to the determined vehicle, and based on the positioning technology and map data, and then obtain the traffic data of the target monitoring lane and the real-time driving data of the vehicle, so as to judge whether the vehicle has a collision risk according to the traffic data and the real-time driving data, and realize comprehensive and accurate monitoring of the vehicle driving state, so as to judge whether there is a collision risk in real time based on the road conditions and the vehicle driving data, improve the timeliness and accuracy of judging the collision risk of the vehicle, and be conducive to timely discovering potential collision risks and taking risk response measures in a timely manner, thereby helping to improve driving safety. In addition, when the vehicle has a collision risk, a driving adjustment guide can be generated, and it can be judged whether the driver performs the corresponding driving adjustment operation within the preset time and whether the operation is performed according to the driving adjustment guide. If the judgment result is no, based on the assisted driving function, the vehicle is controlled to perform the assisted driving operation, which can improve the accuracy of the driving guide for the driver in the case of a collision risk, and improve the timeliness of the use of the assisted driving function and the accuracy of the vehicle control in the case of the driver failing to respond in time or failing to operate correctly, which is conducive to improving the risk response ability of the vehicle, thereby helping to improve driving safety.

[0153] In an optional embodiment, when the risk judgment result is used to indicate that the vehicle has a collision risk, the method may further include the following operations:

[0154] When the target driving scenario includes a driving test and training scenario and the vehicle is in the test state, the preset test time of the vehicle for the current test item is extended according to the collision risk, driving adjustment operation and traffic data to obtain the target test time;

[0155] Detect the driver's first driving performance on the vehicle within the target assessment time;

[0156] Evaluate the driver's first assessment result on the current assessment item based on the target assessment duration and the first driving performance.

[0157] Among them, the first driving performance may include one or more combinations of the driver's action behavior data (for example, whether the driver has observation behavior), the driver's vehicle control operation data (for example, whether the driver shifts gears correctly, whether the driver brakes in time, etc.), and the vehicle's driving data within the target assessment time (for example, driving speed, driving direction, whether the assessment content is completed in accordance with the assessment item requirements, etc.), and the embodiment of the present invention is not limited to this.

[0158] The first assessment result may be the driver's score and / or assessment result (eg, pass / fail) for the current assessment item, which is not limited in the embodiment of the present invention.

[0159] It can be seen that this optional embodiment can, when the vehicle is in the assessment state, extend the preset assessment time of the current assessment item according to the collision risk, driving adjustment operation and traffic data, obtain the target assessment time, and detect the driver's first driving performance on the vehicle within the target assessment time, and then evaluate the first assessment result in combination with the target assessment time and the first driving performance. It can flexibly adjust the assessment time of the driving test and training in an emergency situation, thereby improving the adjustment flexibility of the assessment standards of the driving test and training, which is beneficial to giving the driver sufficient time to complete the assessment while improving the driver's emergency response ability and ensuring driving safety, which is beneficial to improving the assessment accuracy and comprehensiveness of the assessment results.

[0160] In this optional embodiment, optionally, generating at least one guidance form of driving adjustment guidance regarding collision risk may include the following operations:

[0161] When the above-mentioned collision risk is a collision risk on the current lane where the vehicle is located (such as emergency braking), it is determined whether the risk level corresponding to the adjacent lane is lower than the risk level of the current lane; when it is determined that the risk level corresponding to the adjacent lane is lower than the risk level of the current lane, a vehicle lane change / lane merging suggestion is generated, and at least one form of driving adjustment guidance on the collision risk is generated according to the vehicle lane change / lane merging suggestion; or,

[0162] Detect the traffic sign of the current lane and the lane type of the current lane, and evaluate the feasibility of the vehicle's U-turn based on the traffic sign and the lane type, based on map data and traffic rules; when the feasibility of the vehicle's U-turn is greater than or equal to the preset feasibility, generate a vehicle U-turn suggestion, and generate at least one form of driving adjustment guidance regarding collision risk based on the vehicle U-turn suggestion.

[0163] Among them, when the lane is a U-turn lane, the feasibility of vehicle U-turn is higher.

[0164] Optionally, the driving adjustment guide can be used to guide the driver to perform emergency operations such as braking and deceleration, which is not limited in the embodiment of the present invention.

[0165] It can be seen that this optional embodiment can also suggest the driver to change lanes / merge when it is judged that the risk situation of the adjacent lane is better than that of the current lane if the collision risk is the collision risk of the current lane; or, by detecting the traffic signs and lane type of the current lane, the feasibility of the vehicle turning around is evaluated. If the feasibility is high, the driver is suggested to turn around, which can improve the accuracy of generating driving adjustment guidelines and improve the degree of matching between driving adjustment guidelines and actual driving conditions, which is conducive to improving the accuracy of risk handling.

[0166] In this optional embodiment, optionally, according to the collision risk, the driving adjustment operation and the traffic data, extending the preset assessment time of the vehicle for the current assessment item to obtain the target assessment time may include the following operations:

[0167] Assess the risk level of collision risk and determine the risk level coefficient corresponding to the risk level;

[0168] According to the traffic data, the road condition complexity level corresponding to the target monitoring lane is evaluated, and the road condition complexity coefficient corresponding to the road condition complexity level is determined;

[0169] Evaluate the driver's emergency response coefficient based on the driver's response time to driving adjustment operations;

[0170] Detecting the driving intervention situation corresponding to the assisted driving function and determining the driving intervention coefficient corresponding to the driving intervention situation;

[0171] Based on the determined extension formula, the target assessment duration is determined according to the risk level coefficient, road condition complexity coefficient, emergency response coefficient, driving intervention coefficient and the preset assessment duration of the current assessment item.

[0172] Optionally, the above extension formula may be as follows:

[0173] Target assessment duration = preset assessment duration + (risk level coefficient * road condition complexity coefficient + student reaction time coefficient + ADAS intervention degree coefficient) * adjustment factor;

[0174] Among them, the student reaction time in the formula is the above-mentioned emergency response coefficient, and the ADAS intervention degree coefficient is the above-mentioned driving intervention coefficient; further, the adjustment factor in the formula can be determined by iterative optimization, or can be determined according to the driver's driving experience and / or driving environment conditions, which is not limited in the embodiments of the present invention.

[0175] Among them, the risk level may include one of a low risk level, a medium risk level, and a high risk level. For example, the higher the risk level, the longer the required extension time, that is, the higher the risk level coefficient; the higher the road condition complexity level, the more complex the road condition, and the longer the time required for the driver to deal with the emergency, that is, the higher the road condition complexity coefficient; the longer the above-mentioned reaction time, the weaker the driver's ability to deal with emergencies, so the longer the time can be extended to give the driver more opportunities, that is, the higher the emergency response coefficient; the higher the degree of intervention of the assisted driving function, and the fewer emergency measures taken by the driver, the more extended time is needed to evaluate the driver's emergency handling ability in an emergency, that is, the higher the driving intervention coefficient. For example, if the vehicle does not use the assisted driving function, the driving intervention coefficient can be 0, which is not limited in the embodiments of the present invention.

[0176] It can be seen that this optional embodiment can also determine the target assessment time by evaluating the risk level coefficient corresponding to the risk level of the collision risk, the road condition complexity coefficient corresponding to the target monitoring lane, the emergency response coefficient corresponding to the driver, and the driving intervention coefficient corresponding to the assisted driving function, and based on the extension formula and the preset assessment time of the current assessment item, it can improve the comprehensiveness of the analysis of the driving conditions and driving conditions, thereby improving the accuracy of extending the assessment time of the current assessment item, which is conducive to improving the accuracy of determining the target assessment time.

[0177] In this optional embodiment, optionally, based on the determined extension formula, according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment duration of the current assessment item, determining the target assessment duration may include the following operations:

[0178] Based on the determined extension formula, the extended assessment time corresponding to the current assessment item is calculated according to the risk level coefficient, road condition complexity coefficient, emergency response coefficient, driving intervention coefficient and the preset assessment time of the current assessment item;

[0179] Determine whether the extended assessment duration is less than or equal to the preset maximum duration threshold;

[0180] When it is determined that the extended assessment duration is less than or equal to the maximum duration threshold, the extended assessment duration is determined as the target assessment duration;

[0181] When it is determined that the extended assessment duration is greater than the maximum duration threshold, the maximum duration threshold is determined as the target assessment duration.

[0182] It can be seen that this optional embodiment can also calculate the extended assessment time corresponding to the current assessment item based on the extension formula. If the extended assessment time is less than or equal to the maximum time threshold, the extended assessment time will be determined as the target assessment time. Otherwise, the maximum time threshold will be determined as the target assessment time. This can further improve the accuracy of determining the target assessment time, and setting a maximum time threshold for the assessment time can improve the reliability of adjusting the assessment time.

[0183] In yet another optional embodiment, when the risk judgment result is used to indicate that the vehicle does not have a collision risk, the method may further include the following operations:

[0184] Detecting the driver's second driving performance on the vehicle within the preset assessment time of the current assessment item;

[0185] Evaluate the driver's second assessment result on the current assessment item based on the preset assessment duration and the second driving performance.

[0186] It can be seen that this optional embodiment can also evaluate the second assessment result directly according to the second driving performance within the original preset assessment time when there is no risk of collision of the vehicle, which can improve the flexibility of the assessment and the flexibility of the assessment results.

[0187] In the embodiment of the present invention, illustratively, Figure 3 is a schematic diagram of a scenario to which a dynamic determination method for vehicle collision risk disclosed in an embodiment of the present invention is applicable, wherein: Figure 3 (A) is the scene of vehicle merging / changing lanes. Figure 3 (B) is a vehicle turning scenario, which is not limited in the present embodiment. It should be noted that: Figure 3 The scene diagram shown is only for showing one scene applicable to a method for dynamic determination of vehicle collision risk, and is not used to limit other scenes applicable to the method and device for dynamic determination of vehicle collision risk, and Figure 1 The scene schematic diagram shown does not limit the specific road conditions, vehicle conditions, etc. in the scene.

[0188] Embodiment 3

[0189] See also Figure 4 , Figure 4 1 is a schematic diagram of a structure of a dynamic identification device for vehicle collision risk disclosed in an embodiment of the present invention. Figure 4The described dynamic identification device for vehicle collision risk may include one of a dynamic identification device, a dynamic identification terminal, a dynamic identification system and a server, wherein the server includes a local server or a cloud server, which is not limited in the embodiment of the present invention; the device may be applied to a vehicle or a control system capable of controlling the driving of a vehicle, and optionally, the vehicle may be a driving training vehicle or a driving test vehicle, or other vehicles, which is not limited in the embodiment of the present invention. Figure 4 As shown, the dynamic determination device of the vehicle collision risk may include:

[0190] A determination module 301 is used to determine a target driving scene corresponding to the vehicle;

[0191] The determination module 301 is further used to determine the target monitoring lane according to the target driving scene based on the positioning technology and the pre-acquired map data;

[0192] The acquisition module 302 is used to acquire the traffic data corresponding to the target monitoring lane and the real-time driving data of the vehicle; the traffic data includes the lane road condition data and / or the motion data of the adjacent objects;

[0193] The judgment module 303 is used to judge whether the vehicle has a collision risk based on the traffic data and the real-time driving data, and obtain a risk judgment result.

[0194] It can be seen that the device described in the embodiment of the present invention can determine the target monitoring lane according to the target driving scene corresponding to the determined vehicle and based on positioning technology and map data, and then obtain the traffic data of the target monitoring lane and the real-time driving data of the vehicle, so as to judge whether the vehicle has a collision risk based on the traffic data and the real-time driving data, and can realize comprehensive and accurate monitoring of the vehicle's driving status, so as to be able to judge whether there is a collision risk in real time based on road conditions and vehicle driving data, improve the timeliness and accuracy of the judgment of vehicle collision risk, facilitate timely discovery of potential collision risks and subsequent timely risk response measures, and thus facilitate improving driving safety.

[0195] In an optional embodiment, the specific manner in which the determination module 301 determines the target monitoring lane according to the target driving scene, based on the positioning technology and pre-acquired map data may include:

[0196] When the target driving scenario includes a driving test and training scenario, analyzing the test and training item currently being assessed in the driving test and training scenario; determining a first target lane corresponding to the test and training item based on the positioning technology and pre-acquired map data according to the test and training item; the first target lane includes at least one lane that the vehicle needs to pass through / need to enter in the test and training item;

[0197] When the target driving scenario includes a traffic environment scenario, determining a risk factor type corresponding to the traffic environment scenario; determining a second target lane based on the risk factor type and positioning technology and map data; the second target lane includes at least one adjacent lane corresponding to the vehicle;

[0198] The current lane and the target lane where the vehicle is located are determined as the target monitoring lanes corresponding to the vehicle; the target lanes include the first target lane and / or the second target lane.

[0199] It can be seen that the device described in the implementation of this optional embodiment can determine the first target lane corresponding to the test and training item according to the currently assessed test and training item when the target driving scenario includes a driving test and training scenario; and when the target driving scenario includes a traffic environment scenario, determine the second target lane according to the risk factor type corresponding to the traffic environment scenario, and determine the current lane and target lane where the vehicle is located as the target monitoring lanes corresponding to the vehicle, which can improve the analysis accuracy and analysis flexibility of the target driving scenario, is conducive to improving the determination flexibility and determination accuracy of the target lane, and further is conducive to improving the determination accuracy of the target monitoring lane.

[0200] In this optional embodiment, the judgment module 303 may optionally judge whether the vehicle has a collision risk based on the traffic data and the real-time driving data. The specific method of obtaining the risk judgment result may include:

[0201] Calculate the traffic flow parameters corresponding to the target monitoring lane according to the traffic data and the real-time driving data; the traffic flow parameters include one or more combinations of average vehicle speed, vehicle flow density, traffic flow and time index within the target area of ​​the target monitoring lane;

[0202] According to traffic data and real-time driving data, based on a predetermined traffic flow analysis model, the risk parameters corresponding to the vehicle are calculated;

[0203] Based on the determined collision risk assessment algorithm, according to the traffic flow parameters and the risk parameters, it is determined whether there is any neighboring object whose distance to the vehicle is less than or equal to a preset distance within a first preset time period after the current moment;

[0204] When it is determined that the distance between any neighboring object and the vehicle within the first preset time period is less than or equal to the preset distance, determining that the vehicle is at risk of collision;

[0205] When it is determined that there is no adjacent object whose distance to the vehicle is less than or equal to the preset distance within the first preset time period, it is determined that there is no collision risk for the vehicle.

[0206] It can be seen that the device described in the implementation of this optional embodiment can also first calculate the traffic flow parameters corresponding to the target monitoring lane and the risk parameters corresponding to the vehicle based on the traffic data and real-time driving data, and then based on the collision risk assessment algorithm, according to the traffic flow parameters and the risk parameters, determine whether there is any neighboring object whose distance from the vehicle is less than or equal to the preset distance within the first preset time period after the current moment. If the judgment result is yes, it is determined that the vehicle is at risk of collision, otherwise it is determined that the vehicle is not at risk of collision. This can improve the analysis flexibility and accuracy of traffic data and real-time driving data, thereby helping to improve the accuracy of determining traffic flow parameters and risk parameters, and further help to improve the accuracy of judging whether the distance between the neighboring object and the vehicle is within the preset range, thereby improving the accuracy and reliability of the risk judgment results.

[0207] In an optional embodiment, if Figure 5 As shown, the device may also include:

[0208] A generating module 304 is used to generate at least one driving adjustment guide in the form of guidance about the collision risk when the risk judgment result indicates that the vehicle has a collision risk; the driving adjustment guide is used to prompt the driver to adjust the driving operation for the vehicle;

[0209] The judgment module 303 is further used to judge whether it is detected that the driver performs the driving adjustment operation corresponding to the driving adjustment instruction within the second preset time period and whether the matching degree between the driving adjustment operation and the driving adjustment instruction is higher than or equal to the preset matching degree;

[0210] The control module 305 is used to control the vehicle to execute the assisted driving operation corresponding to the driving adjustment instructions based on the assisted driving function corresponding to the vehicle when it is determined that the driver is not detected to execute the driving adjustment operation corresponding to the driving adjustment instructions within a second preset time period or the matching degree between the driving adjustment operation and the driving adjustment instructions is lower than the preset matching degree.

[0211] It can be seen that the device described in the implementation of this optional embodiment can generate driving adjustment instructions when the vehicle is at risk of collision, and determine whether the driver performs the corresponding driving adjustment operations within a preset time and whether the operations are performed in accordance with the driving adjustment instructions. If the judgment result is no, based on the assisted driving function, the vehicle is controlled to perform assisted driving operations, which can improve the accuracy of driving instructions for the driver when there is a risk of collision, and improve the timeliness of the use of the assisted driving function and the accuracy of vehicle control when the driver fails to respond in time or fails to operate correctly, which is beneficial to improving the vehicle's risk response capabilities, and thus is beneficial to improving driving safety.

[0212] In this optional embodiment, optionally, as Figure 5As shown, the device may also include:

[0213] The duration extension module 306 is used to extend the preset assessment duration of the vehicle for the current assessment item according to the collision risk, the driving adjustment operation and the traffic data to obtain the target assessment duration when the risk judgment result indicates that the vehicle has a collision risk and when the target driving scenario includes a driving test and training scenario and the vehicle is in an assessment state;

[0214] A detection module 307, used to detect a first driving performance of the driver on the vehicle within a target assessment time;

[0215] The evaluation module 308 is used to evaluate the first evaluation result of the driver on the current evaluation item according to the target evaluation time and the first driving performance.

[0216] It can be seen that the device described in the implementation of this optional embodiment can also extend the preset assessment time of the current assessment item when the vehicle is in the assessment state, according to the collision risk, driving adjustment operation and traffic data, to obtain the target assessment time, and detect the driver's first driving performance on the vehicle within the target assessment time, and then evaluate the first assessment result in combination with the target assessment time and the first driving performance, so as to flexibly adjust the assessment time of the driving test and training in an emergency situation, thereby improving the adjustment flexibility of the assessment standards of the driving test and training, which is beneficial to give the driver sufficient time to complete the assessment while improving the driver's emergency response ability and ensuring driving safety, which is beneficial to improve the assessment accuracy and comprehensiveness of the assessment results.

[0217] In this optional embodiment, the duration extension module 306 may optionally extend the preset assessment duration of the vehicle for the current assessment item according to the collision risk, the driving adjustment operation and the traffic data. The specific method of obtaining the target assessment duration may include:

[0218] Assess the risk level of collision risk and determine the risk level coefficient corresponding to the risk level;

[0219] According to the traffic data, the road condition complexity level corresponding to the target monitoring lane is evaluated, and the road condition complexity coefficient corresponding to the road condition complexity level is determined;

[0220] Evaluate the driver's emergency response coefficient based on the driver's response time to driving adjustment operations;

[0221] Detecting the driving intervention situation corresponding to the assisted driving function and determining the driving intervention coefficient corresponding to the driving intervention situation;

[0222] Based on the determined extension formula, the target assessment duration is determined according to the risk level coefficient, road condition complexity coefficient, emergency response coefficient, driving intervention coefficient and the preset assessment duration of the current assessment item.

[0223] It can be seen that the device described in the implementation of this optional embodiment can also determine the target assessment time by evaluating the risk level coefficient corresponding to the risk level of the collision risk, the road condition complexity coefficient corresponding to the target monitoring lane, the emergency response coefficient corresponding to the driver, and the driving intervention coefficient corresponding to the assisted driving function, based on the extension formula and the preset assessment time of the current assessment item. This can improve the comprehensiveness of the analysis of the driving conditions and driving conditions, thereby improving the accuracy of extending the assessment time of the current assessment item, which is conducive to improving the accuracy of determining the target assessment time.

[0224] In this optional embodiment, the duration extension module 306 may optionally determine the target assessment duration based on the determined extension formula, according to the risk level coefficient, the road complexity coefficient, the emergency response coefficient, the driving intervention coefficient, and the preset assessment duration of the current assessment item. The specific method may include:

[0225] Based on the determined extension formula, the extended assessment time corresponding to the current assessment item is calculated according to the risk level coefficient, road condition complexity coefficient, emergency response coefficient, driving intervention coefficient and the preset assessment time of the current assessment item;

[0226] Determine whether the extended assessment duration is less than or equal to the preset maximum duration threshold;

[0227] When it is determined that the extended assessment duration is less than or equal to the maximum duration threshold, the extended assessment duration is determined as the target assessment duration;

[0228] When it is determined that the extended assessment duration is greater than the maximum duration threshold, the maximum duration threshold is determined as the target assessment duration.

[0229] It can be seen that the device described in the implementation of this optional embodiment can also calculate the extended assessment time corresponding to the current assessment item based on the extension formula. If the extended assessment time is less than or equal to the maximum time threshold, the extended assessment time will be determined as the target assessment time. Otherwise, the maximum time threshold will be determined as the target assessment time. This can further improve the accuracy of determining the target assessment time, and setting the maximum time threshold for the assessment time can improve the reliability of adjusting the assessment time.

[0230] Embodiment 4

[0231] See also Figure 6 , Figure 6 FIG. 1 is a schematic diagram of the structure of another dynamic identification device for vehicle collision risk disclosed in an embodiment of the present invention. Figure 6 As shown, the dynamic determination device of the vehicle collision risk may include:

[0232] A memory 401 storing executable program codes;

[0233] a processor 402 coupled to the memory 401;

[0234] The processor 402 calls the executable program code stored in the memory 401 to execute part or all of the steps in the method for dynamically determining the vehicle collision risk described in the first embodiment of the present invention or the second embodiment of the present invention.

[0235] Embodiment 5

[0236] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the dynamic determination method of vehicle collision risk described in Embodiment 1 or Embodiment 2 of the present invention.

[0237] Embodiment 6

[0238] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute part or all of the steps in the dynamic determination method of vehicle collision risk described in Example 1 or Example 2.

[0239] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0240] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0241] Finally, it should be noted that the method and device for dynamically distinguishing vehicle collision risks disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A dynamic determination method for vehicle collision risk, characterized in that: The method comprises: Determine the target driving scenario corresponding to the vehicle; According to the target driving scenario, based on positioning technology and pre-acquired map data, determine the target monitoring lane; Acquire traffic data corresponding to the target monitoring lane and real-time driving data of the vehicle; the traffic data includes lane road condition data and / or motion data of adjacent objects; Based on the traffic data and the real-time driving data, it is determined whether the vehicle has a collision risk, and a risk determination result is obtained.

2. The method for dynamic determination of vehicle collision risk according to claim 1, characterized in that: Determining the target monitoring lane according to the target driving scenario based on positioning technology and pre-acquired map data includes: When the target driving scenario includes a driving test and training scenario, analyzing the test and training item currently being assessed in the driving test and training scenario; determining a first target lane corresponding to the test and training item based on the positioning technology and pre-acquired map data according to the test and training item; the first target lane includes at least one lane that the vehicle needs to pass through / enter in the test and training item; When the target driving scenario includes a traffic environment scenario, determining a risk factor type corresponding to the traffic environment scenario; determining a second target lane according to the risk factor type based on the positioning technology and the map data; the second target lane includes at least one adjacent lane corresponding to the vehicle; The current lane and the target lane where the vehicle is located are determined as the target monitoring lane corresponding to the vehicle; the target lane includes the first target lane and / or the second target lane.

3. The method for dynamically determining vehicle collision risk according to claim 1, characterized in that: The determining, based on the traffic data and the real-time driving data, whether the vehicle has a collision risk and obtaining a risk determination result includes: Calculate the traffic flow parameters corresponding to the target monitoring lane according to the traffic data and the real-time driving data; the traffic flow parameters include a combination of one or more of the average vehicle speed, vehicle flow density, traffic flow and time index within the target area of ​​the target monitoring lane; Calculating the risk parameter corresponding to the vehicle based on the traffic data and the real-time driving data and a predetermined traffic flow analysis model; Based on the determined collision risk assessment algorithm, judging whether there is any of the neighboring objects whose distance to the vehicle is less than or equal to a preset distance within a first preset time period after the current moment according to the traffic flow parameter and the risk parameter; When it is determined that the distance between any of the neighboring objects and the vehicle within the first preset time period is less than or equal to the preset distance, determining that the vehicle is at risk of collision; When it is determined that there is no adjacent object whose distance to the vehicle is less than or equal to the preset distance within the first preset time period, it is determined that there is no collision risk for the vehicle.

4. The method for dynamically determining vehicle collision risk according to any one of claims 1 to 3, characterized in that: When the risk judgment result is used to indicate that the vehicle has the collision risk, the method further includes: generating at least one driving adjustment guide in the form of guidance regarding the collision risk; the driving adjustment guide is used to prompt the driver to adjust the driving operation for the vehicle; Determining whether the driver is detected to have performed a driving adjustment operation corresponding to the driving adjustment instruction within a second preset time period and whether a matching degree between the driving adjustment operation and the driving adjustment instruction is higher than or equal to a preset matching degree; When it is determined that the driver is not detected performing the driving adjustment operation corresponding to the driving adjustment instructions within the second preset time period or the matching degree between the driving adjustment operation and the driving adjustment instructions is lower than the preset matching degree, based on the assisted driving function corresponding to the vehicle, the vehicle is controlled to perform the assisted driving operation corresponding to the driving adjustment instructions.

5. The method for dynamically determining vehicle collision risk according to claim 4, characterized in that: When the risk judgment result is used to indicate that the vehicle has the collision risk, the method further includes: When the target driving scenario includes a driving test and training scenario and the vehicle is in an assessment state, according to the collision risk, the driving adjustment operation and the traffic data, extending a preset assessment time of the vehicle for a current assessment item to obtain a target assessment time; detecting a first driving performance of the driver on the vehicle within the target assessment time; A first assessment result of the driver on the current assessment item is evaluated based on the target assessment duration and the first driving performance.

6. The method for dynamically determining vehicle collision risk according to claim 5, characterized in that: The extending the preset assessment time of the vehicle for the current assessment item according to the collision risk, the driving adjustment operation and the traffic data to obtain a target assessment time includes: Assessing the risk level of the collision risk and determining a risk level coefficient corresponding to the risk level; According to the traffic data, evaluating the road condition complexity level corresponding to the target monitoring lane, and determining the road condition complexity coefficient corresponding to the road condition complexity level; evaluating an emergency response coefficient of the driver according to the driver's reaction time to the driving adjustment operation; detecting a driving intervention situation corresponding to the driving assistance function, and determining a driving intervention coefficient corresponding to the driving intervention situation; Based on the determined extension formula, the target assessment duration is determined according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment duration of the current assessment item.

7. The method for dynamically determining vehicle collision risk according to claim 6, characterized in that: The determining of the target assessment duration based on the determined extension formula according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment duration of the current assessment item includes: Based on the determined extension formula, the extended assessment time corresponding to the current assessment item is calculated according to the risk level coefficient, the road condition complexity coefficient, the emergency response coefficient, the driving intervention coefficient and the preset assessment time of the current assessment item; Determine whether the extended assessment duration is less than or equal to a preset maximum duration threshold; When it is determined that the extended assessment duration is less than or equal to the maximum duration threshold, the extended assessment duration is determined as the target assessment duration; When it is determined that the extended assessment duration is greater than the maximum duration threshold, the maximum duration threshold is determined as the target assessment duration.

8. A dynamic determination device for vehicle collision risk, characterized in that: The device comprises: A determination module, used to determine a target driving scenario corresponding to the vehicle; The determination module is further used to determine a target monitoring lane according to the target driving scenario based on positioning technology and pre-acquired map data; An acquisition module, used to acquire traffic data corresponding to the target monitoring lane and real-time driving data of the vehicle; the traffic data includes lane road condition data and / or motion data of adjacent objects; The judgment module is used to judge whether the vehicle has a collision risk based on the traffic data and the real-time driving data, and obtain a risk judgment result.

9. A dynamic determination device for vehicle collision risk, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the dynamic determination method of vehicle collision risk as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the dynamic determination method of vehicle collision risk as described in any one of claims 1-7.

Images