Dynamic assessment method and system based on real-time dynamic vehicle risk scenario state

Abstract

The present invention provides a dynamic assessment method and system for vehicle risk scenarios based on real-time dynamics. The method includes the following steps: S1, based on real-time collected road information, detecting the risk scenario in which the vehicle is located, where risk scenarios include a vehicle cutting into the lane from the side, a vehicle ahead braking suddenly, and a vehicle ahead cutting out of the lane; S2, acquiring the vehicle's driving state data; S3, based on the acquired risk scenario, retrieving a characteristic braking model corresponding to the risk scenario, and combining the driving state data and the characteristic braking model to predict the vehicle's collision risk, thereby obtaining a collision risk prediction result; S4, executing a corresponding intelligent strategy based on the collision risk prediction result. This invention helps to improve the intelligence level of intelligent driving assistance and intelligent driving control in vehicle risk scenarios, thereby enhancing the user experience.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving assistance technology, and in particular to a dynamic assessment method and system based on real-time dynamic vehicle risk scenario states. Background Art

[0002] Current L1 and L2 intelligent driving technologies include warning functions for risky scenarios. However, these warning functions typically rely on fixed braking models to provide collision warnings. These models also calculate collision time and distance, thereby enabling collision warnings. However, in real-world scenarios, factors influencing collisions vary. Therefore, relying solely on fixed methods for collision warnings or assessments fails to meet the demands of modern intelligent driving assistance and intelligent control, nor does it satisfy user needs for intelligent driving assistance. Summary of the Invention

[0003] In response to the above problems, the present invention aims to provide a dynamic assessment method and system based on real-time dynamic vehicle risk scenario conditions.

[0004] The purpose of the present invention is achieved by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a dynamic assessment method based on real-time dynamic vehicle risk scenario conditions, comprising the following steps:

[0006] S1 detects risk scenarios based on real-time collected road information, including side vehicles cutting into the lane, vehicles ahead braking suddenly, and vehicles ahead cutting out of the lane.

[0007] S2 obtains the driving status data of the vehicle;

[0008] S3 retrieves the characteristic braking model corresponding to the risk scenario based on the acquired risk scenario, and predicts the collision risk of the vehicle by combining the driving state data and the characteristic braking model to obtain a collision risk prediction result;

[0009] S4 executes corresponding intelligent strategies based on the collision risk prediction results.

[0010] Preferably, step S1 includes:

[0011] S11 acquires and collects road information in front of and to the sides of the vehicle through onboard sensors, wherein the road information includes position information, azimuth information, relative speed information, and relative acceleration information of the vehicle in front or in the direction of the vehicle;

[0012] S12: When a vehicle is detected in front of the vehicle, further obtain the relative position information, azimuth information, relative speed information, and relative acceleration information of the front vehicle A1 and the vehicle; when the distance between the front vehicle and the vehicle is less than a preset first threshold distance, the azimuth angle is within a first standard azimuth angle range, the relative speed is greater than a first threshold speed, and / or the relative acceleration is greater than a first threshold acceleration, the front vehicle is judged to be a risk target vehicle due to sudden braking, and output is output that the vehicle has entered the first risk scenario;

[0013] S13: When a vehicle is detected in front of the vehicle, the relative position information and azimuth information of the front vehicle A1 and the vehicle are further obtained; when the range of the lane covered by the front vehicle is less than the preset second threshold range and the azimuth is within the second standard azimuth range according to the relative position, it is judged that the front vehicle is cutting out of the lane, and the relative position information, azimuth information, relative speed information and relative acceleration information of the vehicle A2 further ahead are further obtained with respect to the vehicle; when the distance between the vehicle A2 further ahead and the vehicle is less than the preset first threshold distance, the azimuth is within the first standard azimuth range, the relative speed is greater than the first threshold speed, and / or the relative acceleration is greater than the first threshold acceleration according to the relative position, it is judged that the vehicle A2 further ahead is a risk target vehicle, and the current entry into the second risk scenario is output;

[0014] S14 When a vehicle is detected on the side of the vehicle, the relative position information, azimuth information, relative speed information and relative acceleration information of the side vehicle B1 and the vehicle are further obtained; when the distance between the front vehicle and the vehicle is less than the preset third threshold distance, the azimuth angle is within the third standard azimuth angle range, and the relative speed is greater than the third threshold speed, and / or the relative acceleration is greater than the third threshold acceleration, the vehicle in front is judged to be a risk target vehicle that has cut into the lane, and the output is that the current vehicle has entered the third risk scenario.

[0015] Preferably, in step S11, the vehicle-mounted sensors include radar, camera, and lidar; by fusing and processing the data collected by different sensors, feature information corresponding to the vehicle in front or the vehicle on the side is extracted, including vehicle speed, distance, relative speed, and acceleration.

[0016] Preferably, step S2 includes:

[0017] S21 obtains the current driving state data of the vehicle, wherein the driving state data includes the vehicle speed V c (t), acceleration / deceleration a c (t), maximum deceleration Bs max And standard braking performance improvement time bT.

[0018] 5. The dynamic assessment method based on real-time dynamic vehicle risk scenario state according to claim 4, characterized in that step S3 comprises:

[0019] S31 retrieves a characteristic braking model corresponding to the risk scenario according to the acquired risk scenario, wherein the characteristic braking model is:

[0020]

[0021] Where, Bs n (t) represents the braking deceleration of the vehicle at time t, where T0≤t≤T S , T0 represents the moment when a risk scenario is detected, T S Indicates the time when the vehicle is expected to decelerate to a standstill, Bs0 indicates the deceleration data of the vehicle at time T0, Bs0 = a c (T0), rT n represents the standard reaction time corresponding to the current n-th risk scenario, RF represents the reaction force factor, and Bs max Indicates the maximum deceleration of the vehicle, bbT n Indicates the standard braking performance improvement time corresponding to the current n-th risk scenario;

[0022] S32 detects the current vehicle speed V at the time when the risk scenario occurs c (T0), combined with the corresponding characteristic braking model, the collision risk prediction between the vehicle and the target risk vehicle is performed, including: calculating the current collision characteristic value Cru(t), where the calculation function of the collision characteristic value is:

[0023]

[0024] Where Cru(t) represents the collision characteristic, dis AB (T0) represents the relative distance between the vehicle and the risk target vehicle when the risk scene is detected, dis y Indicates the preset reserved safety distance, ΔV ABc (T0) represents the relative speed between the host vehicle and the risk target vehicle when the risk scenario is detected; Δa ABc (T0) represents the relative acceleration between the host vehicle and the risk target vehicle when the risk scenario is detected; T S Indicates the estimated time of deceleration to a standstill;

[0025] When the collision characteristic value Cru(t) is less than the second standard distance disT2, the output risk prediction result is a level 2 collision risk;

[0026] When the collision characteristic value Cru(t) is less than the first standard distance disT1, the output risk prediction result is a level 1 collision risk;

[0027] When the collision characteristic value Cru(t) is not less than the second standard distance disT2, the risk prediction result is output as no risk.

[0028] Preferably, step S4 includes:

[0029] When the risk prediction result is a level 2 collision risk, a collision warning message is issued;

[0030] When the risk prediction result is a level one collision risk, an emergency braking command is initiated.

[0031] In the second aspect, the present invention shows a dynamic assessment system based on real-time dynamic vehicle risk scenario state, including a road information acquisition module, a driving information acquisition module, an analysis and processing module and a strategy control module; wherein,

[0032] The road information acquisition module is used to detect risk scenarios of the vehicle based on real-time collected road information, where risk scenarios include a vehicle cutting into the lane, a vehicle in front suddenly braking, and a vehicle in front cutting out of the lane;

[0033] The driving information acquisition module is used to obtain the driving status data of the vehicle;

[0034] The analysis and processing module is used to retrieve the characteristic braking model corresponding to the risk scenario based on the acquired risk scenario, and predict the collision risk of the vehicle by combining the driving state data and the characteristic braking model to obtain the collision risk prediction result;

[0035] The strategy control module is used to execute corresponding intelligent strategies based on the collision risk prediction results.

[0036] The beneficial effects of the present invention are as follows: a dynamic assessment method and system based on real-time dynamic vehicle risk scenario status is proposed, which first collects road information during vehicle driving and detects the risk scenario of the current vehicle based on the road information; combined with the vehicle's own driving status data, when a risk scenario is detected, the corresponding characteristic braking model is adaptively called according to the risk scenario, and collision risk analysis is performed for the risk scenario based on the vehicle driving status data and the characteristic braking model. By using a targeted characteristic braking model based on the risk scenario as the basis for collision analysis, the pertinence and adaptability of the collision analysis results can be improved, the analysis effect can be improved, and the intelligence level of the vehicle's intelligent driving assistance and intelligent driving control in the risk scenario state can also be improved, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0038] Figure 1 This is a flow chart of a method for dynamic assessment of vehicle risk scenarios based on real-time dynamics according to an embodiment of the present invention;

[0039] Figure 2 This is a schematic diagram of an example of road information of the present invention;

[0040] Figure 3 for Figure 1 Schematic diagram of the process of step S1 shown in the embodiment;

[0041] Figure 4 for Figure 1 A schematic flow chart of step S3 shown in the embodiment. DETAILED DESCRIPTION

[0042] The present invention is further described in conjunction with the following application scenarios.

[0043] See also Figure 1 , which shows a dynamic assessment method based on real-time dynamic vehicle risk scenario state, including the following steps:

[0044] S1 detects risk scenarios based on real-time collected road information, including side vehicles cutting into the lane, vehicles ahead braking suddenly, and vehicles ahead cutting out of the lane.

[0045] S2 obtains the driving status data of the vehicle;

[0046] S3 retrieves the characteristic braking model corresponding to the risk scenario based on the acquired risk scenario, and predicts the collision risk of the vehicle by combining the driving state data and the characteristic braking model to obtain a collision risk prediction result;

[0047] S4 executes corresponding intelligent strategies based on the collision risk prediction results.

[0048] The above-mentioned embodiment of the present invention proposes a dynamic assessment method for vehicle risk scenarios based on real-time dynamics. First, road information is collected during vehicle travel, and based on this road information, the risk scenario currently encountered by the vehicle is detected. Combined with the vehicle's own driving status data, when a risk scenario is detected, the corresponding characteristic braking model is adaptively called based on the risk scenario, and collision risk analysis is performed for the risk scenario based on the vehicle's driving status data and the characteristic braking model. By using a targeted characteristic braking model based on risk scenarios as the basis for collision analysis, the relevance and adaptability of the collision analysis results can be improved, enhancing the analysis effect. This also improves the intelligence level of the vehicle's intelligent driving assistance and intelligent driving control in risk scenarios, thereby enhancing the user experience.

[0049] The method steps described in the above embodiments can be executed on an onboard intelligent control terminal or a cloud server. By connecting to an onboard information acquisition system, relevant data collected by onboard sensors or the vehicle itself can be acquired. Dynamic analysis and evaluation can be performed based on the acquired data, and appropriate feedback can be provided when a collision risk is identified. This is applicable to most L1 or L2 intelligent driving models.

[0050] Preferably, the intelligent strategy includes emergency braking or risk reminder.

[0051] Among them, as attached Figure 2 As shown, the front vehicle referred to in the present invention is a vehicle in the front area of ​​the same lane as the vehicle, and the side vehicle is a vehicle in the side or side front area of ​​the lanes adjacent to the left and right of the vehicle.

[0052] Preferably, see Figure 3 , step S1 includes:

[0053] S11 acquires and collects road information in front of and to the sides of the vehicle through onboard sensors, wherein the road information includes position information, azimuth information, relative speed information, and relative acceleration information of the vehicle in front or in the direction of the vehicle;

[0054] S12 When a vehicle is detected in front of the vehicle, further obtain the relative position information, azimuth information, relative speed information and relative acceleration information of the front vehicle A1 and the vehicle; when the distance dis between the front vehicle and the vehicle is obtained based on the relative position OA1 is smaller than the preset first threshold distance disT1 and the azimuth angle θ A1 Within the first standard azimuth angle θT1, and the relative speed ΔV OA1 Greater than the first threshold speed ΔVT1, and / or relative acceleration Δa OA1When the acceleration is greater than the first threshold ΔaT1, the vehicle ahead is judged to be a risk target vehicle due to sudden braking, and the first risk scenario is output;

[0055] S13 When a vehicle is detected in front of the vehicle, further obtain the relative position information and azimuth information of the front vehicle A1 and the vehicle; when the range of the front vehicle covering the vehicle lane is less than the preset second threshold range according to the relative position, and the azimuth angle θ A1 When the vehicle ahead is judged to be cutting out of the lane within the second standard azimuth angle θT2, the relative position information, azimuth information, relative speed information and relative acceleration information of the vehicle ahead A2 and the vehicle ahead are further obtained; when the distance dis between the vehicle ahead and the vehicle ahead is obtained based on the relative position OA2 The distance is less than the preset first threshold distance disT1, the azimuth angle θ2 is within the first standard azimuth angle θT1 range, and the relative speed ΔV OA2 Greater than the first threshold speed ΔVT1, and / or relative acceleration Δa OA When the acceleration is greater than the first threshold ΔaT1, the vehicle ahead is determined to be a risk target vehicle, and the second risk scenario is output;

[0056] S14 When a vehicle is detected on the side of the vehicle, further obtain the relative position information, azimuth information, relative speed information and relative acceleration information of the side vehicle B1 and the vehicle; when the distance dis between the front vehicle and the vehicle is obtained based on the relative position OB1 is smaller than the preset third threshold distance disT3, azimuth angle θ B1 Within the third standard azimuth angle θT3, and the relative speed ΔV OB1 Greater than the third threshold speed ΔVT3, and / or relative acceleration Δa OB1 When the acceleration is greater than the third threshold acceleration ΔaT3, it is determined that the vehicle ahead is a risk target vehicle that has cut into the lane, and the output indicates that the vehicle has entered the third risk scenario.

[0057] In an exemplary implementation scenario, the settings of the first threshold distance disT1, the first standard azimuth angle θT1, the first threshold speed ΔVT1, the first threshold acceleration ΔaT1, the second standard azimuth angle θT2, the third threshold distance disT3, the third standard azimuth angle θT3, the third threshold speed ΔVT3, and the third threshold acceleration ΔaT3 can all be set according to experience or historical data. For example, disT1∈[5,30] / m, θT1:[1,10]~[10,15] / °, ΔVT1∈[5,10] / (km / h), ΔaT1∈[3,5] / (m / s 2), θT2: [15,20]~[20,25] / °, disT3∈[2,20] / m, θT3: [15,20]~[20,25] / °, ΔVT3∈[5,10] / (km / h), ΔaT3∈[3,5] / (m / s 2 ).

[0058] The above-described embodiment of the present invention collects status data of vehicles ahead and to the side of the vehicle's lane and adjacent lanes during its travel. This data is then compared with corresponding thresholds based on the driving status data of surrounding vehicles to detect the risk scenario the vehicle is in. This risk scenario detection serves as a judgment condition to initiate subsequent collision risk analysis. Furthermore, the identification of risk scenarios provides a basis for the characteristic braking model used in subsequent collision risk analysis, thereby improving the intelligence level of dynamic collision risk prediction.

[0059] Among them, considering that the driver's attention or vigilance is different in different risk scenarios (for example, the vehicle in front brakes suddenly, or a vehicle suddenly cuts in from the adjacent lane, etc.), therefore, the conditions that ultimately cause a collision are also different for different risk scenarios. The above-mentioned embodiment of the present invention performs corresponding collision risk analysis according to different risk scenarios, which can help improve the accuracy and reliability of collision risk prediction.

[0060] In an exemplary implementation scenario, the relative speed can be decomposed based on the lateral speed and longitudinal speed, and compared with corresponding thresholds based on the relative lateral speed and relative longitudinal speed, respectively, as a judgment condition for the risk scenario; similarly, the relative acceleration can also be decomposed based on the lateral acceleration and longitudinal acceleration, and compared with corresponding thresholds based on the relative lateral acceleration and relative longitudinal acceleration, respectively, as a judgment condition for the risk scenario; the above-mentioned longitudinal direction represents the direction along the lane, and the lateral direction represents the tangent direction along the lane.

[0061] Optionally, the on-board sensors include radars, cameras, lidars, etc.; by fusing and performing feature extraction on the data collected by different sensors, it is possible to accurately extract feature information corresponding to the vehicle in front or on the side, such as vehicle speed, distance, relative speed, acceleration, etc.

[0062] Preferably, step S2 includes:

[0063] S21 obtains the current driving state data of the vehicle, wherein the driving state data includes the vehicle speed V c (t), acceleration / deceleration a c (t), maximum deceleration Bsmax And standard braking performance improvement time bT.

[0064] In an exemplary scenario, the standard braking performance improvement time is measured based on vehicle test data or historical braking data, and can be a preset standard value or an empirical value.

[0065] The acceleration / deceleration data can be obtained based on the throttle / brake opening slope of the current vehicle, and the maximum deceleration is obtained based on the performance parameters or test data of the vehicle.

[0066] Preferably, see Figure 4 , step S3 includes:

[0067] S31 retrieves a characteristic braking model corresponding to the risk scenario according to the acquired risk scenario, wherein the characteristic braking model is:

[0068] Where, Bs n (t) represents the braking deceleration of the vehicle at time t, where T0≤t≤T S , T0 represents the moment when a risk scenario is detected, T S Indicates the time when the vehicle is expected to decelerate to a standstill, Bs0 indicates the deceleration data of the vehicle at time T0, Bs0 = a c (T0), rT n represents the standard reaction time corresponding to the current n-th risk scenario, RF represents the reaction force factor, and Bs max Indicates the maximum deceleration of the vehicle, bT n Indicates the standard braking performance improvement time corresponding to the current n-th risk scenario;

[0069] S32 detects the current vehicle speed V at the time when the risk scenario occurs c (T0), combined with the corresponding characteristic braking model, the collision risk prediction between the vehicle and the target risk vehicle is performed, including: calculating the current collision characteristic value Cru(t), where the calculation function of the collision characteristic value is:

[0070]

[0071] Where Cru(t) represents the collision characteristic, dis AB (T0) represents the relative distance between the vehicle and the risk target vehicle when the risk scene is detected, dis y Indicates the preset reserved safety distance, ΔV ABc (T0) represents the relative speed between the host vehicle and the risk target vehicle when the risk scenario is detected; Δa ABc (T0) represents the relative acceleration between the host vehicle and the risk target vehicle when the risk scenario is detected; TS Indicates the estimated time of deceleration to a standstill;

[0072] When the collision characteristic value Cru(t) is less than the second standard distance disT2, the output risk prediction result is a level 2 collision risk;

[0073] When the collision characteristic value Cru(t) is less than the first standard distance disT1, the output risk prediction result is a level 1 collision risk;

[0074] When the collision characteristic value Cru(t) is not less than the second standard distance disT2, the risk prediction result is output as no risk.

[0075] In an exemplary scenario, the characteristic braking model called for different risk scenarios has a standard reaction time rT n , Standard braking performance improvement time bT n The settings are different. Based on simulation tests and reality tests, it can be concluded that for the first risk scenario of sudden braking in front, the standard reaction time rT1=0.6s and the standard braking efficiency improvement time bT1=0.43s are obtained; for the second risk scenario of the vehicle in front cutting out, the standard reaction time rT2=0.58s and the standard braking efficiency improvement time bT2=0.52s are obtained; for the third risk scenario of the side vehicle urgently cutting into the vehicle, the standard reaction time rT3=0.52s and the standard braking efficiency improvement time bT3=0.48s are obtained.

[0076] In the above-mentioned embodiment of the present invention, when a risk scenario is detected, the corresponding characteristic braking model is called according to the risk scenario, wherein the key parameters in the characteristic braking model are set accordingly based on the empirical values ​​or test values ​​obtained in different scenarios. Based on different characteristic braking models, the vehicle collision risk is further analyzed, and the braking distance or braking time of the vehicle can be calculated based on the characteristic braking model, thereby accurately estimating the possible collision risk and improving the accuracy of the collision risk estimation.

[0077] At the same time, further subsequent decisions can be made based on the results of collision risk analysis to further issue risk warning reminders or vehicle emergency braking, which can achieve the intelligent level of intelligent driving assistance or intelligent driving control.

[0078] In an exemplary implementation scenario, the relative speed ΔV between the host vehicle and the risk target vehicle when a risk scenario is detected is ABc(T0) represents the longitudinal relative speed of the two vehicles in the actual calculation process. If the risk target vehicle is in the same lane as the host vehicle, the relative speed does not need to be corrected and the relative speed value measured in step S1 is directly used for calculation. If the risk target vehicle is in a different lane from the host vehicle, the relative speed is corrected, that is, the corrected relative speed ΔV A ′ Bc (T0) = cos(θ) × ΔV ABc (T0), where θ represents the angle between the risk target vehicle and the longitudinal direction, that is, the corrected relative speed ΔV A ′ Bc (T0) is calculated.

[0079] Similarly, the relative acceleration Δa between the vehicle and the risk target vehicle when the risk scene is detected is ABc (T0) During the actual calculation process, the relative acceleration may also be corrected in a similar manner as described above, which will not be repeated in the present invention.

[0080] In an exemplary implementation scenario, the estimated time T for deceleration to a standstill is S Based on the current vehicle speed V c (T0), combined with the braking deceleration Bs corresponding to the characteristic braking model n (t) is deduced, and when the vehicle speed drops to 0, the corresponding time T is obtained. S .

[0081] In an exemplary implementation scenario, in step S32, in addition to the method of predicting the collision risk based on the collision feature quantity proposed in the above embodiment, the collision risk between the vehicle and the target risk vehicle can also be predicted by using a collision prediction model that has been trained in the prior art. Based on the collected parameters and the braking model proposed above, the collision risk between the vehicle and the target risk vehicle can be further analyzed.

[0082] Furthermore, based on the risk scenario-based configuration of different characteristic braking models, it is important to consider that in actual collision risk warning applications, the driver's state cannot be ignored. Therefore, during the decision-making and handling process facing risk scenarios, the driver's driving state will also have a significant impact on the final collision risk. Existing collision risk warning technologies typically make judgments based on a fixed distance value. For example, a distance less than 2 meters is considered a collision risk, or an estimated collision time less than 2 seconds is considered a risk. However, in real-world scenarios, different drivers have different psychological expectations of collision risk and their ability to cope with risk. For example, when a driver is fatigued, their reaction time will decrease, and therefore their reaction time to risk scenarios will also fluctuate. Therefore, using a fixed reaction time in the braking model to estimate the final collision risk will inevitably lead to deviations. Therefore, the characteristic braking model proposed in this invention further incorporates a reaction force factor as an adjustment parameter to further adjust the characteristic braking model based on the driver's current actual driving state, thereby further improving the accuracy and adaptability of the characteristic braking model, thereby improving the reliability of collision risk.

[0083] The larger the reaction force factor is, the lower the driver's reaction force is, and therefore the braking capacity obtained based on the braking model is lower, thereby increasing the sensitivity of the collision risk trigger.

[0084] Preferably, step S3 further includes:

[0085] S30 obtains the real-time reaction force factor RF, including:

[0086] S301 obtains the identity information of the driver of the vehicle and retrieves corresponding driving characteristic data based on the obtained identity information, wherein the driving characteristic data includes a driving style factor Std based on the driver's preset driving style, where Std∈[1,10]. A larger Std indicates a more aggressive driving style set by the driver, and conversely, a larger Std indicates a more conservative driving style set by the driver.

[0087] S302 acquires an eye image of the driver of the vehicle using an infrared camera, and uses an image recognition engine to detect the driver's blinking movements based on the acquired eye image, and calculates the driver's blink frequency PE(t) in the current time period GT1, that is, the number of blinks per minute;

[0088] S303 calculates the current reaction force factor RF based on the vehicle speed data and the driver's blink frequency data in the current time period GT1, wherein the reaction force factor calculation function used is:

[0089]

[0090] Where RF(t) represents the reaction force factor at the current moment, ck represents the preset reaction force adjustment parameter, where ck∈[0.01,1]; ave represents the preset sensitivity factor, where ave∈[0.01,100], ω1 and ω2 represent the preset weight factors, respectively; PE(t) represents the driver's blink frequency in the current time period GT1, and PET represents the standard blink frequency, which is set based on experience. represents the rate of change of vehicle speed at the i-th sampling point in the current time period, where i = 1, 2, …, ni, ni represents the total number of sampling points, mean{·} represents the mean function, sd{·} represents the standard deviation function, and Std represents the preset driving style factor.

[0091] Among them, the setting method of the current time period GT1 can be a time range of a fixed time length from the current moment to the previous moment; it can be a time range of a fixed time length starting from a new time node after a fixed time length, and the current period GT1 represents the latest time range at the specific current moment; or it can be set according to other methods, and the present invention does not make specific limitations here.

[0092] In one exemplary implementation scenario, in step S301, obtaining the driver's identity information can be accomplished by having the driver log in to a corresponding account, or by identifying the driver through facial recognition, fingerprint recognition, or other methods. During initial setup of the driver's account, the driver can select parameters such as a driving style factor for subsequent personalized access.

[0093] The above-mentioned embodiment of the present invention proposes a dynamic acquisition method of the reaction force factor, a key parameter in the characteristic braking model, wherein the driver's actual reaction force state can be reflected based on the current driver's fatigue state (the fatigue state is reflected by the blinking frequency. During normal driving, the higher the driver's blinking frequency, the higher the fatigue level reflected. It can be considered that the driver's reaction force will be reduced in the fatigue state) and operation data (reflected by the vehicle's speed change rate. The more normal the driving state, the smoother the vehicle speed change. In the case of insufficient mental state or insufficient reaction force, sudden braking and other timely vehicle correction operations usually occur, resulting in an increase in the speed change rate). The characteristic braking model is corrected, so that the braking analysis and collision analysis results obtained based on the braking model are more in line with the actual driving scenario, thereby improving the accuracy and adaptability of collision risk analysis, and helping to improve the effect and user experience of intelligent driving assistance and intelligent driving control.

[0094] Preferably, step S4 includes:

[0095] When the risk prediction result is a level 2 collision risk, a collision warning message is issued;

[0096] When the risk prediction result is a level one collision risk, an emergency braking command is initiated.

[0097] By setting the secondary collision risk analysis results, corresponding auxiliary prompts or emergency braking functions can be executed based on the severity of different collision risks to adapt to the use of different application scenarios.

[0098] Based on the above-mentioned dynamic assessment method based on real-time dynamic vehicle risk scenario state, the present invention further proposes a dynamic assessment system based on real-time dynamic vehicle risk scenario state, which is used to perform the above-mentioned Figure 1 The method shown includes: a road information acquisition module, a driving information acquisition module, an analysis and processing module, and a strategy control module; wherein,

[0099] The road information acquisition module is used to detect risk scenarios of the vehicle based on real-time collected road information, where risk scenarios include a vehicle cutting into the lane, a vehicle in front suddenly braking, and a vehicle in front cutting out of the lane;

[0100] The driving information acquisition module is used to obtain the driving status data of the vehicle;

[0101] The analysis and processing module is used to retrieve the characteristic braking model corresponding to the risk scenario based on the acquired risk scenario, and predict the collision risk of the vehicle by combining the driving state data and the characteristic braking model to obtain the collision risk prediction result;

[0102] The strategy control module is used to execute corresponding intelligent strategies based on the collision risk prediction results.

[0103] It should be noted that, in the above implementation, each functional module is also used to perform the above Figure 1 The present invention will not repeat the methods of the corresponding steps shown and the corresponding specific implementation methods of each step here.

[0104] It should be noted that the functional units / modules in the various embodiments of the present invention may be integrated into a single processing unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated into a single unit / module. The aforementioned integrated units / modules may be implemented in the form of hardware or software functional units / modules.

[0105] Through the description of the above embodiments, it will be clear to those skilled in the art that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by instructing the relevant hardware through a computer program. During implementation, the above program can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a computer. Computer-readable media can include, but are not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should analyze that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A dynamic assessment method based on real-time dynamic vehicle risk scenario state, characterized by: The steps include: S1 detects risk scenarios based on real-time collected road information, including side vehicles cutting into the lane, vehicles ahead braking suddenly, and vehicles ahead cutting out of the lane. S2 obtains the driving status data of the vehicle; S3 retrieves the characteristic braking model corresponding to the risk scenario based on the acquired risk scenario, and predicts the collision risk of the vehicle by combining the driving state data and the characteristic braking model to obtain a collision risk prediction result; S4 executes corresponding intelligent strategies based on the collision risk prediction results; Wherein, step S1 includes: S11 acquires and collects road information in front of and to the sides of the vehicle through onboard sensors, wherein the road information includes position information, azimuth information, relative speed information, and relative acceleration information of the vehicle in front or in the direction of the vehicle; S12: When a vehicle is detected in front of the vehicle, further obtain the relative position information, azimuth information, relative speed information, and relative acceleration information of the front vehicle A1 and the vehicle; when the distance between the front vehicle and the vehicle is less than a preset first threshold distance, the azimuth angle is within a first standard azimuth angle range, the relative speed is greater than a first threshold speed, and / or the relative acceleration is greater than a first threshold acceleration, the front vehicle is judged to be a risk target vehicle due to sudden braking, and output is output that the vehicle has entered the first risk scenario; S13: When a vehicle is detected in front of the vehicle, the relative position information and azimuth information of the front vehicle A1 and the vehicle are further obtained; when the range of the lane covered by the front vehicle is less than the preset second threshold range and the azimuth is within the second standard azimuth range according to the relative position, it is judged that the front vehicle is cutting out of the lane, and the relative position information, azimuth information, relative speed information and relative acceleration information of the vehicle A2 further ahead are further obtained with respect to the vehicle; when the distance between the vehicle A2 further ahead and the vehicle is less than the preset first threshold distance, the azimuth is within the first standard azimuth range, the relative speed is greater than the first threshold speed, and / or the relative acceleration is greater than the first threshold acceleration according to the relative position, it is judged that the vehicle A2 further ahead is a risk target vehicle, and the current entry into the second risk scenario is output; S14 When a vehicle is detected on the side of the vehicle, the relative position information, azimuth information, relative speed information and relative acceleration information of the side vehicle B1 and the vehicle are further obtained; when the distance between the front vehicle and the vehicle is less than the preset third threshold distance, the azimuth angle is within the third standard azimuth angle range, and the relative speed is greater than the third threshold speed, and / or the relative acceleration is greater than the third threshold acceleration, the vehicle in front is judged to be a risk target vehicle that has cut into the lane, and the output is that the current vehicle has entered the third risk scenario.

2. The dynamic assessment method based on real-time dynamic vehicle risk scenario state according to claim 1 is characterized in that: In step S11, the vehicle-mounted sensors include radar, camera, and lidar; by fusing and processing the data collected by different sensors, feature information corresponding to the vehicle in front or on the side is extracted, including vehicle speed, distance, relative speed, and acceleration.

3. The dynamic assessment method based on real-time dynamic vehicle risk scenario state according to claim 1 is characterized in that: Step S2 includes: S21 obtains the current driving state data of the vehicle, wherein the driving state data includes the vehicle speed , Acceleration / deceleration , maximum deceleration and standard braking performance improvement time .

4. The dynamic assessment method based on real-time dynamic vehicle risk scenario state according to claim 3 is characterized in that: Step S3 includes: S31 retrieves a characteristic braking model corresponding to the risk scenario according to the acquired risk scenario, wherein the characteristic braking model is: Where, represents the braking deceleration of the vehicle at time t, where , Indicates the moment when a risk scenario is detected. Indicates the estimated time of deceleration to a standstill. express The vehicle's deceleration data at this moment, , Indicates the standard reaction time corresponding to the current n-th risk scenario, and represents the reaction force factor. Indicates the maximum deceleration of the vehicle. Indicates the standard braking performance improvement time corresponding to the current n-th risk scenario; S32 detects the current vehicle speed at the time when the risk scenario occurs , combined with the corresponding characteristic braking model to predict the collision risk between the vehicle and the target risk vehicle, including: calculating the current collision characteristic quantity , where the calculation function of the collision characteristic quantity is: Where, Represents the collision characteristic quantity, Indicates the relative distance between the vehicle and the target vehicle when a risk scenario is detected, indicating the preset reserved safety distance. Indicates the relative speed between the vehicle and the target vehicle when a risk scenario is detected; Indicates the relative acceleration between the host vehicle and the risk target vehicle when a risk scenario is detected; Indicates the estimated time of deceleration to a standstill; When the collision characteristic Less than the second standard distance When , the output risk prediction result is the second-level collision risk; When the collision characteristic Less than the first standard distance When , the output risk prediction result is the first-level collision risk; When the collision characteristic Not less than the second standard distance When , the output risk prediction result is no risk.

5. The dynamic assessment method based on real-time dynamic vehicle risk scenario state according to claim 4 is characterized in that: Step S4 includes: When the risk prediction result is a level 2 collision risk, a collision warning message is issued; When the risk prediction result is a level one collision risk, an emergency braking command is initiated.

6. A dynamic assessment system based on real-time dynamic vehicle risk scenario status, characterized by: It includes a road information acquisition module, a driving information acquisition module, an analysis and processing module, and a strategy control module; wherein, The road information acquisition module is used to detect risk scenarios of the vehicle based on real-time collected road information, where risk scenarios include a vehicle cutting into the lane, a vehicle in front suddenly braking, and a vehicle in front cutting out of the lane; The driving information acquisition module is used to obtain the driving status data of the vehicle; The analysis and processing module is used to retrieve the characteristic braking model corresponding to the risk scenario based on the acquired risk scenario, and predict the collision risk of the vehicle by combining the driving state data and the characteristic braking model to obtain the collision risk prediction result; The strategy control module is used to execute corresponding intelligent strategies based on the collision risk prediction results; Among them, the road information acquisition module includes: The vehicle's sensors collect information about the road ahead and to the side of the vehicle, including the position, azimuth, relative speed, and relative acceleration of the vehicle ahead or to the side. When a vehicle is detected in front of the vehicle, the relative position information, azimuth information, relative speed information, and relative acceleration information of the front vehicle A1 and the vehicle are further obtained; when the distance between the front vehicle and the vehicle is less than a preset first threshold distance, the azimuth angle is within a first standard azimuth angle range, the relative speed is greater than a first threshold speed, and / or the relative acceleration is greater than a first threshold acceleration, the front vehicle is judged to be a risk target vehicle due to sudden braking, and the first risk scenario is outputted; When a vehicle is detected in front of the vehicle, the relative position information and azimuth information of the front vehicle A1 and the vehicle are further obtained; when the range of the lane covered by the front vehicle is less than the preset second threshold range and the azimuth is within the second standard azimuth range according to the relative position, it is judged that the front vehicle is cutting out of the lane, and the relative position information, azimuth information, relative speed information and relative acceleration information of the vehicle A2 further ahead and the vehicle are further obtained; when the distance between the vehicle A2 further ahead and the vehicle is less than the preset first threshold distance, the azimuth is within the first standard azimuth range, the relative speed is greater than the first threshold speed, and / or the relative acceleration is greater than the first threshold acceleration according to the relative position, it is judged that the vehicle A2 further ahead is a risk target vehicle, and the current entry into the second risk scenario is output; When a vehicle is detected on the side of the vehicle, the relative position information, azimuth information, relative speed information and relative acceleration information of the side vehicle B1 and the vehicle are further obtained; when it is obtained based on the relative position that the distance between the front vehicle and the vehicle is less than the preset third threshold distance, the azimuth angle is within the third standard azimuth angle range, and the relative speed is greater than the third threshold speed, and / or the relative acceleration is greater than the third threshold acceleration, it is judged that the front vehicle has cut into the lane and is a risk target vehicle, and the current entry into the third risk scenario is output.

Images