Collision early warning method and device, equipment, storage medium and computer program product

Abstract

The invention provides a collision early warning method and device, equipment, a storage medium and a computer program product. The collision early warning method comprises the following steps: acquiring first driving state data of a target bus driving in or out of a bus stop at a first moment and second driving state data of a network connection vehicle; track prediction is carried out according to the first driving state data and historical state data of the target public transport vehicle, and a target prediction track corresponding to a first time range starting from the first moment is obtained; and determining an early warning range corresponding to the first time range according to the first driving state data, the second driving state data and the target prediction trajectory, so as to determine a risk vehicle entering the early warning range from the networked vehicles, and carrying out collision early warning on the risk vehicle. According to the method and the device, a more accurate prediction track and an early warning range are predicted in combination with the scene that the bus enters and exits from the station, and the timeliness and the accuracy of collision early warning in the scene that the bus enters and exits from the station are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of Internet of Things, and in particular to a collision warning method and device, equipment, a storage medium and a computer program product. BACKGROUND

[0002] At present, highway construction is rapidly developing, and the number of vehicles is rapidly expanding, so traffic safety is very important. The public transportation platform area is a key point for traffic accidents and traffic efficiency on urban roads. The bus stops and leaves the platform will have a great impact on other vehicles around. Collision warning for risk vehicles in time when the bus stops can greatly reduce the probability of accidents.

[0003] In related technologies, the distance between the vehicle and other vehicles and their respective speeds are calculated at the vehicle end, or the risk vehicles are positioned and their trajectories are predicted to perform vehicle collision warning. However, real-time calculation of the distance between each vehicle makes the vehicle end calculation time-consuming, and positioning of the risk vehicle is easily affected by the single vehicle sensing distance, making it difficult to cover the network-connected vehicle blind area. For the scenario of bus entering and leaving the station and the like, the time and range accuracy of the warning data obtained by the above method cannot be guaranteed. SUMMARY

[0004] The embodiments of the present application provide a collision warning method, device, equipment, storage medium and computer program product, which improve the timeliness and accuracy of collision warning.

[0005] The technical solutions of the embodiments of the present application are as follows:

[0006] In a first aspect, the embodiments of the present application provide a collision warning method, comprising:

[0007] obtaining first driving state data of a target bus and second driving state data of a network-connected vehicle; wherein the target bus is a bus entering or leaving a bus station at a first time, and the network-connected vehicle is a vehicle other than the target bus;

[0008] performing trajectory prediction according to the first driving state data and historical state data of the target bus to obtain a target prediction trajectory corresponding to a first time range; wherein the start time of the first time range is the first time;

[0009] determining a warning range corresponding to the first time range according to the first driving state data, the second driving state data and the target prediction trajectory;

[0010] According to the second driving state data and the pre-warning range, a risk vehicle is determined from the connected vehicle, and a collision pre-warning is performed on the risk vehicle.

[0011] In some embodiments of the present application, the first driving state data comprises first vehicle speed data, and the trajectory prediction according to the first driving state data and the historical state data of the target bus vehicle obtains a target prediction trajectory corresponding to a first time range, which comprises:

[0012] An initial prediction trajectory is determined through a trajectory prediction model and the historical state data of the target bus vehicle;

[0013] The initial prediction trajectory is filtered through the first vehicle speed data to determine the target prediction trajectory.

[0014] In some embodiments of the present application, the determination of the pre-warning range corresponding to the first time range according to the first driving state data, the second driving state data and the target prediction trajectory comprises:

[0015] The running trajectory range of the target bus vehicle corresponding to the first time range is determined according to the first driving state data and the target prediction trajectory;

[0016] A pre-warning distance threshold is determined according to the first driving state data and the second driving state data;

[0017] The pre-warning range is determined according to the running trajectory range and the pre-warning distance threshold.

[0018] In some embodiments of the present application, the first driving state data comprises first position data, and the determination of the running trajectory range of the target bus vehicle corresponding to the first time range according to the first driving state data and the target prediction trajectory comprises:

[0019] A nearest lateral tangent is determined according to the first position data, and a farthest lateral perpendicular is determined according to the target prediction trajectory corresponding to the first time range;

[0020] The running trajectory range corresponding to the first time range is determined according to the nearest lateral tangent and the farthest lateral perpendicular.

[0021] In some embodiments of the present application, the first driving state data comprises first deceleration data and first position data, the second driving state data comprises second vehicle speed data and second position data, and the determination of the pre-warning distance threshold according to the first driving state data and the second driving state data comprises:

[0022] determine the pre-warning distance threshold based on the first deceleration data, the first position data, the first vehicle speed data, the second position data and the second vehicle speed data.

[0023] In some embodiments of the present application, the collision pre-warning to the risk vehicle comprises:

[0024] pushing collision pre-warning information and / or driving suggestion information to the risk vehicle; the collision pre-warning information at least comprises the first position data of the target public vehicle, and the driving suggestion information at least comprises direction suggestion information and / or speed suggestion information.

[0025] In a second aspect, the embodiments of the present application further provide a collision pre-warning device, comprising:

[0026] an acquisition unit configured to acquire first driving state data of a target public vehicle and second driving state data of a networked vehicle; wherein the target public vehicle is a public vehicle entering or leaving a bus station at a first time, and the networked vehicle is a vehicle other than the target public vehicle;

[0027] a prediction unit configured to perform trajectory prediction according to the first driving state data and historical state data of the target public vehicle to obtain a target prediction trajectory corresponding to a first time range;

[0028] a determination module configured to determine a pre-warning range corresponding to the first time range according to the first driving state data, the second driving state data and the target prediction trajectory, and determine a risk vehicle from the networked vehicle according to the second driving state data and the pre-warning range; wherein a start time of the first time range is the first time;

[0029] a pre-warning module configured to perform collision pre-warning to the risk vehicle.

[0030] In a third aspect, the embodiments of the present application further provide a collision pre-warning device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the collision pre-warning method of any one of the above when executing the computer program.

[0031] In a fourth aspect, the embodiments of the present application further provide a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the collision pre-warning method of any one of the above.

[0032] In a fifth aspect, the embodiments of the present application further provide a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the collision pre-warning method of any one of the above.

[0033] In the collision warning method provided by the embodiment of the application, the first driving state data of the target public vehicle and the second driving state data of the networked vehicle are obtained; the target public vehicle is a public vehicle entering or leaving a bus station at a first time, and the networked vehicle is a vehicle other than the target public vehicle; the first time range corresponding target prediction trajectory is obtained according to the first driving state data and the historical state data of the target public vehicle; the starting time of the first time range is the first time; the first time range corresponding warning range is determined according to the first driving state data, the second driving state data and the target prediction trajectory; the risk vehicle is determined from the networked vehicle according to the second driving state data and the warning range, and the collision warning is performed on the risk vehicle. The embodiment of the application can predict a more accurate prediction trajectory by combining the scene of the public vehicle entering or leaving the station, can determine a more accurate warning range in real time, and improves the timeliness and accuracy of the collision warning in the scene of the public vehicle entering or leaving the station, thereby improving the driving safety and traffic efficiency of the public vehicle and the surrounding networked vehicle.

[0034] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the technical solutions of the application. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 The system architecture schematic diagram of the collision warning method provided by the embodiment of the application is shown.

[0036] Figure 2 The flowchart of the collision warning method provided by the embodiment of the application is shown.

[0037] Figure 3 The flowchart of determining the target prediction trajectory provided by the embodiment of the application is shown.

[0038] Figure 4 The schematic diagram of the target prediction trajectory provided by the embodiment of the application is shown.

[0039] Figure 5 The flowchart of determining the warning range provided by the embodiment of the application is shown.

[0040] Figure 6 The flowchart of determining the running trajectory range of the target public vehicle provided by the embodiment of the application is shown.

[0041] Figure 7 The schematic diagram of the nearest transverse tangent provided by the embodiment of the application is shown.

[0042] Figure 8 The schematic diagram of the farthest transverse vertical provided by the embodiment of the application is shown.

[0043] Figure 9 A schematic diagram of a running track range is shown.

[0044] Figure 10 A schematic diagram of a pre-warning range is shown.

[0045] Figure 11 A schematic diagram of a pre-warning range in a scenario that a target bus vehicle drives into a platform is shown.

[0046] Figure 12 A schematic diagram of a pre-warning range in a scenario that a target bus vehicle drives out of a platform is shown.

[0047] Figure 13 A schematic diagram of a collision pre-warning device is shown.

[0048] Figure 14 A structural schematic diagram of an electronic device is shown. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0050] It should be understood that the "embodiments of the present application" or "the foregoing embodiments" mentioned throughout the specification mean that the specific features, structures or characteristics related to the embodiments are included in at least one embodiment of the present application. Therefore, "in the embodiments of the present application" or "in the foregoing embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be applied in one or more embodiments in any suitable manner. In various embodiments of the present application, the size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The serial number of the above-mentioned embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0051] In addition, the drawings are only schematic illustrations of the embodiments of the present application, and are not necessarily drawn to scale. The same reference signs in the drawings represent the same or similar parts, and therefore repeated description thereof will be omitted. Some block diagrams shown in the drawings are functional entities, which do not necessarily have to correspond to physically or logically independent entities. These functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0052] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this application and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or," as used herein, refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0053] It should be understood that, although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a particular order or hierarchy. These terms are used only to distinguish one type of information from another. For example, a first information can be termed a second information, and similarly, a second information can be termed a first information, without departing from the scope of the present disclosure. Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining" or "in response to a determination."

[0054] At present, highway construction is rapidly developing, and the number of vehicles is rapidly expanding, so the protection of traffic safety is crucial. The bus station area is a key point for traffic accidents and traffic efficiency on urban roads. The bus vehicle stops at the station, and drives away from the station, which will have a great impact on other vehicles around. Collision warning for risk vehicles in time when the bus vehicle stops at the station can greatly reduce the probability of accidents. In related technologies, the distance between the vehicle and other vehicles and the speed of each vehicle are calculated at the vehicle end to perform vehicle collision warning. However, real-time calculation of the distance between each vehicle makes the vehicle end calculation time-consuming, so that the accuracy of the time and range of the warning data is difficult to guarantee. In addition, the method of positioning and trajectory prediction of risk vehicles to realize collision warning will be affected by the single vehicle sensing distance, and it is difficult to cover the blind area of the connected vehicle, and it is also difficult to meet the scene requirements such as the time and trajectory of the bus vehicle entering and leaving the station.

[0055] Based on the above problems, the embodiment of the present application provides a collision warning method, which can predict a more accurate prediction trajectory by combining the scene of the bus vehicle entering and leaving the station, and can determine a more accurate warning range in real time, thereby improving the timeliness and accuracy of collision warning in the scene of the bus vehicle entering and leaving the station, and improving the driving safety and passing efficiency of the bus vehicle and the surrounding connected vehicles.

[0056] Figure 1 A system architecture schematic diagram of the collision warning method provided by the embodiment of the present application is shown. As shown in Figure 1 The system 100 for realizing the collision warning method can at least include a bus vehicle-mounted intelligent scheduling device 101, a bus vehicle-mounted OBU (Onboard Unit) 102, a connected vehicle OBU 103, and a vehicle-road cooperation cloud control platform 104.

[0057] The bus-mounted intelligent scheduling device 101 is loaded on a bus vehicle, and can obtain and send a scheduling instruction for the bus vehicle to arrive at a station. The bus-mounted OBU 102 is loaded on the bus vehicle, and can receive the scheduling instruction sent by the bus-mounted intelligent scheduling device 101. The high-precision positioning service module contained in the scheduling instruction can further obtain real-time positioning information, a timestamp, a vehicle ID (Identity document, identification number) and other driving state data such as a speed and a heading angle of the bus vehicle. The connected vehicle OBU 103 can obtain real-time positioning information, a timestamp, a vehicle ID and other driving state data of the connected vehicle. The bus-mounted OBU 102 and the connected vehicle OBU 103 can further package the collected driving state data into a BSM (Basic Safety Message) based on V2X and send the BSM to the cloud control platform 104 for vehicle-infrastructure cooperation.

[0058] The cloud control platform 104 for vehicle-infrastructure cooperation can include a vehicle data acquisition module 1041, a data analysis module 1042 and a pre-warning information publishing module 1043. The vehicle data acquisition module 1041 can acquire the driving state data collected by the bus-mounted OBU 102 and the connected vehicle OBU 103. The data analysis module 1042 can determine a predicted trajectory according to the real-time positioning information and the historical state data of the bus vehicle acquired by the vehicle data acquisition module 1041, and calculate a pre-warning range and a risk vehicle close to the pre-warning range. The pre-warning information publishing module 1043 can generate a collision pre-warning information according to the risk vehicle determined by the data analysis module 1042, and send the collision pre-warning information to the risk vehicle through an RSI (Roadside Information) based on V2X.

[0059] In the embodiments of the present application, the driving state data of the bus vehicle is first obtained in real time by the bus-mounted OBU 102, the scheduling instruction sent by the bus-mounted intelligent scheduling device 101 is received, and the obtained bus vehicle related data is uploaded to the cloud control platform 104 for vehicle-infrastructure cooperation. The connected vehicle OBU 103 uploads the related data of the connected vehicle to the cloud control platform 104 for vehicle-infrastructure cooperation. The cloud control platform 104 for vehicle-infrastructure cooperation determines a pre-warning range and a risk vehicle entering the pre-warning range through calculation, and sends a collision pre-warning information to the risk vehicle.

[0060] The collision pre-warning method in the embodiments of the present application can be applied to a collision pre-warning device and a collision pre-warning apparatus, or applied to a hardware device or a system configured with the collision pre-warning device or the collision pre-warning apparatus. In the implementation process of the collision pre-warning method in the embodiments of the present application, the collision pre-warning device and the collision pre-warning apparatus can be the system 100 as described above, or the cloud control platform 104 for vehicle-infrastructure cooperation as described above, which is not specifically limited in the present application.

[0061] The following will take the vehicle-road cooperation cloud control platform 104 in Figure 1 The execution subject of the vehicle-road cooperation cloud control platform 104 in the above embodiment of the present application will be taken as an example to describe the collision warning method in the embodiment of the present application. It can be understood that the execution subject here is only exemplary, and the embodiment of the present application does not particularly limit the execution subject.

[0062] Figure 2 A flowchart of a collision warning method provided by the embodiment of the present application is shown. As shown in Figure 2 The collision warning method includes at least steps S201 to S204.

[0063] In step S201, first driving state data of a target public vehicle and second driving state data of a networked vehicle are obtained; wherein the target public vehicle is a public vehicle entering or leaving a bus station at a first time, and the networked vehicle is other vehicle except the target public vehicle.

[0064] In step S202, trajectory prediction is performed according to the first driving state data and historical state data of the target public vehicle, and a target prediction trajectory corresponding to a first time range is obtained; wherein the starting time of the first time range is the first time.

[0065] In step S203, a warning range corresponding to the first time range is determined according to the first driving state data, the second driving state data and the target prediction trajectory.

[0066] In step S204, a risk vehicle is determined from the networked vehicle according to the second driving state data and the warning range, and collision warning is performed on the risk vehicle.

[0067] The above steps of the embodiment of the present application will be described in more detail.

[0068] In step S201, first driving state data of a target public vehicle and second driving state data of a networked vehicle are obtained; wherein the target public vehicle is a public vehicle entering or leaving a bus station at a first time, and the networked vehicle is other vehicle except the target public vehicle.

[0069] In the embodiment of the present application, the target public vehicle is a public vehicle meeting the specific scenario of entering or leaving the station, and the networked vehicle refers to a vehicle connected with the vehicle-road cooperation cloud control platform through wireless communication technology except the target public vehicle.

[0070] The first time can be used to define the specific scenario of the bus entering or leaving the station in the embodiments of the application. The first time represents the start time of the scenario of the bus entering or leaving the station. For different scenarios of the bus entering or leaving the station, the first time is determined by different methods. For the bus entering the station, the first time can represent the time when the bus is at a preset distance from the station. For the bus leaving the station, the first time can represent the time when the bus leaves the station. The preset distance can be 50 meters, or other distance values, which are not particularly limited in the embodiments of the application. It can be understood that the first time corresponding to different scenarios of the bus entering or leaving the station is different, and the target bus determined by the first time is different.

[0071] The first driving state data can represent the driving state data of the target bus. The first driving state data can include time data, position data, speed data, acceleration data, and heading angle data of the target bus, and the like. It can be understood that before determining the target bus that meets the specific scenario of entering or leaving the station, the driving state data of each bus needs to be obtained in real time, so as to determine whether it meets the specific scenario of entering or leaving the station according to the position data, and then determine the target bus from it.

[0072] Correspondingly, the second driving state data can represent the driving state data of the connected vehicle. The second driving state data can include time data, position data, speed data, acceleration data, and heading angle data of the connected vehicle, and the like.

[0073] The time data and other data in the first driving state data can be obtained from the first time when the entering or leaving station scenario starts to the time when the scenario ends. The first driving state data can be obtained at a certain interval, which can be an interval of 0.1 seconds, an interval of 0.5 or 1 second, or can be adjusted according to actual needs. It can be understood that the other data in the first driving state data can be updated corresponding to the real-time obtained time data. The time interval for obtaining the first driving state data is different, the corresponding data update frequency is different, and the timeliness of the collision warning is also different.

[0074] Similarly, the time data in the second driving state data starts to be obtained and ends to be obtained at the same time as the first driving state data. The time interval for obtaining the second driving state data can also be the same as the first driving state data. The acquisition time of the first driving state data and the second driving state data is synchronized, and the first driving state data and the second driving state data at the same time are calculated to determine the collision risk, so as to improve the accuracy of the collision warning.

[0075] In the embodiments of the present application, the real-time position data and other driving state data of the bus vehicle can be acquired by the bus-mounted OBU, and the acquired data is sent to the bus-mounted intelligent scheduling device. When the bus-mounted intelligent scheduling device detects that the bus vehicle reaches a preset distance from the station or the bus vehicle drives away from the station, the bus vehicle is the target bus vehicle, and the station scheduling instruction is sent to the bus-mounted OBU through the bus-mounted intelligent scheduling device of the target bus vehicle. The driving state data and scheduling data of the target bus vehicle are sent to the cloud control platform of vehicle-road cooperation through the bus-mounted OBU. Similarly, the real-time position data and other driving state data of the connected vehicle can be acquired in real time through the connected vehicle OBU, and the driving state data of the connected vehicle near the target bus vehicle is sent to the cloud control platform of vehicle-road cooperation.

[0076] In the example, after determining the target bus vehicle driving into or driving out of the bus station, the first driving state data of the target bus vehicle and the second driving state data of other connected vehicles are acquired to assist in the determination of the subsequent warning range and risk vehicle, and the reliability of the reference data is improved through the scene limitation of the bus vehicle driving into or driving out of the station, so that the accuracy of the determined warning range and risk vehicle is higher.

[0077] In step S202, the trajectory prediction is performed according to the first driving state data and the historical state data of the target bus vehicle, and the target prediction trajectory corresponding to the first time range is obtained; wherein the starting time of the first time range is the first time.

[0078] Here, the historical state data of the target bus vehicle can include multiple position data, speed data, acceleration data, heading angle data and the like of the target bus vehicle in the scene of driving into the station area or driving out of the station area in a historical period of time, and the scheduling time of the target bus vehicle, the driving habit of the driver, the related station layout and other data in the historical period of time can also be included in the historical state data of the target bus vehicle to improve the comprehensiveness and referenceability of the historical state data of the target bus vehicle.

[0079] The first time and the first time range correspond to different determination modes of different scenarios of the target bus vehicle driving into or driving out of the station in the embodiments of the present application. If corresponding to the scenario of the target bus vehicle driving into the station, the first time is the time when the target bus vehicle reaches a preset distance from the station, and the first time range starts from the time when the target bus vehicle reaches a preset distance from the station and ends at the time when the target bus vehicle arrives at the station; if corresponding to the scenario of the target bus vehicle driving out of the station, the first time is the time when the target bus vehicle drives away from the station, and the first time range starts from the time when the target bus vehicle drives away from the station and ends at the time when the target bus vehicle drives out of the station and ends the lane change.

[0080] When the target prediction trajectory of the target public vehicle is determined, the initial prediction trajectory can be determined according to the historical trajectory information of the target public vehicle, and the initial prediction trajectory is corrected and screened to obtain the target prediction trajectory with higher accuracy.

[0081] Figure 3 A flowchart for determining a target prediction trajectory is shown. As shown in Figure 3 , the flow of determining the target prediction trajectory includes at least steps S301 to S302:

[0082] In the embodiment of the application, the first driving state data of the target public vehicle includes first speed data. When the trajectory is predicted according to the first driving state data and the historical state data of the target public vehicle, step S301 can be performed first to determine the initial prediction trajectory by the trajectory prediction model and the historical state data of the target public vehicle. The first speed data represents the speed data of the target public vehicle.

[0083] For example, the trajectory prediction model can include an encoder and a decoder. The encoder can be composed of multiple LSTMs (Long Short Term Memory, long short term memory recurrent neural network), RNNs (Recurrent Neural Network, recurrent neural network) or other neural networks, and the decoder can be composed of multiple MLPs (Multi-Layer Perception, multi-layer perception), RBFNs (Radial basis function network, radial basis function network) or other deep learning models for restoring information from encoded form to original form.

[0084] Taking LSTM as an encoding unit and MLP as a decoder for example, after obtaining the historical state data of the target public vehicle, the historical state data can be first converted into multiple data vectors, and then the multiple data vectors are input into the encoder to obtain the hidden vector at time t by formula (1):

[0085] h t =LSTM(h t-1 ,F t ) (1)

[0086] Where h t represents the hidden vector at time t output by the encoding unit LSTM, h t-1 represents the hidden vector at time t-1 generated by the previous encoding unit LSTM, and F t represents the data vector corresponding to time t in the historical state data of the target public vehicle.

[0087] Next, the decoder can be used to obtain multiple initial prediction trajectories for the future t seconds, and the specific calculation method is shown in formula (2):

[0088] y predict_1 ,y predict_2 ,...,y predict_n =MLP(h t ,y history ) (2)

[0089] wherein h t represents the hidden vector output by the encoding unit LSTM at time t, y history represents the position information of the target bus at time t, y predict_1 represents the first initial prediction trajectory determined by the MLP model, y predict_2 represents the second initial prediction trajectory determined by the MLP model, and y predict_n represents the nth (n>1) initial prediction trajectory determined by the MLP model.

[0090] After obtaining the initial prediction trajectory, the initial prediction trajectory can be corrected and screened to obtain a target prediction trajectory with higher accuracy.

[0091] In step S302, the initial prediction trajectory is filtered by the speed data of the target bus. Specifically, the real trajectory of the target bus within time T can be denoted as wherein the trajectory point at time T is which contains the longitude and latitude information and can be denoted as The original prediction trajectory obtained by the trajectory prediction model can be denoted as wherein i can be any number between 1 and n. The smoothed trajectory after filtering can be denoted as Taking the smoothed trajectory obtained by the Kalman filtering algorithm as an example, the specific calculation method is shown in formula (3) and formula (4):

[0092]

[0093]

[0094] wherein represents the real trajectory point at time T, represents the predicted trajectory point at time T, b represents the error coefficient, v T represents the speed at time T, represents the trajectory point at time T in the smoothed trajectory, represents the trajectory point at time T-1 in the smoothed trajectory, and g T represents the gain, and g TThe value range of g can be [0, 1], if g T is 0, the smooth trajectory and the original predicted trajectory of the period are the same; if g T is 1, the smooth trajectory and the real trajectory of the period are the same.

[0095] When the covariance between the real trajectory and the smooth trajectory is less than δ (δ < 1.5), it is considered that the smooth trajectory has a certain reliability. Since the gain value is closer to 0, the reliability of the smooth trajectory is lower. In order to improve the reliability of the smooth trajectory, the smooth trajectory with the gain value in the value range [β, 1] (β > 0.5) can be selected incrementally to obtain the target predicted trajectory.

[0096] Finally, m (m ≤ n) target predicted trajectories as shown in Figure 4 can be screened out, and the warning range can be determined based on the m target predicted trajectories. Figure 4 In , 401 represents a target bus vehicle, 402 represents a platform corresponding to the target bus vehicle, and 403 represents a target predicted trajectory.

[0097] In this example, the initial predicted trajectory generated by the trajectory prediction model is filtered and screened to obtain a target predicted trajectory with higher accuracy, thereby improving the accuracy and reliability of the target predicted trajectory.

[0098] In step S203, a warning range corresponding to the first time range is determined according to the first driving state data, the second driving state data, and the target predicted trajectory.

[0099] The warning range refers to the risk range around the target bus vehicle. If the connected vehicle enters the warning range, it can be considered that the connected vehicle has a certain collision risk with the target bus vehicle. It can be understood that the warning range is updated in real time according to the real-time driving state of the connected vehicle and the target bus vehicle. Since the positions of the connected vehicle and the target bus vehicle at different times can be different, different warning ranges can be determined according to different time ranges.

[0100] When determining the warning range in the first time range, the running trajectory range of the target bus vehicle in the first time range and the warning distance threshold between the target bus vehicle and the connected vehicle can be determined first, and then the warning range can be determined according to the running trajectory range and the warning distance threshold.

[0101] Figure 5 A flowchart for determining a warning range is shown. As Figure 5 shown, the process of determining the warning range at least includes steps S501 to S503.

[0102] In step S501, a running track range of the target public vehicle corresponding to the first time range is determined according to the first driving state data and the target prediction track.

[0103] Here, the first driving state data includes first position data, a nearest lateral tangent is determined according to the first position data, and a farthest lateral perpendicular is determined according to the target prediction track corresponding to the first time range.

[0104] Here, the first position data refers to position data of the target public vehicle. Taking a scenario in which the target public vehicle enters a station as an example, the first time range starts from a time when the target public vehicle is at a preset distance from the station and ends at a time when the target public vehicle arrives at the station.

[0105] Figure 6 A flowchart of determining a running track range of a target public vehicle is shown. As shown in the flowchart, the process of determining the running track range includes at least steps S601 to S602. Figure 6

[0106] In step S601, a nearest lateral tangent is determined according to the first position data, and a farthest lateral perpendicular is determined according to the target prediction track corresponding to the first time range.

[0107] Specifically, real-time position coordinates of the target public vehicle obtained through a UTM (Universal Transverse Mercator Grid System) can be denoted as (x r ,y r ), and a first track point coordinate in a future t seconds in the target prediction track can be denoted as (x p1 ,y p1 ). An included angle a between a line connecting the above two coordinates and an actual driving direction of the target public vehicle is calculated, a ∈ (0 ° ,90 ° ). All target prediction tracks are traversed in sequence, and an included angle between the first track point in each target prediction track and the real-time position of the target public vehicle is calculated to obtain an included angle set V = {a1, a2,..., am}, where m represents a number of the target prediction tracks. m

[0108] Next, a maximum value in the included angle set V, that is, a maximum included angle a max in the included angle set V, can be calculated. The target prediction track corresponding to the included angle a max is farthest from the target public vehicle among the multiple target prediction tracks. The target prediction track corresponding to the included angle a max can be denoted as y farmost , and a first track point coordinate in the target prediction track can be denoted as​​

[0109] Finally, you can use the coordinate point As the cutting point, is the slope, for y farmost By drawing a tangent to the trajectory curve, the nearest horizontal tangent can be obtained.

[0110] like Figure 7 As shown, Figure 7 A schematic diagram of a nearest transverse tangent provided by an embodiment of the present application is shown. Reference numeral 701 represents a trajectory point in the target predicted trajectory, reference numeral 702 represents the center position of the target bus, reference numeral 703 represents the line connecting the real-time center position of the target bus and the first trajectory point in the target predicted trajectory, reference numeral 704 represents the nearest transverse tangent, and reference numeral 705 represents the forward direction of the target bus.

[0111] When determining the farthest horizontal vertical line, the coordinates of the platform center point corresponding to the target bus obtained through UTM can be marked as (x c ,y c ), and mark the coordinates of the last trajectory point in the target prediction trajectory in the future t seconds as (x pend ,y pend ), calculate the Euclidean distance between the last trajectory point and the platform center coordinates, as well as the angle B between the line between the two points and the target bus's travel direction, and obtain the angle set U = {B1,...,B m}, filter from the set U Trajectory points within the range, get the trajectory point set The Euclidean distance set between the trajectory points in the set E and the platform center point is calculated as D = {d i ,...,d j}, then the maximum value of the Euclidean distance d max =max(D), then d max The corresponding target prediction trajectory is the target prediction trajectory farthest from the current position of the target bus in the scene of entering the platform, and the target prediction trajectory is recorded as y d_farmost , where the coordinates of the last trajectory point are marked as Taking this trajectory point as the starting point, draw a vertical line perpendicular to the center of the road where the target bus is located to obtain the farthest horizontal vertical line.

[0112] like Figure 8 As shown, Figure 8A schematic diagram of the farthest transverse perpendicular line is shown. Wherein, 801 represents a trajectory point in the target prediction trajectory, 802 represents the center position point of the target bus vehicle, 803 represents the line connecting the real-time center position of the target bus vehicle and the last trajectory point in the target prediction trajectory, 804 represents the farthest transverse perpendicular line, and 805 represents the forward direction of the target bus vehicle.

[0113] In step S602, the running trajectory range corresponding to the first time range is determined according to the nearest transverse tangent line and the farthest transverse perpendicular line.

[0114] Specifically, a straight line passing through the center point of the target bus vehicle and parallel to the road center line, and a straight line passing through the center point of the corresponding station of the target bus vehicle and parallel to the road center line can be determined, and the four intersection coordinates of the two straight lines determined in the above steps and the nearest transverse tangent line and the farthest transverse perpendicular line are determined, that is, a quadrilateral region can be determined according to the four intersection coordinates, and the range corresponding to the quadrilateral region is also the running trajectory range of the target bus vehicle.

[0115] As shown in Figure 9 , Figure 9 A schematic diagram of the running trajectory range is shown. Wherein, 901 represents a straight line passing through the center point of the target bus vehicle and parallel to the road center line, 902 represents the nearest transverse tangent line, 903 represents a straight line passing through the center point of the corresponding station of the target bus vehicle and parallel to the road center line, 904 represents the farthest transverse perpendicular line, and 905 represents the road center line.

[0116] In this example, a plurality of target prediction trajectories with higher accuracy are selected from the original prediction trajectory, and the running trajectory range of the target bus vehicle is determined according to the target prediction trajectory, and the running trajectory range is updated in real time according to the first driving state data of the target bus vehicle, which improves the accuracy and reliability of the running trajectory range, so as to improve the accuracy of the warning range determined according to the running trajectory range.

[0117] In step S502, the warning distance threshold is determined according to the first driving state data and the second driving state data.

[0118] The warning distance threshold refers to a safety distance threshold determined according to the current state of the target bus vehicle and the connected vehicle, which can be the shortest alarm distance when the connected vehicle approaches the warning range. The first driving state data of the target bus vehicle includes the first deceleration data and the first position data of the target bus vehicle, and the first deceleration data can include the real-time deceleration and the maximum deceleration of the target bus vehicle. The second driving state data of the connected vehicle includes the second speed data and the second position data of the connected vehicle, and the distance between the target bus vehicle and the connected vehicle can be determined according to the first position data and the second position data.

[0119] Taking the scenario that the target bus enters the station as an example, the scenario start time can be denoted as t i , the scenario end time can be denoted as t j , and any time within the triggering range of the scenario can be denoted as t k ,k∈[i,j]. The scenario start time t i here is the first time within the first time range, and the scenario end time t j is the last time within the first time range. The specific manner of determining the early warning distance threshold is shown in formula (5):

[0120]

[0121] wherein D k_min_warning represents the early warning distance threshold, represents the relative speed of the target bus and the upstream connected vehicle thereof, a max represents the maximum deceleration of the target bus, represents the real-time deceleration of the target bus, Δt represents the frequency interval of the early warning information issued by the vehicle-road cooperative cloud control platform, and t n represents the driver reaction time of the connected vehicle.

[0122] In step S503, the early warning range is determined according to the running track range and the early warning distance threshold.

[0123] Taking the early warning of the connected vehicle upstream of the target bus as an example, the upstream lane range whose distance to the running track range of the target bus reaches the early warning distance threshold is the early warning range.

[0124] Specifically, after determining the running track range of the target bus, the lanes in which the target bus can possibly appear within the first time range can be determined. For example, if a road has three lanes, namely, lane No. 1, lane No. 2 and lane No. 3, and the running track range of the target bus appears in lane No. 2 and lane No. 3, then the early warning range is in lane No. 2 and lane No. 3 and is located upstream of the running track range, the distance between the early warning range and the running track range reaches the early warning distance threshold, the width of the early warning range can be the sum of the widths of lane No. 2 and lane No. 3, and the length thereof should be consistent with the length of the running track range. The distance between the running track range and the early warning range can be determined according to the shortest distance between the parallel straight lines upstream or downstream of each other. As shown in FIG. 4, Figure 10 Figure 10 ​A schematic diagram of the early warning range is shown. Wherein, 1001 represents the running track range of the target public transport vehicle, 1002 represents the early warning range, 1003 represents the early warning distance threshold, 1004 represents the road direction, 1005 represents the first lane, 1006 represents the second lane, and 1007 represents the third lane.

[0125] In step S204, the risk vehicle is determined from the networked vehicle according to the second driving state data and the early warning range, and the collision early warning is performed on the risk vehicle.

[0126] The second driving state data of the networked vehicle can include the position data of the networked vehicle, and the risk vehicle refers to the networked vehicle that may collide with the target public transport vehicle in the scenario of the target public transport vehicle entering or exiting the station.

[0127] After determining the early warning range, if the networked vehicle enters the early warning range, the networked vehicle is determined as the risk vehicle.

[0128] After determining the risk vehicle, the collision early warning can be performed on the risk vehicle. For example, the collision early warning information and / or driving suggestion information can be pushed to the risk vehicle through voice broadcast, interface display, etc. The collision early warning information can include the position data of the target public transport vehicle that causes the risk to the vehicle, and the driving suggestion information can include the driving direction suggestion and / or the recommended driving speed suggestion of the vehicle, etc.

[0129] In this example, the risk vehicle is determined according to the early warning range with high accuracy and the position of the networked vehicle, wherein the early warning range can be updated in real time according to the driving state data of the target public transport vehicle and the networked vehicle, thereby improving the timeliness and accuracy of the collision early warning.

[0130] Figure 11 A schematic diagram of the early warning range in the scenario of the target public transport vehicle entering the station is shown. Wherein, 1101 represents the target public transport vehicle, 1102 represents the networked vehicle, 1103 represents the early warning distance threshold, 1104 represents a target prediction track in the scenario of the target public transport vehicle entering the station, 1105 represents the station corresponding to the target public transport vehicle, 1106 represents the early warning range, 1107 represents the road center line, 1108 represents the position corresponding to the first time in the target prediction track of the target public transport vehicle, and 1109 represents the road direction. Figure 11 As can be seen from FIG. 11, the position of the networked vehicle 1102 is in the early warning range, so the networked vehicle 1102 can be determined as the risk vehicle.

[0131] Figure 12A schematic diagram of a warning range in a scenario in which a target bus vehicle drives out of a platform is shown. Among them, 1201 represents a target bus vehicle, 1202 represents a networked vehicle, 1203 represents a warning distance threshold, 1204 represents a target prediction trajectory in a driving-out-of-platform scenario of the target bus vehicle, 1205 represents a platform corresponding to the target bus vehicle, 1206 represents a warning range, 1207 represents a road center line, 1208 represents a position corresponding to the first time in the target prediction trajectory of the target bus vehicle, and 1209 represents a road direction. Figure 12 It can be seen that the position of the networked vehicle 1202 is within the warning range, so it can be determined that the networked vehicle 1202 is a risk vehicle.

[0132] The collision warning method provided by the embodiment of the application can predict more accurate time nodes and prediction trajectories by combining the scenarios of the bus vehicle entering and leaving the platform, can determine a more accurate warning range in real time, improves the timeliness and accuracy of collision warning in the scenarios of the bus vehicle entering and leaving the platform, and thus improves the driving safety and passing efficiency of the bus vehicle and the surrounding networked vehicles.

[0133] Based on the above embodiment, another embodiment of the application exemplarily illustrates the application of the collision warning method in actual scenarios. In view of the problem of insufficient accuracy of collision influence range and time in the manner of realizing vehicle-road cooperative collision warning in the bus platform area according to the related technical solution, the embodiment of the application combines a bus-mounted intelligent scheduling device, a bus-mounted OBU device and a vehicle-road cooperative cloud control platform, realizes accurate determination of the bus entering and leaving time range on the basis of the interaction of the driving state data of the bus and the bus scheduling information obtained by the bus-mounted intelligent scheduling device. The short-time prediction trajectory is fitted and corrected through the historical trajectory data of the bus, the trajectory of the bus when entering and leaving the platform is comprehensively predicted, and the driving state data of the networked vehicle is combined in real time, so as to "advance" and "accurately" determine the influence range of the trajectory change of the bus, and the networked vehicles in the influence range are warned of collision. The collision warning method of the embodiment of the application does not require a road side sensing device, improves the accuracy of the warning range of the networked vehicle, and thus improves the safety and efficiency of the driving of the networked vehicle in the bus platform area.

[0134] The embodiment of the application can accurately predict the short-time driving track of the bus vehicle to the station and from the station by combining the real-time vehicle information of the bus vehicle, including vehicle high-precision positioning, real-time vehicle speed, heading angle and other data, and historical in-out station track data of the bus vehicle after triggering the in-out station event of the bus vehicle on the bus vehicle scheduling platform, thereby predicting the lane causing collision risk in the future short time, issuing the in-out station warning information of the bus vehicle to the connected vehicle with collision risk on the lane, so that other connected vehicles take appropriate measures to avoid the collision risk with the bus vehicle in advance, reduce the traffic accident rate around the bus vehicle, and improve the in-out station efficiency of the bus vehicle.

[0135] The collision warning method in the embodiment of the application can be applied to a collision warning device and a collision warning apparatus, or applied to a hardware device or a system configured with the collision warning device or the collision warning apparatus. In the implementation process of the collision warning method in the embodiment of the application, the collision warning device and the collision warning apparatus can be the system 100 as described above, or the car-road cooperation cloud control platform 104 as described above, and the application does not make specific limitations. Figure 1 Figure 1 The collision warning method in the embodiment of the application can be applied to a collision warning device and a collision warning apparatus, or applied to a hardware device or a system configured with the collision warning device or the collision warning apparatus. In the implementation process of the collision warning method in the embodiment of the application, the collision warning device and the collision warning apparatus can be the system 100 as described above, or the car-road cooperation cloud control platform 104 as described above, and the application does not make specific limitations.

[0136] First, the data between the bus intelligent scheduling device and the car-road cooperation cloud control platform is connected, the vehicle scheduling information is collected through the bus intelligent scheduling device, the high-precision positioning information and other driving state information obtained by the bus OBU device are combined to determine the vehicle positioning and the accurate time information of the pre-station driving off the platform, and the information is uploaded to the car-road cooperation cloud control platform. The platform issues the information through the UU communication mode and accurately pushes it to the surrounding connected vehicles to prompt that the bus vehicle will stop or start to avoid the collision risk. It has good applicability to the harbor type stop station and the roadside stop station area.

[0137] The embodiment of the application includes a vehicle data acquisition module, a data analysis processing module and an information data publishing module. The vehicle data acquisition module is used to realize the accurate stop station data acquisition of the bus vehicle, the bus vehicle state data acquisition and the connected vehicle state data acquisition, as shown in Figure 1 The above tasks can be realized by the bus intelligent scheduling device 101, the bus OBU 102 and the connected OBU 103.

[0138] ​The bus vehicle will stop at the platform name, ID, time data, and the data will be pushed to the bus OBU 102. The position data of the bus vehicle is obtained through the bus OBU 102. When the bus vehicle is 50 meters away from the platform, the bus intelligent scheduling device 101 pushes the station announcement information, pushes the station instruction to the bus OBU 102, and the bus intelligent scheduling device 101 sends data to the bus OBU 102 at the input time of the original predicted trajectory of the bus vehicle. The data collected by the bus OBU 102 also includes timestamp, bus vehicle ID, speed data, heading angle data, acceleration data, etc. After collecting the above data, the bus OBU 102 packs the collected and received data into V2X BSM messages and sends them to the cloud control platform 104.

[0139] In this example, the cloud control platform 104 does not rely on the single data source of the bus OBU 102, but combines the data obtained by the bus intelligent scheduling device 101 to obtain the real-time station timestamp and platform position information of the bus vehicle in advance, so as to assist the cloud control platform 104 to accurately determine the predicted trajectory and the time node of the driving state change of the bus vehicle through the combination of information.

[0140] The data analysis and processing module is used to predict the short-time trajectory of the bus vehicle based on the real-time positioning information and historical trajectory data of the bus vehicle. According to the predicted short-time trajectory, the driving trajectory change time and position of the bus vehicle, and the lane and range affected by the driving trajectory change of the bus vehicle are determined.

[0141] Specifically, first, based on the motion position and state information of the bus vehicle located in the corresponding platform area within a period of time, a trajectory prediction model is used to predict the driving trajectory of the bus vehicle in the future short time, that is, the dynamic trajectory of the bus vehicle from obtaining the station instruction sent by the bus intelligent scheduling device 101 to the stop station. The accuracy of the short-time prediction trajectory is effectively improved.

[0142] The specific steps of constructing the trajectory prediction model are as follows:

[0143] Due to the running characteristics of the bus vehicle, such as fixed stop station, relatively fixed driver shift, and relatively stable passenger flow in each period. In the platform area, the scheduling time of the bus vehicle stop station, the driving habit of the driver, the station layout, etc. are used as the influencing factors of the bus vehicle stop station in the historical trajectory prediction. The encoding part uses several LSTMs as encoding units, which can determine the hidden state vector output by any t time for a single encoding unit according to formula (1).

[0144] The decoding part uses several MLPs and can determine the final prediction result according to formula (2).

[0145] Based on the above steps, the trajectory prediction model in the embodiment of the present application is constructed, and the model can output all possible driving trajectories of all traffic participants in the scene in the next t seconds in real time.

[0146] Next, the n (n>1) possible driving trajectories obtained in the above steps can be corrected and screened, and then the possible driving areas of the bus in the future T time period can be divided based on the screened driving trajectories, and the warning areas of the connected vehicles can be further divided based on the driving areas.

[0147] Since the predicted trajectory generated by the trajectory prediction model only contains latitude and longitude position information, it does not contain vehicle speed information. However, in fact, vehicle speed is also an important factor affecting the future trajectory. Therefore, based on the Kalman filter algorithm and the speed information of the bus, the future t-second trajectory generated by the trajectory prediction model is further corrected and filtered to make the predicted future trajectory more reliable. The possible driving trajectory can be filtered using formulas (3) and (4), and the smoothed trajectory after filtering can be filtered to obtain a target predicted trajectory with higher reliability. For example, the smoothed trajectory with a gain value in the value range [β, 1] (β greater than > 0.5) can be incrementally selected to obtain the target predicted trajectory.

[0148] After obtaining the target predicted trajectory, the running trajectory range of the bus can be determined according to the target predicted trajectory. Specifically, the real-time position coordinates of the bus obtained through UTM can be marked as (x r ,y r ), and mark the coordinates of the first trajectory point in the target prediction trajectory in the future t seconds as (x p1 ,y p1 ), calculate the angle a between the line connecting the two coordinates and the actual driving direction of the bus, a∈(0 ° ,90 ° ), traverse all target prediction trajectories in turn and calculate the angle between the first trajectory point in each target prediction trajectory and the real-time position of the bus, and obtain the angle set V = {a1, a2, ..., a m}, where m represents the number of target prediction trajectories.

[0149] Next, we can calculate the maximum value in the angle set V, that is, the maximum angle a in the angle set V max , angle a max The corresponding target prediction trajectory is the one farthest from the bus among multiple target prediction trajectories. The angle a can be max The corresponding target prediction trajectory is recorded as y farmostThe first trajectory point coordinate in the target prediction trajectory is denoted as

[0150] Finally, a tangent line of the y trajectory curve can be drawn with the tangent point being , and the slope being farmost .

[0151] When determining the farthest lateral vertical line, the bus vehicle corresponding platform center point coordinate obtained by the UTM is denoted as (x c , y c ), and the last trajectory point coordinate in the target prediction trajectory in the future t seconds is denoted as (x pend , y pend ). The Euclidean distance between the last trajectory point and the platform center point coordinate is calculated, and the included angle B between the line connecting the two points and the driving direction of the bus vehicle is obtained, to obtain an included angle set U = {B1,..., B m}. The trajectory points in the range of are filtered from the set U to obtain a trajectory point set The Euclidean distance set between the trajectory points in the set E and the platform center point is calculated as D = {d i ,..., d j}. The maximum value d max = max(D) of the Euclidean distance is obtained, and the target prediction trajectory corresponding to d max is the target prediction trajectory farthest from the current position of the bus vehicle in the driving-into-platform scenario. The target prediction trajectory is denoted as y d_farmost , and the last trajectory point coordinate in the target prediction trajectory is denoted as . A vertical line perpendicular to the center of the road where the bus vehicle is located is drawn from the trajectory point, and the farthest lateral vertical line is obtained.

[0152] Then, a straight line passing through the center point of the bus vehicle and parallel to the road center line, and a straight line passing through the center point of the platform corresponding to the bus vehicle and parallel to the road center line are determined. The four intersection point coordinates of the two straight lines determined in the above steps and the nearest lateral tangent line and the farthest lateral vertical line are determined, and a quadrilateral region is determined according to the four intersection point coordinates. The range corresponding to the quadrilateral region is the running trajectory range of the bus vehicle.

[0153] When determining the running trajectory range of the bus vehicle, the warning distance threshold between the bus vehicle and the connected vehicle can also be determined according to formula (5).

[0154] Finally, the warning range can be determined according to the running trajectory range of the bus vehicle and the warning distance threshold.

[0155] According to the vehicle trajectory prediction method, the time range in which the trajectory of the target public transport vehicle can be accurately predicted is t i , the real-time position of the public transport vehicle is x i , the warning distance threshold D k_min_warning is set at the current speed, and the safety warning range of the upstream connected vehicle for the surrounding connected vehicle is the lane range at a distance D k_min_warning from the public transport vehicle.

[0156] Specifically, after determining the running trajectory range of the target public transport vehicle, the possible lanes of the target public transport vehicle in the first time range can be determined. For example, if a road has three lanes, namely, lane 1, lane 2, and lane 3, and the running trajectory range of the target public transport vehicle appears in lane 2 and lane 3, the warning range is in lane 2 and lane 3 and is upstream of the running trajectory range, the distance between the warning range and the running trajectory range reaches the warning distance threshold, the width of the warning range can be the sum of the widths of lane 2 and lane 3, and the length of the warning range should be consistent with the length of the running trajectory range. The distance between the running trajectory range and the warning range can be determined according to the shortest distance between the parallel straight lines upstream or downstream of the two ranges.

[0157] The information data publishing module is configured to push the warning information to the connected vehicle determined as the risk vehicle.

[0158] In the time range in which the public transport vehicle enters or exits the station, if the connected vehicle enters the warning range, the car-road cooperation cloud control platform 104 determines that the connected vehicle is a risk vehicle, generates an RSI message based on V2X, and sends the RSI message to the connected vehicle OBU 103 to push the warning information that the public transport vehicle will enter or exit the station to the connected vehicle. The connected vehicle OBU 103 can play the warning information through an HMI interface or in the form of voice, thereby realizing the collision warning function in the collision influence lane range.

[0159] Based on the above embodiment, the short-time prediction trajectory is fitted and corrected based on the historical trajectory data of the public transport vehicle, the trajectory of the public transport vehicle when entering or exiting the station is comprehensively predicted, and the driving state data returned by the connected vehicle in real time is combined, so that the influence range of the trajectory change of the public transport vehicle is determined in advance and accurately, and the connected vehicles in the influence range are given collision warnings, the accuracy of the warning range of the connected vehicle is improved, and the safety and efficiency of the driving of the connected vehicle in the public transport station area are improved.

[0160] In another embodiment of the present application, based on the same inventive concept as the foregoing embodiments, Figure 13 A schematic diagram of a collision warning device provided by an embodiment of the present application is shown. As shown in Figure 13 The computing unit control device 1300 includes an acquisition unit 1301, an acquisition unit 1302, a determination module 1303, and a warning module 1304.

[0161] The acquisition unit 1301 is configured to acquire first driving state data of a target public transport vehicle and second driving state data of a connected vehicle; the target public transport vehicle is a public transport vehicle that enters or exits a bus station at a first time point, and the connected vehicle is a vehicle other than the target public transport vehicle;

[0162] The prediction unit 1302 is configured to perform trajectory prediction according to the first driving state data and historical state data of the target public transport vehicle to obtain a target predicted trajectory corresponding to a first time range;

[0163] The determination module 1303 is configured to determine a warning range corresponding to the first time range according to the first driving state data, the second driving state data and the target predicted trajectory, and determine a risk vehicle from the connected vehicle according to the second driving state data and the warning range; the starting time point of the first time range is the first time point.

[0164] The warning module 1304 is configured to perform collision warning on the risk vehicle.

[0165] In some embodiments of the present application, the first driving state data includes first speed data, and the prediction unit 1302 is specifically configured to determine an initial predicted trajectory by a trajectory prediction model and the historical state data of the target public transport vehicle, and filter the initial predicted trajectory by the first speed data to determine the target predicted trajectory.

[0166] In some embodiments of the present application, the determination module 1303 is specifically configured to determine a running trajectory range of the target public transport vehicle corresponding to the first time range according to the first driving state data and the target predicted trajectory, determine a warning distance threshold according to the first driving state data and the second driving state data, and determine the warning range according to the running trajectory range and the warning distance threshold.

[0167] In some embodiments of the present application, the first driving state data includes first position data, and the determination module 1303 is further specifically configured to determine a nearest lateral tangent according to the first position data, and determine a farthest lateral perpendicular according to the target predicted trajectory corresponding to the first time range, and determine the running trajectory range corresponding to the first time range according to the nearest lateral tangent and the farthest lateral perpendicular.

[0168] In some embodiments of the present application, the first driving state data includes first deceleration data and first position data, the second driving state data includes second vehicle speed data and second position data, and the determining module 1303 is further specifically configured to determine the early warning distance threshold based on the first deceleration data, the first position data, the first vehicle speed data, the second position data, and the second vehicle speed data.

[0169] In some embodiments of the present application, the early warning module 1304 is specifically configured to push collision early warning information and / or driving suggestion information to the risk vehicle; the collision early warning information at least includes the first position data of the target public vehicle, and the driving suggestion information at least includes direction suggestion information and / or speed suggestion information.

[0170] The above device embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects to the method embodiments. In some embodiments, the device provided by the embodiments of the present application has the functions or includes the modules for executing the methods described in the above method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application.

[0171] It should be noted that, in the embodiments of the present application, if the above-mentioned computing unit control method is realized in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a ROM (Read Only Memory), a magnetic disk or an optical disk, and various program code storage media. Thus, the embodiments of the present application are not limited to any specific hardware, software or firmware, or any combination of hardware, software and firmware.

[0172] The embodiments of the present application provide a computer device, which includes a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements part or all of the steps in the above method when executing the program.

[0173] The embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement part or all of the steps in the above method. The computer readable storage medium can be transitory or non-transitory.

[0174] The embodiment of the present application provides a computer program, including computer readable code, wherein the processor in the computer device executes part or all steps of the above method when the computer readable code runs in the computer device.

[0175] The embodiment of the present application provides a computer program product, including a non-transitory computer readable storage medium storing a computer program, wherein the computer program is read and executed by a computer to implement part or all steps of the above method. The computer program product can be implemented by hardware, software or a combination thereof. In some embodiments, the computer program product is embodied as a computer storage medium, and in some other embodiments, the computer program product is embodied as a software product, such as an SDK (Software Development Kit) or the like.

[0176] It should be noted that the above description of the various embodiments tends to emphasize the differences between the various embodiments, and the same or similar parts can be referred to each other. The above description of the device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the device, storage medium, computer program and computer program product embodiments of the present application, please refer to the description of the method embodiments of the present application.

[0177] The embodiment of the present application further provides an electronic device capable of implementing the above method. As shown in the Figure 14 The hardware entities of the computer device 1400 include a processor 1401 and a memory 1402, wherein the memory 1402 stores a computer program executable on the processor 1401, and the processor 1401 implements the steps in the method of any of the above embodiments when executing the program.

[0178] The memory 1402 stores a computer program executable on the processor, and the memory 1402 is configured to store instructions and applications executable by the processor 1401, and can also cache data to be processed by the processor 1401 and each module in the computer device 1400 (for example, image data, audio data, voice communication data and video communication data), which can be implemented by a flash memory or a RAM (Random Access Memory).

[0179] The processor 1401 implements the steps of any of the above computer unit control methods when executing the program. The processor 1401 generally controls the overall operation of the computer device 1400.

[0180] The embodiment of the present application provides a computer storage medium, and the computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the computer unit control method according to any one of the above embodiments.

[0181] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects to the method embodiments. For technical details not disclosed in the storage medium and device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0182] The processor can be at least one of an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), a DSPD (Digital Signal Processing Device), a PLD (Programmable Logic Device), a FPGA (Field Programmable Gate Array), a CPU (Central Processing Unit), a controller, a microcontroller, and a microprocessor. It can be understood that the electronic device for realizing the functions of the processor can also be other electronic devices, and the embodiments of the present application are not limited specifically.

[0183] The computer storage medium / memory can be a ROM (Read Only Memory), a PROM (Programmable Read-Only Memory), an EPROM (Erasable Programmable Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), an FRAM (Ferromagnetic Random Access Memory), a flash memory, a magnetic surface memory, an optical disc, a CD-ROM (Compact Disc Read-Only Memory), or the like. The computer storage medium / memory can also be various terminals including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, and the like.

[0184] It should be understood that every feature, structure, or characteristic described in relation to one embodiment is applicable to at least one other embodiment. Therefore, the appearance of the phrase "in one embodiment" or "in some embodiments" in various places throughout the specification is not necessarily referring to the same embodiment. Furthermore, it is to be understood that the features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is also to be understood that the order of steps / operations in the above-described embodiments can be changed, and that the embodiments can include additional steps / operations not shown in the figures. Embodiments are not limited to the sequence of steps / operations described in the figures. The sequence of steps / operations should be determined based on the function and logic of the steps / operations, and should not limit the implementation of the embodiments. The sequence of the above-described embodiments is only for description, and does not represent the advantages or disadvantages of the embodiments.

[0185] It should be noted that the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0186] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The above-described device embodiments are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be through some interfaces, indirect coupling or communication connection between devices or units, which can be electrical, mechanical or other forms.

[0187] The units described above as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0188] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or hardware plus software functional unit.

[0189] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the above-mentioned method embodiments when executed; and the foregoing storage medium includes a mobile storage device, a read only memory (ROM), a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0190] Alternatively, the integrated units of the present application can be stored in a computer readable storage medium if they are realized in the form of software function modules and sold or used as independent products. Based on such understanding, the technical solutions of the present application or the parts that make contributions to the related art can be embodied in the form of software product, and the computer software product is stored in a storage medium, includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes a mobile storage device, a ROM, a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0191] The above is only the implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application.

Claims

1. A collision warning method, characterized in that: include: Acquire first driving state data of a target bus and second driving state data of a networked vehicle; wherein the target bus is a bus entering or exiting a bus stop at a first moment, and the networked vehicle is a vehicle other than the target bus; Performing trajectory prediction based on the first driving state data and the historical state data of the target bus to obtain a target predicted trajectory corresponding to a first time range; wherein the starting time of the first time range is the first time; determining a warning range corresponding to the first time range according to the first driving state data, the second driving state data, and the target predicted trajectory; A risky vehicle is determined from the connected vehicles based on the second driving state data and the warning range, and a collision warning is performed on the risky vehicle.

2. The collision warning method according to claim 1, characterized in that: The first driving state data includes first vehicle speed data, and performing trajectory prediction based on the first driving state data and historical state data of the target bus to obtain a target predicted trajectory corresponding to a first time range includes: Determine an initial predicted trajectory using a trajectory prediction model and historical status data of the target bus; The initial predicted trajectory is filtered using the first vehicle speed data to determine the target predicted trajectory.

3. The collision warning method according to claim 1 or 2, characterized in that: The determining, based on the first driving state data, the second driving state data, and the target predicted trajectory, of a warning range corresponding to the first time range includes: Determine the operating trajectory range of the target bus corresponding to the first time range according to the first driving state data and the target predicted trajectory; determining a warning distance threshold according to the first driving state data and the second driving state data; The warning range is determined according to the running trajectory range and the warning distance threshold.

4. The collision warning method according to claim 3, characterized in that: The first driving state data includes first position data, and determining the operating trajectory range of the target bus corresponding to the first time range based on the first driving state data and the target predicted trajectory includes: determining a nearest horizontal tangent line based on the first position data, and determining a farthest horizontal perpendicular line based on the target predicted trajectory corresponding to the first time range; The running trajectory range corresponding to the first time range is determined according to the nearest horizontal tangent and the farthest horizontal vertical line.

5. The collision warning method according to claim 3, characterized in that: The first driving state data includes first deceleration data and first position data, the second driving state data includes second vehicle speed data and second position data, and determining the warning distance threshold based on the first driving state data and the second driving state data includes: The warning distance threshold is determined based on the first deceleration data, the first position data, the first vehicle speed data, the second position data, and the second vehicle speed data.

6. The collision warning method according to claim 5, characterized in that: The performing of a collision warning on the risk vehicle includes: Push collision warning information and / or driving suggestion information to the risk vehicle; the collision warning information at least includes the first position data of the target bus, and the driving suggestion information at least includes direction suggestion information and / or speed suggestion information.

7. A collision warning device, characterized in that: include: an acquisition unit, configured to acquire first driving state data of a target bus and second driving state data of a network-connected vehicle; wherein the target bus is a bus entering or exiting a bus stop at a first moment, and the network-connected vehicle is a vehicle other than the target bus; a prediction unit, configured to perform trajectory prediction based on the first driving state data and the historical state data of the target bus to obtain a target predicted trajectory corresponding to a first time range; a determination module, configured to determine a warning range corresponding to the first time range based on the first driving state data, the second driving state data, and the target predicted trajectory; and determine a risky vehicle from the connected vehicles based on the second driving state data and the warning range; wherein the start time of the first time range is the first time; The early warning module is used to provide a collision warning to the risk vehicle.

8. A collision warning device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the collision warning method according to any one of claims 1 to 6 is implemented.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the collision warning method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the collision warning method according to any one of claims 1 to 6 is implemented.

Images