A method, device, equipment and storage medium for controlling vehicle driving behavior

Abstract

The present disclosure provides a method, apparatus, device, and storage medium for controlling vehicle driving behavior, which relate to fields such as autonomous driving, intelligent transportation, and vehicle-road cooperation. The specific implementation solution is as follows: Obtain road emergency information. Use historical road data related to the emergency time information and the emergency location information to determine the cellular data of the emergency section. Use the cellular data to perform road simulation on the emergency section to obtain simulated road simulation data. Based on the simulated road simulation data, control the driving behavior of the first vehicle traveling on the emergency section. Through the cellular data of the emergency section, the present disclosure can accurately simulate the road conditions of the emergency section. So as to make a plan based on the results obtained from the simulation, which can effectively avoid road congestion or secondary accidents and improve the planning effect for the accident section.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to the field of intelligent transportation. Generally, it relates to a method, apparatus, device, and storage medium for controlling vehicle driving behavior. Background Art

[0002] With the development of society, vehicles have gradually become popular in people's lives. When people travel, they often choose to take or drive a car as a means of transportation. Along with the continuous improvement of urban road infrastructure, the number of vehicles traveling on urban roads is also increasing.

[0003] For some highway sections, viaducts, ring roads, streets near residential areas, etc., the traffic flow is often relatively large. When traffic accidents occur on these sections, it usually causes local traffic congestion. If it is during a period with a large traffic flow, it will cause a larger area of road congestion as time goes by. Summary of the Invention

[0004] The present disclosure provides a method, apparatus, device, and storage medium for controlling vehicle driving behavior.

[0005] According to a first aspect of the present disclosure, a method for controlling vehicle driving behavior is provided. The method includes: obtaining road emergency event information. The road emergency event information includes emergency event time information and emergency event location information. Using historical road data related to the emergency event time information and the emergency event location information, determine the cellular data of the emergency event section. The emergency event section includes the location corresponding to the emergency event location information, and the cellular data is used to describe the vehicle driving conditions of the corresponding section. Using the cellular data to perform road simulation on the emergency event section to obtain simulation road simulation data. Based on the simulation road simulation data, control the driving behavior of a first vehicle traveling on the emergency event section. Through the cellular data of the emergency event section, the present disclosure can accurately simulate the road conditions of the emergency event section. So as to plan based on the results obtained from the simulation, effectively avoid road congestion or secondary accidents, and improve the planning effect for the accident section.

[0006] According to a second aspect of the present disclosure, there is provided a device for controlling a vehicle driving behavior, the device comprising: an acquisition module configured to acquire information on road emergencies, the information on road emergencies including emergency time information and emergency location information; a determination module configured to determine cellular data of an emergency section by using historical road data related to the emergency time information and the emergency location information, wherein the emergency section includes the location corresponding to the emergency location information, and the cellular data is used to describe the vehicle driving conditions of the corresponding section; a simulation module configured to perform a road simulation on the emergency section by using the cellular data to obtain simulation road simulation data; and a control module configured to control the driving behavior of a first vehicle traveling on the emergency section based on the simulation road simulation data. The present disclosure can accurately simulate the road conditions of the emergency section through the cellular data of the emergency section. So as to make a plan based on the obtained simulation results, it is possible to effectively avoid road congestion or secondary accidents and improve the planning effect of the accident section.

[0007] According to a third aspect of the present disclosure, there is provided a device for controlling a vehicle driving behavior, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the methods in the first aspect above.

[0008] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute any one of the methods in the first aspect or the second aspect above.

[0009] According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements any one of the methods in the first aspect or the second aspect above.

[0010] A method, a device, a device and a storage medium for controlling a vehicle driving behavior provided by the present disclosure can accurately simulate the road conditions of an emergency section through the cellular data of the emergency section. So as to make a plan based on the obtained simulation results, it is possible to effectively avoid road congestion or secondary accidents and improve the planning effect of the accident section.

[0011] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0013] Figure 1 is a schematic diagram of an application scenario of an embodiment of the present disclosure;

[0014] Figure 2 is a flowchart of a method for controlling vehicle driving behavior according to an embodiment of the present disclosure;

[0015] Figure 3 is a flowchart of another method for controlling vehicle driving behavior according to an embodiment of the present disclosure;

[0016] Figure 4 is a schematic diagram of a vehicle emergency braking according to an embodiment of the present disclosure;

[0017] Figure 5 is a flowchart of a method for determining lane queue length data according to an embodiment of the present disclosure;

[0018] Figure 6 is a flowchart of a method for determining road network saturation data according to an embodiment of the present disclosure;

[0019] Figure 7 is a schematic diagram of a vehicle lane change probability according to an embodiment of the present disclosure;

[0020] Figure 8 is another schematic diagram of a vehicle lane change probability according to an embodiment of the present disclosure;

[0021] Figure 9 is still another schematic diagram of a vehicle lane change probability according to an embodiment of the present disclosure;

[0022] Figure 10 is yet another schematic diagram of a vehicle lane change probability according to an embodiment of the present disclosure;

[0023] Figure 11 is another schematic diagram of a vehicle lane change probability according to an embodiment of the present disclosure;

[0024] Figure 12 is a schematic diagram of a lane change condition according to an embodiment of the present disclosure;

[0025] Figure 13 is still another flowchart of a method for controlling vehicle driving behavior according to an embodiment of the present disclosure;

[0026] Figure 14 is a schematic diagram of a road simulation according to an embodiment of the present disclosure;

[0027] Figure 15 is a schematic diagram of a following rule process according to an embodiment of the present disclosure;

[0028] Figure 16Schematic diagram of a device for controlling vehicle driving behavior according to an embodiment of the present disclosure;

[0029] Figure 17 Schematic diagram of a device for controlling vehicle driving behavior according to an embodiment of the present disclosure. Detailed implementation manners

[0030] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0031] The main application scenarios of the present disclosure can be, for example, scenarios where a vehicle is driving on a road. For example Figure 1 as shown Figure 1 shows a scenario 100, which includes at least one vehicle 101. It can be understood that Figure 1 shows multiple vehicles 101. The vehicle is driving in lane 102. And based on the driver operating the vehicle 101, the vehicle 101 can accelerate, decelerate, move at a constant speed or change the driving lane 102 within lane 102.

[0032] Assume that when scenario 100 is located on a highway section, in the construction and management of intelligent highways, traffic safety is of utmost importance to both traffic managers and travelers. It can be understood that travelers can include the driver operating the vehicle 101 and the passengers sitting in the vehicle 101. Traffic managers can be understood as departments, management personnel or management platforms that maintain, regulate and supervise traffic sections.

[0033] In particular, for emergencies on the road, predicting the traffic operation state and accident impact range at the accident location in the next few minutes or within a certain time period can facilitate traffic managers to timely take appropriate traffic control measures and guidance measures, and divert the congested sections accordingly, thereby effectively reducing the probability of traffic congestion and secondary accidents.

[0034] In some related technologies, intelligent monitoring is carried out for emergencies. For example, accident information is obtained through road monitoring and video recognition, and then information support is provided based on real-time road conditions or video information. The prediction method for road conditions in such solutions is also only a macro traffic flow prediction based on historical data, resulting in deficiencies in prediction accuracy and visualization level.

[0035] It can be seen that the accident data provided by the above method using artificial intelligence (AI) video recognition cannot predict and evaluate the impact range of accidents. The prediction and evaluation using the method of macroscopic traffic flow cannot truly visualize and restore the road conditions, and the prediction accuracy is also insufficient. Moreover, the vehicle information data in the actual intelligent highway is currently recognized through checkpoint and roadside devices, and the accuracy and integrity of the data are far from enough.

[0036] Therefore, the present disclosure provides a method, device, equipment and storage medium for controlling vehicle driving behavior. Through the cellular data of the emergency section, the road conditions of the emergency section can be accurately simulated. So that based on the results obtained from the simulation, planning can be carried out, which can effectively avoid road congestion or secondary accidents and improve the planning effect of the accident section.

[0037] Next, the present disclosure will be elaborated in detail with reference to the accompanying drawings.

[0038] Figure 2 It is a flowchart of a method for controlling vehicle driving behavior according to an embodiment of the present disclosure.

[0039] Based on Figure 1 In the scenario shown, the present disclosure also provides a method for controlling vehicle driving behavior. This method can be applied to a terminal device or a network device. In some examples, the network device can be a server or a server cluster. Of course, in other examples, the terminal device can include, for example, but not limited to, a mobile phone, a wearable device, a tablet computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a laptop, a mobile computer, an augmented reality (AR) device, a virtual reality (VR) device, an artificial intelligence (AI) device, and / or a vehicle-mounted device, etc. Any terminal device or portable terminal device, and the present disclosure does not make a limitation.

[0040] It can be understood that the terminal device and the network device in the present disclosure can be collectively referred to as devices.

[0041] The method involved in the present disclosure may include the following steps:

[0042] S201, obtain road emergency information.

[0043] In some examples, a device can obtain road emergency information. This road emergency information can include emergency time information and emergency location information. It is understood that the emergency time information is used to indicate the time when the emergency occurred, and the emergency time location information can describe the location of the emergency, such as the road section and location.

[0044] It can be understood that the road emergency event information may include any information used to describe a road emergency event.

[0045] S202 : Determine cellular data of the road section where the emergency occurred by using historical road data related to the emergency time information and the emergency location information.

[0046] In some examples, the device can obtain historical road data related to the road emergency event time and location information based on the road emergency event acquired in S201. Cellular data for the road section where the emergency occurred can then be determined based on the acquired historical road data. The road section where the emergency occurred includes the location corresponding to the emergency location information. It will be understood that the road section where the emergency occurred represents the road section where the emergency occurred, and the road section should at least include the location where the emergency occurred. The cellular data can be used to describe vehicle travel conditions on the corresponding road section.

[0047] In some examples, a cell can represent the smallest road unit. For example, the hierarchy of road basic data can be, from largest to smallest, as follows: road → road segment → lane → cell. It is understood that roads have the largest scope; a road can be composed of multiple road segments, each road segment can contain multiple lanes, and each lane can be composed of multiple cells. It is understood that the layer-by-layer division described above can be considered as a road network segmentation process. In some examples, each cell data can contain vehicle driving information within a corresponding length. For example, a cell can be set to a road segment with a length of 0.1 meters (m).

[0048] In some examples, the grey prediction model (GM) (1,1) can be used to predict the cell data of the corresponding road section at any time in the future. For example, a certain road section can be predicted based on historical road data. It is understood that historical road data can be composed of cell historical data at different locations in the historical period. The prediction series X can be constructed using formula 1. (0) .

[0049] X (0) =(x (0) (1), x (0) (2),......,x (0) (n))…Formula 1

[0050] Among them, x(0) (n) represents the nth historical road data, where n is any positive integer. It can be understood that different x (0) (n) can represent historical road data at the same location but at different times.

[0051] For example, for the predicted sequence X (0) The historical road data used can be statistically obtained on a daily basis. For each day, it can be divided into smaller time granularities to obtain historical road data for different time periods of the day. In some examples, the time granularity can be set to 15 minutes (minute, min). Taking the unit of the emergency time information as a day as an example, corresponding labels can be added to the historical road data of different days to distinguish the historical road data corresponding to different days. For example, the labels can be divided into working days, holidays, weekends, etc. Among them, working days can include Monday to Friday. Weekends can include Saturday and Sunday.

[0052] In some examples, when obtaining historical road data, outliers in the historical road data can also be removed. The specific method can be implemented with reference to existing methods, and will not be elaborated in this disclosure.

[0053] In some examples, if the obtained historical road data corresponds to a holiday and the data for the corresponding holiday is less than the preset minimum data volume threshold, the historical road data of the nearest consecutive weekend to the current date can be used for supplementation. It can be understood that in order to ensure the accuracy of the predicted sequence X (0) usually, the number of historical road data to be used will be preset in advance. In some examples, the minimum data volume threshold can be set to 4 pieces. It can be understood that each piece of data can correspond to the historical road data of one day.

[0054] In other examples, assuming that the date to be predicted for the predicted sequence X (0) is the make-up work situation on a weekend, the make-up work on the weekend can be regarded as a kind of working day, and according to the time, the historical road data corresponding to the nearest working day to this weekend make-up work can be selected for prediction.

[0055] For example, if the date to be predicted for the predicted sequence X (0) is Saturday 13:00 - 13:15, then the historical road data of Saturday 13:00 - 13:15 is obtained. If the date to be predicted for the predicted sequence X (0) is Monday 13:00 - 13:15, then the historical road data of Monday 13:00 - 13:15 is obtained. If the date to be predicted for the predicted sequence X (0) is a holiday 13:00 - 13:15, then the historical road data of the corresponding holiday 13:00 - 13:15 is obtained. If the date to be predicted for the predicted sequence X (0)If the date to be predicted is a make-up workday on the weekend from 13:00 to 13:15, then obtain the historical road data for the same time period (13:00 - 13:15) on the historical working day closest to this weekend make-up workday in chronological order.

[0056] In some examples, the predicted sequence X shown in Formula 1 (0) can be cumulatively summed once to obtain a new sequence X (1) , as shown in Formula 2, for example.

[0057] X (1) =(x (1) (1), x (1) (2),......, x (1) (n))... Formula 2

[0058] where x (1) (n) can be calculated by Formula 3.

[0059]

[0060] After that, sequence Z (1) can be generated using X (1) , as shown in Formula 4, for example.

[0061] Z (1) =(z (1) (2), z (1) (3),......, z (1) (n))... Formula 4

[0062] where z (1) (n) can be calculated by Formula 5.

[0063]

[0064] It can be understood that the value of k in Formula 5 takes values 1, 2,..., n - 1.

[0065] After that, matrix Y and matrix B can be constructed. As shown in Formula 6 and Formula 7, for example.

[0066]

[0067]

[0068] Then, based on the two matrices shown in Formula 6 and Formula 7, parameters a and u can be output. For example, it can be obtained through Formula 8.

[0069]

[0070] where B T represents the transpose matrix of B.

[0071] After that, the cumulative value x (1) (k + 1) can be predicted through Equation 9, that is

[0072]

[0073] Finally, the predicted value x (0) (k + 1) can be calculated through Equation 10

[0074] x (0) (k + 1) = x (1) (k + 1) - x (1) (k) …… Equation 10

[0075] It can be understood that through Equations 1 to 10 involved in the GM(1,1) model, the cellular data of the corresponding road section at any future time can be predicted. Of course, the specific implementation process can refer to the existing methods and will not be elaborated in this disclosure.

[0076] S203. Use the cellular data to perform road simulation on the emergency section to obtain simulated road simulation data.

[0077] In some examples, the device can perform road simulation on the corresponding emergency section based on the cellular data determined in S202 above, so as to obtain simulated road simulation data.

[0078] In some examples, when performing road simulation, based on the road emergency information, for the cellular data corresponding to the accident location, time, starting and ending lanes, the state thereof can be modified to a state prohibiting vehicles from entering. For example, 0 can be used to represent prohibition of entry, and 1 can be used to represent permission to enter. Of course, the above is only an exemplary description, and specific adjustments can be made according to the actual situation, which is not limited in this disclosure.

[0079] It can be understood that the above operations can indicate that an emergency has occurred at the corresponding location in the road network.

[0080] S204. Based on the simulated road simulation data, control the driving behavior of the first vehicle driving on the emergency section.

[0081] In some examples, the device can use the simulated road simulation data obtained in S203 to perform corresponding road planning and / or vehicle driving behavior planning. And based on the road planning and / or vehicle driving behavior planning, control the driving behavior of the corresponding vehicle driving on the emergency section. For example, the first vehicle. Wherein, the first vehicle can be any vehicle driving on the emergency section.

[0082] It can be understood that by controlling the driving behavior of the first vehicle, the congestion on the emergency section can be effectively avoided, and the occurrence of secondary accidents can also be prevented to a certain extent.

[0083] Based on the cellular data of the emergency section, the present disclosure can accurately simulate the road conditions of the emergency section. So as to make a plan based on the simulation results, effectively avoid road congestion or secondary accidents, and improve the planning effect of the accident section.

[0084] In some embodiments, as Figure 3 shown, Figure 3 FIG. is a flowchart of another method for controlling the driving behavior of a vehicle according to an embodiment of the present disclosure. Among them, the simulated road simulation data may include vehicle following data. The steps of using the cellular data to perform road simulation on the emergency section in S203 to obtain the simulated road simulation data may include:

[0085] S301, determine the first position information of the first vehicle and the second position information of the second vehicle.

[0086] In some examples, the device can determine the first position information of the first vehicle and the second position information of the second vehicle. Among them, the second vehicle is the vehicle closest to the first vehicle in the driving direction of the first vehicle.

[0087] S302, determine the distance between the first vehicle and the second vehicle according to the first position information and the second position information.

[0088] In some examples, the device can determine the distance between the first vehicle and the second vehicle according to the first position information and the second position information obtained in S301.

[0089] S303, determine the following strategy of the first vehicle following the second vehicle based on the cellular data and the distance.

[0090] In some examples, the device can determine the following strategy of the first vehicle following the second vehicle based on the cellular data and the distance determined in S302. It can be understood that following means a vehicle is driving behind another vehicle.

[0091] In some examples, if it is assumed that the first vehicle is the leading vehicle closest to the emergency, then the cell closest to the leading vehicle in the lane where the emergency is located can be regarded as a second vehicle with a speed of 0 for following.

[0092] After S303, in some embodiments, the steps of controlling the driving behavior of the first vehicle driving on the emergency section in S204 may include:

[0093] S304. Based on the following - vehicle - following strategy, control the first vehicle to follow the second vehicle.

[0094] In some examples, the device may control the first vehicle to follow the second vehicle according to the following - vehicle - following strategy determined in S303.

[0095] This disclosure uses cellular data to determine the following - vehicle - following strategy of a vehicle. Based on the more accurate predicted cellular data, a more reasonable and correct following - vehicle - following strategy can be obtained, thereby avoiding road congestion caused by emergencies and effectively preventing the occurrence of secondary accidents.

[0096] In some embodiments, in S304, based on the cellular data and the spacing, determining the following - vehicle - following strategy for the first vehicle to follow the second vehicle includes: If the spacing meets a preset safety - distance threshold, determine the following - vehicle - following strategy as accelerating the speed of the first vehicle or maintaining a constant speed. If the spacing does not meet the preset safety - distance threshold, determine the following - vehicle - following strategy as decelerating the speed of the first vehicle.

[0097] In some examples, when a vehicle brakes emergently, to avoid collisions between the current vehicle and other vehicles, there should be at least a safe spacing between different vehicles. This spacing can be called the safety - distance threshold, denoted as Gap. safe Among them, the safety - distance threshold is related to the braking capabilities of its own vehicle, the leading vehicle, and the reaction time of the driver.

[0098] It can be seen from a vehicle - emergency - braking schematic diagram as Figure 4 shown that the spacing between the first vehicle 401 and the second vehicle 402 at time t needs to maintain at least the safety - distance threshold. Only in this way can it be ensured that at the moment after the vehicle brakes emergently and stops, that is, at time t stop the first vehicle 401' and the second vehicle 402' will not collide. It can be understood that the first vehicle 401 represents the first vehicle at time t, and the first vehicle 401' represents the first vehicle at time t stop moment. Similarly, the second vehicle 402 represents the second vehicle at time t, and the second vehicle 402' represents the second vehicle at time t stop moment. Among them, Gap safe，n’ represents the safety - distance threshold that the n'th vehicle (i.e., the first vehicle) should maintain from the leading vehicle.

[0099] Among them, the position of the first vehicle 401 can be denoted as x′ n’ (t), the position of the second vehicle 402 can be denoted as x′ n’+1 (t), the body length of the first vehicle 401 and the first vehicle 401' can be denoted as l n’ , the body length of the second vehicle 402 and the second vehicle 402' can be denoted as l n’+1The maximum deceleration of the first vehicle 401 and the first vehicle 401' is b n’ , and the reaction time of the driver of the first vehicle 401 and the first vehicle 401' can be denoted as τ n’ . The driving speed of the first vehicle 401 is v n’ (t), and the driving speed of the second vehicle 402 is v n’+1 (t). Then Gap safe，n’ can be calculated using Equation 11

[0100] Gap safe，n’ = max(2×v n’ (t), x′ n’+1 (t)-x′ n’ (t)-l n’+1 )... Equation 11

[0101] Of course, it can be seen through Figure 4 that Gap safe，n’ can also be obtained based on the braking distance of the first vehicle and the braking distance of the second vehicle. Among them, the braking distance refers to the distance required for the vehicle to stop when braking suddenly. Then Equation 11 can be transformed into Equation 12, that is

[0102]

[0103] where b n’+1 is the maximum deceleration of the second vehicle 402 and the second vehicle 402'.

[0104] In some examples, when the device determines that the distance meets a pre-set safety distance threshold, it can be considered that the current distance between the first vehicle and the second vehicle is relatively safe. Therefore, the following distance strategy can be set to control the first vehicle to accelerate or control the first vehicle to maintain a constant speed. Among them, meeting the pre-set safety distance threshold means that, for example, when the distance is greater than or equal to the safety distance threshold, it can be considered that the distance meets the safety distance threshold.

[0105] For example, the device can first determine whether the distance changes, that is, whether the distance between the first vehicle and the second vehicle changes. When the device determines that the distance increases and further determines that the distance meets the pre-set safety distance threshold, the following distance strategy can be set to control the first vehicle to accelerate.

[0106] In some examples, Equation 13 can be used to determine the speed of the first vehicle after acceleration.

[0107] v n’ (t + 1)= min(v n’ (t)+a′ n’ , V max , Gap safe，n’)...Formula 13

[0108] Among them, a′ n’ represents the normal acceleration of the first vehicle, V max Indicates the pre-set maximum speed limit for the vehicle.

[0109] In some examples, the headway between the first and second vehicles should be no less than 1 second. Headway refers to the time interval between the front ends of two consecutive vehicles in a platoon traveling in the same lane passing a specific section. Headway represents the time difference between the front ends of the two vehicles passing the same location. For example, when a platoon is in motion, the second vehicle in the queue will need to wait an extra 1 second for the preceding vehicle to leave.

[0110] It can be seen from Formula 13 that the maximum speed of the vehicle after acceleration will not exceed the maximum speed limit of the vehicle.

[0111] It can be understood that the car-following strategy setting controls the acceleration of the first vehicle, which can meet the driver's expectation of traveling at a higher speed.

[0112] In some examples, if the device determines that the distance between the first and second vehicles is not increasing, such as decreasing or not changing, and further determines that the distance between the first and second vehicles meets a predetermined safety distance threshold, the following strategy may be configured to control the first vehicle to maintain a constant speed. For example, the speed at the next moment may be determined based on Equation 14.

[0113] v n’ (t+1)=min(v n’ (t), Gap safe，n’ )...Formula 14

[0114] It is understood that the car-following strategy setting controls the first vehicle to maintain a constant speed, which can ensure the safe driving of the vehicle. No speed change measures will be taken at this time.

[0115] In some examples, when the device determines that the distance between the first and second vehicles does not meet a pre-set safety distance threshold, it may be considered that the distance between the first and second vehicles is too small and driving is unsafe (or dangerous), and the following strategy may be configured to control the first vehicle to decelerate. The pre-set safety distance threshold may not be met, for example, when the distance is less than the safety distance threshold.

[0116] It can be understood that at this time, regardless of whether the distance changes or not, and whether the change in the distance is a larger distance or a smaller distance, the following strategy is set to control the first vehicle to decelerate.

[0117] In some examples, it is possible to further determine which deceleration method to use for deceleration based on whether the second vehicle is stationary. For example, if the second vehicle is stationary, i.e., v n’+1 (t) = 0, then based on safety considerations, a safe deceleration rule can be used to decelerate the vehicle. That is, it is necessary to ensure that the distance between the first vehicle and the second vehicle is not less than 1 m. For example, it can be determined by Equation 15.

[0118] v n’ (t + 1) = max{min(v n’ (t) - b n’ , (Gap safe，n’ - 1) / 2), 0} …… Equation 15

[0119] In other examples, if the second vehicle is non-stationary, i.e., v n’+1 (t) ≠ 0, then a deterministic deceleration rule can be used to decelerate the vehicle. For example, it can be determined by Equation 16.

[0120] v n’ (t + 1) = max{min(v n’ (t) - b n’ , Gap safe，n’ / 2), 0} …… Equation 16

[0121] Based on the relationship between the spacing and the safety distance threshold, the present disclosure can specifically determine the following-following strategy of the vehicle, so as to ensure safer driving of the vehicle traveling on the emergency event section.

[0122] In some embodiments, the following-following strategy may further include: controlling the deceleration of the first vehicle by using a pre-configured conventional deceleration. In some examples, considering the uncertainty of the driving behavior of the driver during driving, a random slowdown probability R p is introduced into the following-following rule. In some examples, R p can take 0.11. The vehicle traveling on the road can slow down in terms of speed according to R p . For example, the vehicle speed after slowdown can be calculated by Equation 17.

[0123] v n’ (t + 1) = max{v n’ (t) - b′ n’ , 0}…… Equation 17

[0124] where b′ n’ represents the conventional deceleration of the first vehicle. It can be seen that the random slowdown can decelerate according to b n’ .

[0125] The present disclosure introduces a random slowdown process, which can accurately simulate the uncertainty during a driver's driving, thereby enabling more accurate control of the driving behavior of the first vehicle.

[0126] In some embodiments, the simulated road simulation data may include vehicle lane-changing data. When performing road simulation on the emergency section using the cellular data in S203 to obtain the simulated road simulation data, it may include: if the first position information of the first vehicle is upstream of the lane where the emergency position information is located, determining the first target lane of the first vehicle according to the cellular data. The first target lane is used for the first vehicle to avoid the road accident corresponding to the road emergency information.

[0127] In some examples, the first position information being upstream of the lane where the emergency position information is located can be considered as the first vehicle not having passed through the emergency section yet, or as before the first vehicle reaches the emergency section. At this time, a vehicle lane-changing strategy can be provided for the first vehicle according to the cellular data. And in some cases, the first vehicle is controlled to perform corresponding lane changes.

[0128] For example, a road emergency may cause the closure of multiple lanes. The device can determine the lane numbers on the currently closed road that support passing by avoiding according to the cellular data. For example, they can be denoted as lane 1, lane 2, lane 3, lane 4, etc. from left to right in sequence. The device can determine the lane number closest to the lane where the first vehicle is located and use this lane as the first target lane. When there are multiple lanes with the same spacing, the lane that preferably meets the lane-changing conditions can be selected as the first target lane. The lane-changing conditions can be preset. For example, according to the queue length of the lane, vehicle density, etc., and can be arbitrarily set according to the actual situation, which is not limited in the present disclosure.

[0129] In some examples, after determining the first target lane, if the section where the vehicle is traveling changes, such as driving into other sections, the above process is repeated to re-determine the first target lane.

[0130] The present disclosure provides a lane-changing strategy before the vehicle enters the emergency section, which helps the vehicle effectively avoid obstacles, thereby avoiding further congestion or secondary accidents.

[0131] In some embodiments, the cellular data may further include lane queue length data. Determining the first target lane of the first vehicle according to the cellular data may further include: determining the first target lane according to the lane queue length data. As Figure 5 shown, Figure 5 is a flowchart of a method for determining lane queue length data according to an embodiment of the present disclosure. The lane queue length data can be obtained in the following manner:

[0132] S501. For each lane, determine the number of cells with vehicles in the lane.

[0133] In some examples, the device can determine the lane queue length data for each lane. Therefore, based on each lane, the number of cells with vehicles in the corresponding lane can be determined.

[0134] In some examples, the device can first determine the position of the first vehicle in the lane from the start position of the lane in the opposite direction of the vehicle driving direction. It can be understood that the opposite direction can also be considered as the upstream direction of the lane.

[0135] In some examples, a fixed length L can be preset to be 5m. If the device determines that there are no vehicles in the cells scanned for a length of L in the upstream direction from the first vehicle, the scanning ends. Otherwise, continue to scan in the upstream direction until the queuing condition is not met. The non - meeting of the queuing condition means, for example, that the cell does not contain a vehicle. Of course, it can also be equivalently replaced with other conditions according to the actual situation, which is not limited in this disclosure. At the same time, it can be understood that the fixed length L can be adjusted arbitrarily according to the actual situation, which is not limited in this disclosure.

[0136] S502. Obtain the lane queue length data corresponding to the lane according to the number of cells.

[0137] In some examples, the device can determine the lane queue length data corresponding to the corresponding lane by combining the number of cells containing vehicles counted in S501 with the preset cell length.

[0138] In some examples, the device can also determine the average queue length data of the corresponding road section based on the lane queue length data of each lane.

[0139] This disclosure uses cell data to determine the lane queue length, so that a more suitable first target lane can be planned based on the lane queue length, improving the accuracy of the vehicle avoiding obstacles and further preventing road congestion.

[0140] In some embodiments, the cell data may further include road network saturation data. Determining the first target lane of the first vehicle according to the cell data may further include: determining the first target lane according to the road network saturation data. As Figure 6 shown, Figure 6 is a flowchart of a method for determining road network saturation data according to an embodiment of this disclosure. The road network saturation data can be obtained in the following manner:

[0141] S601. Determine the maximum number of vehicles that the emergency section can carry.

[0142] In some examples, the device can determine the maximum number of vehicles that the emergency section can carry.

[0143] For example, it can be assumed that the designed traffic capacity of each lane is C = 2000 veh / h, which means that 2000 vehicles can pass through per hour. Of course, the specific data of C can be adjusted arbitrarily according to the actual situation. For example, it will vary to different degrees according to different terrains, and the present disclosure does not make any limitations.

[0144] Based on C, the average headway h corresponding to this traffic capacity can be calculated through Equation 18.

[0145]

[0146] After that, the device can use h obtained from Equation 18 to obtain the maximum number of vehicles Cap on the corresponding road section by using Equation 19.

[0147]

[0148] Among them, v’ represents the average vehicle speed on this road section, and l i’ represents the lane length of the i’-th lane on this road section, and i’ is 1, 2, …, n”. l car represents the average vehicle length, and 5 is the preset minimum headway. Of course, 5 can be replaced with any other possible value in other examples, and the present disclosure does not make any limitations.

[0149] S602. Determine the road network saturation data of the emergency section according to the maximum number of vehicles.

[0150] In some examples, the device can determine the road network saturation data of the emergency section according to Cap determined in S601. For example, it can be obtained based on Equation 20.

[0151]

[0152] Among them, x” represents the road network saturation, and Num veh represents the total number of vehicles on the corresponding road section at a predicted moment.

[0153] In the related art, the road network saturation is evaluated by measuring the actual traffic flow and the designed traffic capacity. If a large-scale road blockage is caused by an emergency, it is difficult to find the actual traffic flow in the road network area where the accident is located, and the traffic flow measurement is 0. As a result, the road network saturation is also 0, while the road network in the actual accident area is already saturated. Therefore, the present disclosure introduces the calculation of road network density, which has stronger applicability.

[0154] The present disclosure uses cell data to determine the road network saturation, so that the first target lane that more conforms to the situation can be planned based on the road network saturation, improving the accuracy of vehicles avoiding obstacles and further avoiding road congestion.

[0155] In some embodiments, the method may further include: if the first position information is located downstream of the lane of the emergency event position information, determining a second target lane for the first vehicle based on the attribute information of the first vehicle, the pre-configured driver style information, and the lane information where the first vehicle is located.

[0156] In some examples, that the first position information is located downstream of the lane of the emergency event position information can be considered that the first vehicle has passed through the emergency event section, or that the first vehicle has reached after the emergency event section. At this time, a vehicle lane-changing strategy can be provided for the first vehicle based on the attribute information of the first vehicle, the pre-configured driver style information, and the lane information where the first vehicle is located. And in some cases, control the first vehicle to perform corresponding lane changes.

[0157] For example, determine a second target lane for the first vehicle based on the attribute information of the first vehicle, the pre-configured driver style information, and the lane information where the first vehicle is located.

[0158] In some examples, the vehicle attribute information can, for example, describe what type of vehicle the first vehicle is, such as a car, a large vehicle, etc. Among them, large vehicles are not allowed to drive in the innermost lane. If the lanes are sorted from left to right in sequence, large vehicles are not allowed to drive in the innermost lane, i.e., lane 1. While cars can drive in any lane. In other examples, different driver styles can be pre-configured, such as aggressive, steady, and conservative. Of course, the above is only an exemplary description, and specific settings and adjustments can be made according to the actual situation, and the present disclosure does not make any limitations.

[0159] In some examples, taking the vehicle types of large vehicles and cars, driver styles of aggressive, steady, and conservative, and 3 lanes as an example for description. For example, the above information corresponding to a certain vehicle can be used as input and an output can be obtained, that is, the device determines the selection probability of each lane for the vehicle at the next moment based on the input information. Then determine the second target lane based on this probability. And under some conditions, control the first vehicle to change lanes, that is, change to the second target lane to drive.

[0160] Figure 7 It is a schematic diagram of the vehicle lane-changing probability of an embodiment of the present disclosure.

[0161] Such as Figure 7As shown, if the vehicle type is a car and it is assumed that the car is traveling in the leftmost lane, it can be seen that according to different driver types, the probabilities of choosing the second target lane are all different. It can be understood that the driver type is the driver style mentioned above. For example, when the driver type is aggressive, since the first vehicle is itself in the leftmost lane, it is impossible to choose to change lanes to the left, that is, the lane-changing probability of changing lanes to the left is 0%. Since the driver type is aggressive, obviously the driver is more inclined to a faster vehicle speed. Because the first vehicle is already in the leftmost lane at this time, the lane-changing probability of staying in the original lane is approximately 90%. It can be understood that the vehicle speed of vehicles traveling in the left lane on the road can usually be faster than that of vehicles traveling in the right lane, and the vehicle speed allowed in the leftmost lane is the fastest. Obviously, since changing lanes to the right will reduce the vehicle speed in certain cases, usually an aggressive driver has only a 10% lane-changing probability of changing lanes to the right.

[0162] When the driver type is steady, since the first vehicle is itself in the leftmost lane, it is impossible to choose to change lanes to the left, that is, the lane-changing probability of changing lanes to the left is 0%. Since the driver type is steady, obviously the driver usually does not have a preference for a certain lane. Therefore, the lane-changing probability of staying in the original lane and the lane-changing probability of changing lanes to the right can each account for 50%.

[0163] When the driver type is conservative, since the first vehicle is itself in the leftmost lane, it is impossible to choose to change lanes to the left, that is, the lane-changing probability of changing lanes to the left is 0%. Since the driver type is conservative, obviously the driver is more inclined to a relatively slower vehicle speed to seek a smoother drive. Because the first vehicle is in the leftmost lane at this time, and the vehicle speed of vehicles traveling in the leftmost lane is relatively fast, the lane-changing probability of staying in the original lane is only approximately 10%. And the driver is more inclined to change to a lane with a relatively slower vehicle speed. Therefore, usually a conservative driver has approximately a 90% lane-changing probability of changing lanes to the right.

[0164] Figure 8 It is another schematic diagram of vehicle lane-changing probability according to an embodiment of the present disclosure.

[0165] As Figure 8 shown, if the vehicle type is a car and it is assumed that the car is traveling in the middle lane, at this time the driver can choose to change lanes to either side or stay in the original lane. When the driver type is aggressive, obviously the driver is more inclined to a faster vehicle speed. Therefore, the lane-changing probability of changing lanes to the left is approximately 90%. Because the right lane often corresponds to a lane with a slower vehicle speed, usually an aggressive driver will not change lanes to the right, that is, the lane-changing probability of changing lanes to the right is 0%. And the lane-changing probability of an aggressive driver staying in the original lane is only 10%.

[0166] If the driver type is stable and progressive, and at this time the first vehicle is in the middle lane. In order to maintain a stable driving, the lane-changing probability of keeping the original lane is about 80%. The lane-changing probabilities of changing lanes to the left and to the right can each account for 10%.

[0167] If the driver type is conservative, and at this time the first vehicle is in the middle lane. At this time, the lane-changing probabilities of keeping the original lane and changing lanes to other lanes can each account for 50%. Since the driver is a conservative driver, he is more inclined to the lane with a slower vehicle speed. Therefore, the lane-changing probability of changing lanes to the right is often higher than the lane-changing probability of changing lanes to the left. For example, the lane-changing probability of changing lanes to the right can be 40%, and the lane-changing probability of changing lanes to the left is only 10%.

[0168] Figure 9 It is another schematic diagram of the vehicle lane-changing probability according to the embodiment of the present disclosure.

[0169] As Figure 9 shown, if the vehicle type is a car and it is assumed that the car is driving in the rightmost lane. When the driver type is aggressive, obviously the driver is more inclined to a faster vehicle speed. Since the vehicle speed in the rightmost lane is the slowest, the lane-changing probability of changing lanes to the left is almost 100%. An aggressive driver usually does not keep the original lane, that is, the lane-changing probability of keeping the original lane is 0%. Also, since the first vehicle is already in the rightmost lane at this time, it is impossible to change lanes to the right, that is, the lane-changing probability of changing lanes to the right is also 0%.

[0170] If the driver type is stable and progressive, and at this time the first vehicle is in the rightmost lane. In order to maintain a stable driving, the driver usually selects a lane with a moderate vehicle speed, such as the middle lane. Therefore, the lane-changing probability of changing lanes to the left is about 80%. The lane-changing probability of keeping the original lane is about 20%. Since the first vehicle is already in the rightmost lane at this time, it is impossible to change lanes to the right, that is, the lane-changing probability of changing lanes to the right is still 0%.

[0171] If the driver type is conservative, and at this time the first vehicle is in the rightmost lane. Since the vehicle speeds in the middle lane and the rightmost lane are not the highest vehicle speeds, the lane-changing probabilities of keeping the original lane and changing lanes to the left can each account for 50%. Since the first vehicle is already in the rightmost lane at this time, it is impossible to change lanes to the right, that is, the lane-changing probability of changing lanes to the right is still 0%.

[0172] Figure 10 It is still another schematic diagram of the vehicle lane-changing probability according to the embodiment of the present disclosure.

[0173] As Figure 10As shown, if the vehicle type is a large vehicle and it is assumed that the large vehicle is driving in the middle lane, at this time the driver can choose to change lanes to the right or stay in the original lane. When the driver type is aggressive, since large vehicles are usually not allowed to drive in the leftmost lane and it is assumed that there are only 3 lanes at this time. Therefore, the lane-changing probability of staying in the original lane is almost 100%. Aggressive drivers tend not to choose to change lanes, that is, the lane-changing probability of changing lanes to the right is 0%. And since large vehicles are usually not allowed to drive in the leftmost lane, the driver will not change lanes to the left either, that is, the lane-changing probability of changing lanes to the left is also 0%.

[0174] When the driver type is steady and progressive and the first vehicle is in the middle lane at this time. In order to maintain a stable driving, the lane-changing probability of staying in the original lane is about 90%. And the lane-changing probability of changing lanes to the right can be 10%. Since large vehicles are usually not allowed to drive in the leftmost lane, the driver will not change lanes to the left either, that is, the lane-changing probability of changing lanes to the left is still 0%.

[0175] When the driver type is conservative and the first vehicle is in the middle lane at this time. At this time, the lane-changing probability of staying in the original lane and the lane-changing probability of changing lanes to the right of the driver can each account for 50%. Since large vehicles are usually not allowed to drive in the leftmost lane, the driver will not change lanes to the left either, that is, the lane-changing probability of changing lanes to the left is still 0%.

[0176] Figure 11 It is another schematic diagram of the vehicle lane-changing probability of the present disclosure embodiment.

[0177] As Figure 11 shown, if the vehicle type is a large vehicle and it is assumed that the large vehicle is driving in the rightmost lane. When the driver type is aggressive, obviously the driver prefers a faster speed. Since the speed in the rightmost lane is the slowest, the lane-changing probability of changing lanes to the left is almost 100%. Aggressive drivers usually do not stay in the original lane, that is, the lane-changing probability of staying in the original lane is 0%. And because the first vehicle is already in the rightmost lane at this time, it is impossible to change lanes to the right, that is, the lane-changing probability of changing lanes to the right is also 0%.

[0178] When the driver type is steady and progressive and the first vehicle is in the rightmost lane at this time. In order to maintain a stable driving, the driver usually chooses a lane with a moderate speed, such as the middle lane. Therefore, the lane-changing probability of changing lanes to the left is about 80%. And the lane-changing probability of staying in the original lane is about 20%. Because the first vehicle is already in the rightmost lane at this time, it is impossible to change lanes to the right, that is, the lane-changing probability of changing lanes to the right is still 0%.

[0179] When the driver type is conservative and the first vehicle is in the rightmost lane at this time. Therefore, the lane-changing probability of the driver usually maintaining the original lane and changing lanes to the left can each account for 50%. Since the first vehicle is already in the rightmost lane at this time, it is impossible to change lanes to the right, that is, the lane-changing probability of changing lanes to the right is still 0%.

[0180] It can be understood that the above Figures 7 to 11 is only an exemplary description, and the specific probability can be adaptively adjusted and modified according to the actual situation, and the present disclosure does not make a limitation.

[0181] In some examples, when the device determines the second target lane, it can determine whether to change lanes according to the situation of the vehicles in the second target lane. For example Figure 12 as shown, a vehicle lane-changing scenario 1200 is shown. In this scenario, vehicle 1201 can be the first vehicle, and vehicle 1202 can be the second vehicle. Vehicle 1203 is the vehicle behind the first vehicle in the second target lane, and vehicle 1204 is other vehicles in front of the first vehicle in the second target lane.

[0182] It can be seen that the distance between vehicle 1201 and vehicle 1202 still needs to maintain at least the safety distance threshold Gap safe，n’ . The distance between vehicle 1201 and vehicle 1203 can be denoted as d n’，back . The distance between vehicle 1201 and vehicle 1204 can be denoted as Gap n’，other .

[0183] At this time, if vehicle 1201 wants to change lanes to the second target lane, it needs to determine whether the conditions of Formula 21 and Formula 22 are met. For example

[0184] d n’，back >Gap safe，n’ …… Formula 21

[0185] Gap n’，other >Gap safe，n’ …… Formula 22

[0186] When the conditions of Formula 21 and Formula 22 are met, it can be determined that the first vehicle changes lanes, that is, changes to the second target lane.

[0187] Of course, it can be understood that for the first vehicle to change to the first target lane, the conditions of Formula 21 and Formula 22 can also be applied.

[0188] Of course, in some examples, when the driver makes a forced lane change according to the actual situation, assuming that the above active lane change (such as the first target lane or the second target lane) is also triggered at this time, the driver's forced lane change often has a higher execution priority. That is, give priority to making a forced lane change.

[0189] It can be understood that the purpose of the vehicle lane change involved in the above disclosure is to solve the problem that when a vehicle merges into a ramp or passes through a lane closure section, the vehicles often gather in one lane, and at this time, the other available lanes are not fully utilized.

[0190] In some embodiments, as Figure 13 shown, Figure 13 FIG. is a flowchart of another method for controlling vehicle driving behavior according to an embodiment of the present disclosure. The method may further include the following steps:

[0191] S1301, obtaining vehicle driving information of a first vehicle.

[0192] In some examples, the device may obtain vehicle driving information of the first vehicle. For example, the current position information, vehicle speed, etc. of the first vehicle. For example, the position information of the first vehicle may be x′ n’ (t), and the vehicle speed may be v n’ (t).

[0193] S1302, updating the first position information based on the vehicle driving information and the first position information of the first vehicle.

[0194] In some examples, the device may update the first position information based on the vehicle driving information obtained in S1301 and the first position information of the first vehicle.

[0195] For example, if x′ n’ (t)+v n’ (t)≤L, the updated first position information x′ n’ (t + 1) can be determined using Equation 23. Wherein, L represents the lane length of the lane where the first vehicle is located.

[0196] x′ n’ (t + 1)→x′ n’ (t)+v n’ (t) …… Equation 23

[0197] If x′ n’ (t)+v n’ (t)>L, the updated first position information x′ n’ (t + 1) can also be determined according to the number of downstream lanes connected to the current lane. For example, if the number of downstream lanes is only 1, and the number of empty cells w between the tail vehicle position of the downstream lane and a cell in the entrance lane is greater than the vehicle body length of the first vehicle. Then the position corresponding to the front of the first vehicle in the downstream lane can be obtained through Equation 24. For example,

[0198] min{x′ n’ (t)+vn’ (t)-L-1, w-1}. …… Formula 24

[0199] If the number of downstream lanes is more than one, the lane identical to the current lane can be preferentially selected, and the number of empty cells w between the position of the trailing vehicle in the downstream lane and a cell in the entrance lane is greater than the vehicle length of the first vehicle. Then the position corresponding to the head of the first vehicle in the downstream lane can still be obtained through Formula 24.

[0200] It can be understood that after the vehicle position is updated, the following-following strategy and / or lane-changing strategy can be re-determined based on the updated first position information.

[0201] The present disclosure can also update the first position information, so as to continuously predict and obtain the simulation results within a future period of time, which is beneficial to timely taking appropriate control measures to avoid traffic jams or secondary accidents.

[0202] In some embodiments, the method may further include: updating the cell data according to the updated first position information.

[0203] In some examples, after the first position information is updated, the lane to be changed can be determined first, and the attribute of the first vehicle can be switched to the changed lane. Then, the corresponding cell data on the changed lane is determined, for example, the cell data parallel to the cell data corresponding to the vehicle and located on the changed lane is determined.

[0204] It can be understood that when updating the cell data, the vehicle speed before lane change can be updated to the cell data after lane change. And the update of the vehicle speed can refer to the position update method provided in the above Formula 24, which will not be elaborated in the present disclosure.

[0205] The present disclosure can also update the cell data, which is beneficial to subsequent simulation using the refined cell data again and providing corresponding strategies. Thus, continuous simulation within a future period of time is realized, which is beneficial for the manager to timely take appropriate control measures.

[0206] Figure 14 It is a road simulation schematic diagram of an embodiment of the present disclosure.

[0207] As Figure 14 shown, it can be seen that if the above Figures 2 to 13 method is adopted, road simulation can be carried out for a certain moment or a certain period of time in the future, and the possible traffic jams and the queuing situations of each vehicle can be simulated in advance. Thus, it is beneficial for road managers or drivers to reasonably plan the sections with emergencies and make corresponding preparations in advance.

[0208] Figure 15It is a schematic diagram of a following rule process according to an embodiment of the present disclosure.

[0209] As Figure 15 shown, the present disclosure also provides a schematic diagram of a vehicle following rule process, and the process may include the following steps:

[0210] S1501, vehicle following.

[0211] In some examples, the device may determine that a first vehicle follows a second vehicle.

[0212] S1502, determine whether the spacing becomes larger.

[0213] In some examples, the device may determine whether the spacing between the first vehicle and the second vehicle becomes larger. If the spacing becomes larger, then execute S1503; if the spacing does not become larger, for example, becomes smaller or remains unchanged, then execute S1506.

[0214] S1503, whether the spacing is less than the safety distance.

[0215] In some examples, if it is determined that the spacing becomes larger, the device may further determine whether the spacing is less than a preset safety distance threshold. If the spacing is less than the safety distance threshold, then execute S1504; if the spacing is not less than the safety distance threshold, for example, is greater than or equal to the safety distance threshold, then execute S1505.

[0216] S1504, control the first vehicle to decelerate.

[0217] In some examples, if the spacing is less than the safety distance threshold, the device may control the first vehicle to decelerate.

[0218] S1505, control the first vehicle to accelerate.

[0219] In some examples, if the spacing is greater than or equal to the safety distance threshold, the device may control the first vehicle to accelerate.

[0220] S1506, whether the spacing is less than the safety distance.

[0221] In some examples, if it is determined that the spacing becomes smaller or remains unchanged, the device may further determine whether the spacing is less than a preset safety distance threshold. If the spacing is less than the safety distance threshold, then execute S1507; if the spacing is not less than the safety distance threshold, for example, is greater than or equal to the safety distance threshold, then execute S1508.

[0222] S1507, control the first vehicle to decelerate.

[0223] In some examples, if the spacing is less than the safety distance threshold, the device may control the first vehicle to decelerate.

[0224] S1508, control the first vehicle to maintain a constant speed.

[0225] In some examples, if the distance is greater than or equal to the safety distance threshold, the device can control the first vehicle to maintain a constant speed.

[0226] It can be understood that for the specific implementation process, reference can be made to Figure 3 , Figure 4 the corresponding description, which will not be elaborated herein in the present disclosure.

[0227] The above Figures 2 to 15 scheme described in the present disclosure can make up for the lack of event influence range and road network evaluation in traditional event recognition technologies. And it provides lane-changing rules for vehicle following and lane closure, which can provide more refined vehicle data for the research of sudden accidents.

[0228] Meanwhile, for the scenario of sudden events, the evaluation method of the road network is optimized, which can be applied to the relevant decisions of the highway management department.

[0229] Based on the same concept, the embodiments of the present disclosure also provide a device for controlling vehicle driving behavior.

[0230] It can be understood that in order to implement the above functions, a device for controlling vehicle driving behavior provided by the embodiments of the present disclosure includes the corresponding hardware structures and / or software modules for executing each function. Combining the units and algorithm steps of the various examples disclosed in the embodiments of the present disclosure, the embodiments of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiments of the present disclosure.

[0231] As an exemplary embodiment, Figure 16 is a schematic diagram of a device for controlling vehicle driving behavior shown in an exemplary embodiment of the present disclosure. Referring to Figure 16 as shown, a device 1600 for controlling vehicle driving behavior is provided. The device 1600 can implement the above Figures 1 to 15Any one of the methods involved herein. The device 1600 may include: an acquisition module 1601, configured to acquire road emergency information, where the road emergency information includes emergency time information and emergency location information; a determination module 1602, configured to determine cellular data of the emergency section by using historical road data related to the emergency time information and the emergency location information, where the emergency section includes the location corresponding to the emergency location information, and the cellular data is used to describe the vehicle driving conditions of the corresponding section; a simulation module 1603, configured to perform road simulation on the emergency section by using the cellular data to obtain simulation road simulation data; and a control module 1604, configured to control the driving behavior of a first vehicle traveling on the emergency section based on the simulation road simulation data.

[0232] Through the cellular data of the emergency section, the present disclosure can accurately simulate the road conditions of the emergency section. So as to make a plan based on the simulation results, which can effectively avoid road congestion or secondary accidents and improve the planning effect of the accident section.

[0233] In some possible implementation manners, the simulation road simulation data includes vehicle following data; the simulation module 1603 is further configured to determine a first position information of the first vehicle and a second position information of a second vehicle, where the second vehicle is the vehicle closest to the first vehicle in the driving direction of the first vehicle; determine a distance between the first vehicle and the second vehicle according to the first position information and the second position information; determine a following strategy for the first vehicle to follow the second vehicle based on the cellular data and the distance; and the control module 1604 is further configured to control the first vehicle to follow the second vehicle based on the following strategy.

[0234] The present disclosure determines the following strategy of the vehicle by using the cellular data. A more reasonable and correct following strategy can be obtained based on the more accurate predicted cellular data, thereby avoiding road congestion caused by emergencies and effectively avoiding the occurrence of secondary accidents.

[0235] In some possible implementation manners, the simulation module 1603 is further configured to: if the distance meets a preset safety distance threshold, determine the following strategy as controlling the first vehicle to accelerate or maintain a constant speed; if the distance does not meet the preset safety distance threshold, determine the following strategy as controlling the first vehicle to decelerate.

[0236] Based on the relationship between the distance and the safety distance threshold, the present disclosure can specifically determine the following strategy of the vehicle, thereby ensuring safer driving of the vehicle traveling on the emergency section.

[0237] In some possible implementation manners, the control module 1604 is further configured to: control the first vehicle to decelerate by using a preset conventional deceleration.

[0238] The present disclosure introduces a random slowdown process, which can accurately simulate the uncertainty during a driver's driving, thereby enabling more accurate control of the driving behavior of the first vehicle.

[0239] In some possible implementation manners, the simulated road simulation data includes vehicle lane change data; the simulation module 1603 is further configured to: if the first position information of the first vehicle is located upstream of the lane of the emergency position information, determine a first target lane for the first vehicle according to the cellular data, where the first target lane is used for the first vehicle to avoid the road accident corresponding to the road emergency information.

[0240] The present disclosure provides a lane change strategy before the vehicle enters the emergency section, which helps the vehicle effectively avoid obstacles, thereby avoiding the exacerbation of congestion or the occurrence of secondary accidents.

[0241] In some possible implementation manners, the cellular data includes lane queue length data; the simulation module 1603 is further configured to: determine the first target lane according to the lane queue length data; the lane queue length data is obtained in the following manner: for each lane, determine the number of cells with vehicles in the lane; and obtain the lane queue length data corresponding to the lane according to the number of cells.

[0242] The present disclosure determines the lane queue length using the cellular data, so that a more suitable first target lane can be planned based on the lane queue length, improving the accuracy of the vehicle to avoid obstacles and further preventing road congestion.

[0243] In some possible implementation manners, the cellular data further includes road network saturation data; the simulation module 1603 is further configured to: determine the first target lane according to the road network saturation data; the road network saturation data is obtained in the following manner: determine the maximum number of vehicles that can be carried in the emergency section; and determine the road network saturation data of the emergency section according to the maximum number of vehicles that can be carried.

[0244] The present disclosure determines the road network saturation using the cellular data, so that a more suitable first target lane can be planned based on the road network saturation, improving the accuracy of the vehicle to avoid obstacles and further preventing road congestion.

[0245] In some possible implementation manners, the simulation module 1603 is further configured to: if the first position information is located downstream of the lane of the emergency position information, determine a second target lane for the first vehicle based on the attribute information of the first vehicle, the pre-configured driver style information, and the lane information where the first vehicle is located.

[0246] It can be understood that the purpose of the vehicle lane change involved in the present disclosure is to solve the problem that when a vehicle merges into a ramp or passes through a lane closure section, the vehicles often gather in one lane, and at this time, the other vacant lanes are not fully utilized.

[0247] In some possible implementation manners, the apparatus 1600 further includes: the obtaining module 1601 is further configured to obtain the vehicle driving information of the first vehicle; the updating module 1605 is configured to update the first position information based on the vehicle driving information and the first position information of the first vehicle.

[0248] The present disclosure can also update the first position information, so as to continuously predict and obtain the simulation results within a future period of time, which is beneficial to timely taking appropriate control measures to avoid congestion or secondary accidents.

[0249] In some possible implementation manners, the updating module 1605 is further configured to: update the cell data according to the updated first position information.

[0250] The present disclosure can also update the cell data, which is beneficial to subsequent simulation using the refined cell data again and providing corresponding strategies. Thus, continuous simulation within a future period of time is realized, which is beneficial for the manager to timely take appropriate control measures.

[0251] Regarding the apparatus involved in the above of the present disclosure Figure 16 The specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0252] In the technical solution of the present disclosure, the acquisition, storage, and application of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0253] According to the embodiments of the present disclosure, the present disclosure also provides a device for controlling vehicle driving behavior, a readable storage medium, and a computer program product.

[0254] Figure 16 FIG. shows a schematic block diagram of a device 1700 for controlling vehicle driving behavior that can be used to implement the embodiments of the present disclosure. It can be understood that the device 1700 can be a network device or a terminal device. The device 1700 is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe, a server cluster, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0255] AsFigure 17 As shown, device 1700 includes a computing unit 1701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1702 or a computer program loaded from a storage unit 1708 into a random access memory (RAM) 1703. In the RAM 1703, various programs and data required for the operation of the device 1700 can also be stored. The computing unit 1701, the ROM 1702, and the RAM 1703 are connected to each other via a bus 1704. An input / output (I / O) interface 1705 is also connected to the bus 1704.

[0256] Multiple components in the device 1700 are connected to the I / O interface 1705, including: an input unit 1706, such as a keyboard, a mouse, etc.; an output unit 1707, such as various types of displays, speakers, etc.; a storage unit 1708, such as a magnetic disk, an optical disc, etc.; and a communication unit 1709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1709 allows the device 1700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0257] The computing unit 1701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1701 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1701 executes the various methods and processes described above, such as Figures 1 to 15 any of the methods described. For example, in some embodiments, Figures 1 to 15 any of the methods described can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 1708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1700 via the ROM 1702 and / or the communication unit 1709. When the computer program is loaded into the RAM 1703 and executed by the computing unit 1701, one or more steps of any of the methods described above can be executed. Alternatively, in other embodiments, the computing unit 1701 can be configured to execute the above Figures 1 to 15 any of the methods described by any other appropriate means (e.g., by means of firmware).

[0258] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0259] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0260] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0261] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0262] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0263] A computer system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, or a server of a distributed system, or a server incorporating blockchain. Of course, in some examples, the server can also refer to a server cluster.

[0264] This disclosure, through vehicle visualization and traffic prediction, truly restores in advance the impact of emergencies on traffic in the future, making up for the shortcoming of traditional AI video recognition technology that it is difficult to predict the impact range of events, facilitating managers to take appropriate control measures in a timely manner to avoid congestion or secondary accidents.

[0265] This disclosure also introduces road network density for the analysis of road network saturation, solving the problem that it is difficult to measure the cross-sectional traffic flow under actual accident scenarios as the congestion length dynamically increases.

[0266] This disclosure also designs vehicle following and lane-changing rules in emergency scenarios based on the safety distance and the cellular automata model.

[0267] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0268] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for controlling vehicle driving behavior, the method comprising: Obtaining road emergency information, where the road emergency information includes emergency time information and emergency location information; Using historical road data related to the emergency time information and the emergency location information to determine the cell data of the emergency section, where the emergency section includes the location corresponding to the emergency location information, and the cell data is used to describe the vehicle driving conditions of the corresponding section; Performing road simulation on the emergency section using the cell data to obtain simulation road simulation data; Based on the simulation road simulation data, controlling the driving behavior of a first vehicle traveling on the emergency section; Wherein, the performing road simulation on the emergency section using the cell data to obtain simulation road simulation data includes: If the first position information of the first vehicle is upstream of the lane of the emergency location information, determining a first target lane for the first vehicle according to the cell data, where the first target lane is used for the first vehicle to avoid the road accident corresponding to the road emergency information.

2. The method according to claim 1, wherein The simulation road simulation data includes vehicle following data; The performing road simulation on the emergency section using the cell data to obtain simulation road simulation data includes: Determining the first position information of the first vehicle and the second position information of a second vehicle, where the second vehicle is the vehicle closest to the first vehicle in the driving direction of the first vehicle; Determining the distance between the first vehicle and the second vehicle according to the first position information and the second position information; Based on the cell data and the distance, determining a following strategy for the first vehicle to follow the second vehicle; The controlling the driving behavior of the first vehicle traveling on the emergency section based on the simulation road simulation data includes: Based on the following strategy, controlling the first vehicle to follow the second vehicle.

3. The method according to claim 2, wherein, The determining the following strategy for the first vehicle to follow the second vehicle based on the cell data and the distance includes: If the distance meets a preset safety distance threshold, determining the following strategy as controlling the first vehicle to accelerate or maintain a constant speed; If the distance does not meet the preset safety distance threshold, determining the following strategy as controlling the first vehicle to decelerate.

4. The method according to claim 2, wherein The following strategy further includes: Using a pre-configured conventional deceleration to control the first vehicle to decelerate.

5. The method according to claim 1, wherein The simulation road simulation data includes vehicle lane change data.

6. The method according to claim 5, wherein, The cell data includes lane queue length data; The determining the first target lane for the first vehicle according to the cell data includes: Determining the first target lane according to the lane queue length data; The lane queue length data is obtained in the following manner: For each lane, determining the number of cells with vehicles in the lane; Obtaining the lane queue length data corresponding to the lane according to the number of cells.

7. The method according to claim 5, wherein The cell data further includes road network saturation data; Determining the first target lane of the first vehicle according to the cell data includes: Determining the first target lane according to the road network saturation data; The road network saturation data is obtained in the following manner: Determining the maximum number of vehicles that the emergency section can carry; Determining the road network saturation data of the emergency section according to the maximum number of vehicles that can be carried.

8. The method according to claim 5, wherein The method further includes: If the first position information is downstream of the lane of the emergency position information, determining a second target lane of the first vehicle based on the attribute information of the first vehicle, the pre-configured driver style information, and the lane information where the first vehicle is located.

9. The method according to any one of claims 1-8, wherein, The method further includes: Obtaining the vehicle driving information of the first vehicle; Updating the first position information based on the vehicle driving information and the first position information of the first vehicle.

10. The method according to claim 9, wherein The method further includes: Updating the cell data according to the updated first position information.

11. A device for controlling vehicle driving behavior, the device includes: An acquisition module, configured to acquire road emergency information, where the road emergency information includes emergency time information and emergency position information; A determination module, configured to determine cell data of an emergency section by using historical road data related to the emergency time information and the emergency position information, where the emergency section includes the position corresponding to the emergency position information, and the cell data is used to describe the vehicle driving conditions of the corresponding section; A simulation module, configured to perform road simulation on the emergency section by using the cell data to obtain simulation road simulation data; A control module, configured to control the driving behavior of a first vehicle driving on the emergency section based on the simulation road simulation data; The simulation module is further configured to: If the first position information of the first vehicle is upstream of the lane of the emergency position information, determining a first target lane of the first vehicle according to the cell data, where the first target lane is used for the first vehicle to avoid the road accident corresponding to the road emergency information.

12. The apparatus according to claim 11, wherein, The simulation road simulation data includes vehicle following data; The simulation module is further configured to determine the first position information of the first vehicle and the second position information of a second vehicle, where the second vehicle is the vehicle closest to the first vehicle in the driving direction of the first vehicle; determining the distance between the first vehicle and the second vehicle according to the first position information and the second position information; determining a following strategy for the first vehicle to follow the second vehicle based on the cell data and the distance; The control module is further configured to control the first vehicle to follow the second vehicle based on the following strategy.

13. The device according to claim 12, wherein, The simulation module is further configured to: If the distance meets a pre-set safety distance threshold, determining the following strategy as controlling the first vehicle to accelerate or maintain a constant speed; If the distance does not meet the pre-set safety distance threshold, determining the following strategy as controlling the first vehicle to decelerate.

14. The device according to claim 12, wherein The control module is further configured to: Control the deceleration of the first vehicle by using a pre-configured normal deceleration.

15. The apparatus according to claim 11, wherein, The simulated road simulation data includes vehicle lane change data.

16. The apparatus according to claim 15, wherein, The cell data includes lane queue length data; The simulation module is further configured to: Determine the first target lane according to the lane queue length data; The lane queue length data is obtained in the following manner: For each lane, determine the number of cells with vehicles in the lane; Obtain the lane queue length data corresponding to the lane according to the number of cells.

17. The device according to claim 15, wherein, The cell data further includes road network saturation data; The simulation module is further configured to: Determine the first target lane according to the road network saturation data; The road network saturation data is obtained in the following manner: Determine the maximum number of vehicles that the emergency incident section can carry; Determine the road network saturation data of the emergency incident section according to the maximum number of vehicles that can be carried.

18. The apparatus according to claim 15, wherein, The simulation module is further configured to: If the first position information is downstream of the lane of the emergency incident position information, determine the second target lane of the first vehicle based on the attribute information of the first vehicle, the pre-configured driver style information, and the lane information where the first vehicle is located.

19. The device according to any one of claims 11-18, wherein, The device further includes: The acquisition module is further configured to acquire the vehicle driving information of the first vehicle; An update module, configured to update the first position information based on the vehicle driving information and the first position information of the first vehicle.

20. The apparatus according to claim 19, wherein, The update module is further configured to: Update the cell data according to the updated first position information.

21. A device for controlling vehicle driving behavior, including: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product, including a computer program, where the computer program implements the method according to any one of claims 1-10 when executed by a processor.

Images