Vehicle trajectory processing method

Abstract

The embodiment of the specification provides a vehicle trajectory processing method, applied to a terminal device deployed on a target vehicle, comprising determining an initial position of the target vehicle; sending a trajectory acquisition request carrying the initial position to a cloud platform, and receiving a fusion trajectory set corresponding to the initial position returned by the cloud platform according to the trajectory acquisition request, wherein the fusion trajectory set comprises a fusion trajectory of the target vehicle and a fusion trajectory of an associated vehicle associated with the target vehicle; determining a target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle, and determining an associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle. Through prediction, time delay compensation of the communication link is realized, so that the finally obtained target prediction trajectory and associated prediction trajectory have real-time and accuracy, so that the motion trend of the surrounding vehicles can be determined in time and accurately.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of intelligent driving, and in particular to a vehicle trajectory processing method. BACKGROUND

[0002] With the increasing number of cars, road traffic is gradually becoming dense and complex, which in turn leads to an increase in driving stress for drivers. In complex scenarios such as complex road conditions, extreme weather, or mixed traffic, drivers need to pay attention to the vehicle conditions and road conditions around the vehicle they are driving. Currently, the driving stress of drivers can be reduced by intelligent driving technology, such as predicting the motion trajectory of surrounding vehicles to determine a driving strategy or plan a driving route.

[0003] However, when predicting the trajectory of surrounding vehicles, the motion state of the surrounding vehicles obtained from an external network is often relied on, which is lagging and difficult to accurately determine the motion trend of the surrounding vehicles, thereby leading to inaccurate determination of subsequent driving strategies or driving routes. Therefore, there is an urgent need for an effective technical solution to solve the above problems. SUMMARY

[0004] Therefore, the embodiments of the present specification provide three vehicle trajectory processing methods. One or more embodiments of the present specification simultaneously relate to two vehicle trajectory processing devices, a vehicle trajectory processing system, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects in the prior art.

[0005] According to a first aspect of the embodiments of the present specification, a vehicle trajectory processing method is provided, applied to a terminal device deployed in a target vehicle, comprising:

[0006] determining an initial position of the target vehicle;

[0007] sending a trajectory acquisition request carrying the initial position to a cloud platform, and receiving a fusion trajectory set corresponding to the initial position returned by the cloud platform according to the trajectory acquisition request, wherein the fusion trajectory set includes a fusion trajectory of the target vehicle and a fusion trajectory of an associated vehicle associated with the target vehicle;

[0008] determining a target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle, and determining an associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle.

[0009] According to a second aspect of the embodiments of the present specification, a vehicle trajectory processing device is provided, applied to a terminal device deployed in a target vehicle, comprising:

[0010] The first determining module is configured to determine an initial position of the target vehicle.

[0011] The communication module is configured to send a track acquisition request carrying the initial position to a cloud platform, and receive a fusion track set corresponding to the initial position returned by the cloud platform according to the track acquisition request, wherein the fusion track set includes a fusion track of the target vehicle and a fusion track of an associated vehicle associated with the target vehicle.

[0012] The second determining module is configured to determine a target prediction track of the target vehicle according to the fusion track of the target vehicle, and determine an associated prediction track of the associated vehicle according to the fusion track of the associated vehicle.

[0013] According to a third aspect of the embodiments of the present specification, a vehicle track processing method applied to a cloud platform is provided, including:

[0014] receiving a track acquisition request sent by a terminal device, wherein the track acquisition request carries an initial position of a target vehicle;

[0015] determining a track acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and an associated vehicle associated with the target vehicle;

[0016] determining a fusion track set corresponding to the initial position according to the track acquisition range, wherein the fusion track set includes a fusion track of the target vehicle and a fusion track of the associated vehicle associated with the target vehicle;

[0017] sending the fusion track set to the terminal device.

[0018] According to a fourth aspect of the embodiments of the present specification, a vehicle track processing apparatus applied to a cloud platform is provided, including:

[0019] The receiving module is configured to receive a track acquisition request sent by a terminal device, wherein the track acquisition request carries an initial position of a target vehicle;

[0020] The first determining module is configured to determine a track acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and an associated vehicle associated with the target vehicle;

[0021] The second determining module is configured to determine a fusion track set corresponding to the initial position according to the track acquisition range, wherein the fusion track set includes a fusion track of the target vehicle and a fusion track of the associated vehicle associated with the target vehicle.

[0022] The sending module is configured to send the set of fused trajectories to the terminal device.

[0023] According to a fifth aspect of the embodiments of the present specification, a vehicle trajectory processing method is provided, applied to a vehicle trajectory processing system including a terminal device and a cloud platform, and the method includes:

[0024] The terminal device determines an initial position of a target vehicle and sends a trajectory acquisition request carrying the initial position to the cloud platform.

[0025] The cloud platform determines a trajectory acquisition range according to the initial position and a first preset distance threshold, determines a set of fused trajectories corresponding to the initial position according to the trajectory acquisition range, and sends the set of fused trajectories to the terminal device, wherein the set of fused trajectories includes a fused trajectory of the target vehicle and a fused trajectory of an associated vehicle associated with the target vehicle.

[0026] The terminal device determines a target predicted trajectory of the target vehicle according to the fused trajectory of the target vehicle, and determines an associated predicted trajectory of the associated vehicle according to the fused trajectory of the associated vehicle.

[0027] According to a sixth aspect of the embodiments of the present specification, a vehicle trajectory processing system is provided, including a terminal device and a cloud platform, wherein,

[0028] The terminal device is configured to determine an initial position of a target vehicle and send a trajectory acquisition request carrying the initial position to the cloud platform.

[0029] The cloud platform is configured to determine a trajectory acquisition range according to the initial position and a first preset distance threshold, determine a set of fused trajectories corresponding to the initial position according to the trajectory acquisition range, and send the set of fused trajectories to the terminal device, wherein the set of fused trajectories includes a fused trajectory of the target vehicle and a fused trajectory of an associated vehicle associated with the target vehicle.

[0030] The terminal device is configured to determine a target predicted trajectory of the target vehicle according to the fused trajectory of the target vehicle, and determine an associated predicted trajectory of the associated vehicle according to the fused trajectory of the associated vehicle.

[0031] According to a seventh aspect of the embodiments of the present specification, a computing device is provided, including:

[0032] a memory and a processor;

[0033] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, and the computer executable instructions, when executed by the processor, implement the steps of the vehicle trajectory processing method.

[0034] According to an eighth aspect of an embodiment of the present specification, a computer readable storage medium is provided, which stores computer executable instructions, and the instructions, when executed by a processor, implement the steps of the vehicle trajectory processing method.

[0035] According to a ninth aspect of an embodiment of the present specification, a computer program is provided, and when the computer program is executed in a computer, the computer program causes the computer to execute the steps of the vehicle trajectory processing method.

[0036] One embodiment of the present specification provides a vehicle trajectory processing method, applied to a terminal device deployed on a target vehicle, determining an initial position of the target vehicle; sending a trajectory acquisition request carrying the initial position to a cloud platform, and receiving a fusion trajectory set corresponding to the initial position returned by the cloud platform according to the trajectory acquisition request, wherein the fusion trajectory set includes a fusion trajectory of the target vehicle and a fusion trajectory of an associated vehicle associated with the target vehicle; determining a target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle, and determining an associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle.

[0037] The above method can obtain the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle (i.e. the vehicle around the target vehicle) associated with the target vehicle by acquiring the fusion trajectory set corresponding to the initial position from the cloud platform according to the initial position of the target vehicle. Moreover, due to the time delay of the communication link between the cloud platform and the terminal device, real-time fusion trajectories cannot be obtained. Based on this, the target prediction trajectory of the target vehicle and the associated prediction trajectory of the associated vehicle can be predicted according to the obtained fusion trajectories, and the time delay of the communication link is compensated by prediction, so that the finally obtained target prediction trajectory and associated prediction trajectory have real-time and accuracy, thereby the motion trend of the vehicle around the target vehicle can be determined in time and accurately, and accurate data basis is further provided for subsequent determination of driving strategy or driving route. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 is an application scenario diagram of a vehicle trajectory processing method provided by one embodiment of the present specification;

[0039] Figure 2 is a flowchart of a vehicle trajectory processing method provided by one embodiment of the present specification;

[0040] Figure 3is a process flow diagram of a vehicle trajectory processing method provided by an embodiment of the present specification;

[0041] Figure 4 is a structural schematic diagram of a vehicle trajectory processing apparatus provided by an embodiment of the present specification;

[0042] Figure 5 is a flow diagram of another vehicle trajectory processing method provided by an embodiment of the present specification;

[0043] Figure 6 is a structural schematic diagram of another vehicle trajectory processing apparatus provided by an embodiment of the present specification;

[0044] Figure 7 is a flow diagram of a third vehicle trajectory processing method provided by an embodiment of the present specification;

[0045] Figure 8 is a structural schematic diagram of a vehicle trajectory processing system provided by an embodiment of the present specification;

[0046] Figure 9 is a structural block diagram of a computing device provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0047] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present specification. However, the present specification can be practiced without the specific details, which are not described in the present specification, and it is understood that the scope of the present specification is not limited to the details below. In other instances, well-known methods, procedures, components, and networks have not been described in detail for the sake of brevity.

[0048] The terminology used in one or more embodiments of the present specification is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the present specification. As used in one or more embodiments of the present specification and the accompanying 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 be further understood that the terms "comprises" and / or "comprising," when used in one or more embodiments of the present specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0049] It is to be understood that the terms first, second, etc. can be employed in one or more embodiments of the present specification to describe various information. Such information should not be limited by these terms. These terms are only used to distinguish one category of information from another category of information. For example, without departing from the scope of one or more embodiments of the present specification, first can be termed second, and similarly, second can be termed first. Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "in response to determining."

[0050] In addition, it should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in one or more embodiments of the present specification are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0051] Firstly, the terms involved in one or more embodiments of the present specification are explained.

[0052] GNSS: Global Navigation Satellite System, Global Navigation Satellite System.

[0053] POI: Point of Interest, in a geographic information system, a POI can be a house, a shop, a mailbox, a bus stop, etc.

[0054] At present, the development path of intelligent driving technology is divided into single vehicle type and network type. The single vehicle type intelligent driving technology relies on the sensing ability and chip computing power of the sensors deployed on the vehicle, and the hardware performance and cost requirements of the vehicle are relatively high. It can be seen that the single vehicle type intelligent driving technology is limited by its own sensing technology and sensing range, and it is difficult to process in time and accurately in complex road conditions, extreme weather, mixed vehicle running, etc. At the same time, it will also produce a blind area due to the shielding of other vehicles on the road. The network type intelligent driving technology relies on the cooperative communication between vehicles and road conditions. Specifically, it needs to interact with other networked vehicles, traffic equipment and facilities, and traffic information network, etc. It is limited by the network. Therefore, an effective technical solution is needed to solve the above problems.

[0055] In the present specification, three vehicle trajectory processing methods are provided, and the present specification relates to two vehicle trajectory processing devices, a vehicle trajectory processing system, a computing device, and a computer readable storage medium, which are described in detail one by one in the following embodiments.

[0056] Referring to Figure 1 , Figure 1 A schematic diagram of an application scenario of a vehicle trajectory processing method according to one embodiment of the present specification is shown.

[0057] Figure 1The system includes a target vehicle 102, a terminal device 104 and a cloud platform 106. The terminal device 104 is deployed on the target vehicle 102, and the terminal device 104 and the cloud platform 106 are in communication connection.

[0058] In a specific implementation, when the target vehicle 102 is driving on the road, the terminal device 104 can determine the initial position of the target vehicle 102, and send a trajectory acquisition request carrying the initial position to the cloud platform 106. After receiving the trajectory acquisition request, the cloud platform 106 can determine the fusion trajectory of each vehicle in the trajectory acquisition range corresponding to the initial position, and send the fusion trajectories to the terminal device 104 as a fusion trajectory set. The terminal device 104 can determine the fusion trajectory of the target vehicle 102 and the fusion trajectories of the associated vehicles around the target vehicle 102 in each received fusion trajectory of the vehicle, and determine the target prediction trajectory of the target vehicle 102 according to the fusion trajectory of the target vehicle 102, determine the associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle, and render and display the target prediction trajectory and the associated prediction trajectory on the display interface, so that the driver can observe the road conditions through the display interface of the terminal device even in extreme weather, thereby ensuring the safe driving of the driver.

[0059] Referring to Figure 2 , Figure 2 A flowchart of a vehicle trajectory processing method according to an embodiment of the present specification is shown, which is applied to a terminal device deployed on a target vehicle, and specifically includes the following steps.

[0060] Step 202: Determine the initial position of the target vehicle.

[0061] The terminal device deployed on the target vehicle includes but is not limited to a mobile terminal, a vehicle navigation system terminal, etc. The mobile terminal can be a mobile phone, a tablet, etc. of the driver of the target vehicle or a person riding in the target vehicle. The initial position of the target vehicle can be the position of the target vehicle at the current time during driving. Alternatively, the initial position of the target vehicle can also be a certain position to be reached during driving of the target vehicle. For example, the target vehicle is driving on a highway, and will reach position A on the highway after a period of time according to the current driving speed. The above vehicle trajectory processing method can be used to plan a path for the target vehicle in advance according to the position A.

[0062] In actual application, the initial position of the target vehicle can be represented by latitude and longitude.

[0063] Specifically, the terminal device can include a positioning unit for positioning the target vehicle, thereby determining the position of the target vehicle at the current time during driving. The positioning unit can be a radar or a GNSS.

[0064] In actual implementation, in order to ensure the instantaneity of positioning, the initial position of the target vehicle can be determined at a preset time interval, for example, the initial position of the target vehicle can be determined every 1 minute. The preset time interval can be a fixed time interval set in advance, or can be determined according to the driving speed of the target vehicle, which is not limited in the embodiments of the present disclosure.

[0065] For example, when the target vehicle is driving on a road between region A and region B, the initial position of the target vehicle can be determined as (a, b), where a is the longitude and b is the latitude.

[0066] Step 204: sending a trajectory acquisition request carrying the initial position to a cloud platform, and receiving a fusion trajectory set corresponding to the initial position returned by the cloud platform according to the trajectory acquisition request, wherein the fusion trajectory set includes a fusion trajectory of the target vehicle and a fusion trajectory of an associated vehicle associated with the target vehicle.

[0067] Specifically, after determining the initial position of the target vehicle, a trajectory acquisition request carrying the initial position can be sent to the cloud platform to acquire a fusion trajectory set corresponding to the initial position.

[0068] The cloud platform can be understood as a cloud computing platform, which can calculate the fusion trajectories of all vehicles in a target area. For example, for a highway from region A to region B, the cloud platform can calculate the fusion trajectories of each vehicle driving on the highway. The cloud platform is deployed with a data service, and the communication between the target vehicle and the cloud platform can be realized by using the data service. The cloud platform can use the data service to send the trajectories, event information and the like acquired from the roadside perception unit to the mobile terminal.

[0069] The fusion trajectory set corresponding to the initial position can be understood as a set of fusion trajectories of each vehicle included in the trajectory acquisition range corresponding to the initial position. Then the associated vehicle can be understood as other vehicles in addition to the target vehicle among each vehicle included in the trajectory acquisition range, that is, the associated vehicle can be a vehicle around the target vehicle.

[0070] Based on this, a trajectory acquisition request carrying the initial position can be sent to the cloud platform, and a set of fusion trajectories of each vehicle included in the trajectory acquisition range corresponding to the initial position can be received by the cloud platform according to the trajectory acquisition request. It can be understood that the vehicles located in the trajectory acquisition range include the target vehicle and the associated vehicle associated with the target vehicle.

[0071] In actual application, the target vehicle is also deployed with a vehicle-mounted communication unit, which can realize communication with the cloud platform.

[0072] Continuing with the above example, a trajectory acquisition request carrying the initial position (a, b) can be sent to the cloud platform, and a fusion trajectory set corresponding to the initial position returned by the cloud platform according to the trajectory acquisition request can be received, the fusion trajectory set including the fusion trajectory 1 of the target vehicle 1, the fusion trajectory 2 of the associated vehicle 2, and the fusion trajectory 3 of the associated vehicle 3.

[0073] In actual applications, in order to ensure the comprehensiveness and accuracy of the fusion trajectory of the vehicle obtained from the cloud platform and to provide a data basis for subsequent trajectory prediction, the fusion trajectory of the vehicle can be calculated and spliced by the cloud platform according to the received driving information of the vehicle, and the specific implementation manner is as follows:

[0074] The fusion trajectory of the target vehicle is obtained by splicing the initial trajectory of the target vehicle in the collection range of each shooting positioning device included in the road side perception unit. The initial trajectory of the target vehicle in the collection range of each shooting positioning device is calculated according to the driving information of the target vehicle sent by each shooting positioning device.

[0075] Among them, the road side perception unit can be understood as a vehicle perception device deployed on the roadside, and the road side perception unit can include at least two shooting positioning devices. The driving information of the target vehicle includes but is not limited to the driving speed of the target vehicle, the driving position of the target vehicle, the driving habit of the driver of the target vehicle, and the like.

[0076] In actual applications, the shooting positioning device can be a camera and a radar, which is used to realize real-time perception of traffic targets.

[0077] It can be understood that, since the collection range of each shooting positioning device is limited, based on this, a plurality of shooting positioning devices can be deployed on the roadside, each shooting positioning device collects the driving information of the vehicle in the collection range, and the cloud platform can calculate the initial trajectory of the vehicle in the collection range according to the driving information, and splice the initial trajectory in each collection range to obtain the fusion trajectory of the vehicle.

[0078] Taking a case that three shooting positioning devices are arranged on the side of a road from region A to region B as an example, vehicle 1 travels on the road from region A to region B, vehicle 1 travels to collection range 1, shooting positioning device 1 collects driving information 1 of vehicle 1 in collection range 1, vehicle 1 travels from collection range 1 to collection range 2, shooting positioning device 2 collects driving information 2 of vehicle 1 in collection range 2, vehicle 1 travels from collection range 2 to collection range 3, and shooting positioning device 3 collects driving information 3 of vehicle 1 in collection range 3. Each shooting positioning device can send the respective collected driving information to the cloud platform, the cloud platform calculates initial trajectory 1 of vehicle 1 in collection range 1 based on driving information 1, calculates initial trajectory 2 of vehicle 1 in collection range 2 based on driving information 2, calculates initial trajectory 3 of vehicle 1 in collection range 3 based on driving information 3, and splices initial trajectory 1, initial trajectory 2 and initial trajectory 3 to obtain the fusion trajectory of vehicle 1 in the driving process.

[0079] It can be understood that the calculation process of the fusion trajectory of the target vehicle and the calculation process of the fusion trajectory of the associated vehicle are the same as the fusion trajectory calculation process described above for vehicle 1.

[0080] In summary, by collecting, calculating and splicing the driving information in the driving process of the vehicle, the fusion trajectory of the vehicle is obtained, which provides more comprehensive data for subsequent trajectory prediction based on the fusion trajectory, thereby improving the accuracy of subsequent trajectory prediction.

[0081] In a specific implementation, after sending the trajectory acquisition request carrying the initial position to the cloud platform, the cloud platform can determine the trajectory acquisition range corresponding to the initial position according to the initial position and the first preset distance threshold, so as to facilitate subsequent determination of the fusion trajectory set corresponding to the initial position according to the trajectory acquisition range. In addition, after determining the initial position of the target vehicle, the terminal device can also directly determine the trajectory acquisition range corresponding to the initial position according to the initial position and the first preset distance threshold, and send the trajectory acquisition request carrying the trajectory acquisition range to the cloud platform, so that the cloud platform can directly determine the fusion trajectory set corresponding to the initial position according to the trajectory acquisition range, without the need to calculate the trajectory acquisition range again, thereby reducing the computing power of the cloud platform when a single vehicle acquires the fusion trajectory of the surrounding vehicles, saving the computing power of the cloud platform, and further ensuring the computing power resources of the cloud platform to calculate the fusion trajectories of all vehicles in the target area. The specific implementation is as follows:

[0082] After determining the initial position of the target vehicle, the method further includes:

[0083] determining a trajectory acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and an associated vehicle associated with the target vehicle.

[0084] sending a trajectory acquisition request carrying the trajectory acquisition range to the cloud platform, and receiving a fusion trajectory set corresponding to the trajectory acquisition range returned by the cloud platform according to the trajectory acquisition request.

[0085] The first preset distance threshold can be understood as a preset distance threshold between the target vehicle and the associated vehicle. It can be understood that the vehicle with a distance to the target vehicle reaching the first preset distance threshold is the associated vehicle associated with the target vehicle. For example, if the first preset distance threshold is 10 meters, then if the distance between a vehicle and the target vehicle is less than or equal to 10 meters, the vehicle is determined to be an associated vehicle (i.e., a surrounding vehicle) of the target vehicle. Then, the vehicles located in the trajectory acquisition range can be understood as vehicles that need to acquire fusion trajectories.

[0086] The fusion trajectory set corresponding to the trajectory acquisition range can be understood as a set of fusion trajectories of each vehicle located in the trajectory acquisition range. It can be understood that the vehicles located in the trajectory acquisition range include the target vehicle, and the associated vehicle is other vehicle in the vehicles located in the trajectory acquisition range except the target vehicle.

[0087] Based on this, the trajectory acquisition range can be determined according to the initial position of the target vehicle and the preset distance threshold between the target vehicle and the associated vehicle, and a trajectory acquisition request carrying the trajectory acquisition range is sent to the cloud platform, and a fusion trajectory set corresponding to the trajectory acquisition range returned by the cloud platform according to the trajectory acquisition request is received.

[0088] In the above example, the trajectory acquisition range m can be calculated according to the initial position (a, b) of the target vehicle and the first preset distance threshold c meters, and the vehicles located in the trajectory acquisition range m are the vehicles that need to acquire fusion trajectories. A trajectory acquisition request carrying the trajectory acquisition range m is sent to the cloud platform, and a fusion trajectory set corresponding to the trajectory acquisition range m returned by the cloud platform according to the trajectory acquisition request is received.

[0089] In summary, by calculating the trajectory acquisition range corresponding to the initial position in the mobile terminal, the computing power of the cloud platform can be saved, and the computing power resources of the cloud platform for calculating the fusion trajectories of all vehicles in the target area are further guaranteed.

[0090] Step 206: determining a target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle, and determining an associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle.

[0091] Specifically, after receiving the fusion track set returned by the cloud platform, the target prediction track of the target vehicle can be determined according to the fusion track of the target vehicle in the fusion track set, and the associated prediction track of the associated vehicle can be determined according to the fusion track of the associated vehicle in the fusion track set.

[0092] The target prediction track of the target vehicle can be understood as a track between the fusion track of the target vehicle and the initial position of the target vehicle, and can also be understood as a track of the target vehicle within a preset time period.

[0093] In an embodiment of the present specification, the target prediction track of the target vehicle can be a target prediction track at a current time. It can be understood that, since the target vehicle is in a driving process, the current position of the target vehicle at each time will change, and therefore there will be a deviation between the fusion track of the target vehicle obtained and the actual current position of the target vehicle. The target prediction track is used to compensate for the deviation. For example, the current position of the target vehicle at the 10th second is determined, and the fusion track of the target vehicle from the 1st second to the 10th second is obtained from the cloud platform according to the current position. At the same time of obtaining the fusion track, the target vehicle continues to drive. Due to the time delay of the communication link, the time of obtaining the fusion track can be the 12th second, for example. At this time, the track of the target vehicle between the 10th second and the 12th second cannot be obtained. The vehicle track processing method can determine the target prediction track of the target vehicle between the 10th second and the 12th second according to the obtained fusion track from the 1st second to the 10th second, or can also determine the target prediction track of the target vehicle between the 10th second and the 20th second.

[0094] Similarly, the associated prediction track of the associated vehicle can be understood as a track between the fusion track of the associated vehicle and the initial position of the associated vehicle, and can also be understood as a track of the associated vehicle within a preset time period.

[0095] Specifically, since the cloud platform determines the fusion track set according to the track acquisition range corresponding to the initial position, based on this, after receiving the fusion track set returned by the cloud platform, the fusion track of the target vehicle and the fusion track of the associated vehicle need to be determined in the fusion track set.

[0096] In an optional embodiment of the present specification, the initial position and the historical position of the target vehicle can be determined, and the historical trajectory of the target vehicle can be calculated according to the initial position and the historical position of the target vehicle. The historical trajectory and each fusion trajectory included in the fusion trajectory set are matched by using a preset matching algorithm. The fusion trajectory of the target vehicle is determined in the fusion trajectory set according to the matching result. Then, the fusion trajectories in the fusion trajectory set except for the fusion trajectory of the target vehicle are the fusion trajectories of the associated vehicles. The preset matching algorithm can be any algorithm for matching trajectories, such as a trajectory vector similarity algorithm, and the embodiments of the present specification do not limit this.

[0097] In a specific implementation, when determining the target prediction trajectory of the target vehicle, the first target prediction trajectory and the second target prediction trajectory can be determined in combination with the positioning of the target vehicle and the trajectory prediction model, so as to determine the target prediction trajectory, and the specific implementation manner is as follows:

[0098] The target prediction trajectory of the target vehicle is determined according to the fusion trajectory of the target vehicle, and the target prediction trajectory of the target vehicle includes:

[0099] The first target prediction trajectory of the target vehicle is determined according to the fusion trajectory of the target vehicle and the position at the current moment.

[0100] The fusion trajectory of the target vehicle is input into a trajectory prediction model to obtain the second target prediction trajectory of the target vehicle.

[0101] The target prediction trajectory of the target vehicle is determined according to the first target prediction trajectory and the second target prediction trajectory.

[0102] Specifically, the position of the target vehicle at the current moment can be determined, and the first target prediction trajectory of the target vehicle is determined according to the fusion trajectory of the target vehicle and the position at the current moment. The fusion trajectory of the target vehicle is processed by using a trajectory prediction model to obtain the second target prediction trajectory of the target vehicle output by the trajectory prediction model. The target prediction trajectory of the target vehicle is determined according to the first target prediction trajectory and the second target prediction trajectory.

[0103] In actual application, the trajectory prediction model can be understood as any model capable of predicting the trajectory of a vehicle, which can be trained according to a machine learning method and a deep learning method, and the trajectory prediction model can be a vehicle physical state and kinematics, dynamics model, etc. The embodiments of the present specification do not limit this.

[0104] For example, when the fusion trajectory of the target vehicle from the first second to the tenth second is obtained, it is determined that the position of the target vehicle at the twelfth second (i.e., the current time) is (p, q), where p is the longitude and q is the latitude. Then, the first target prediction trajectory of the target vehicle at the twelfth second can be determined according to the position and the fusion trajectory of the target vehicle from the first second to the tenth second, the second target prediction trajectory of the target vehicle at the twelfth second can be determined by using the trajectory prediction model, and the target prediction trajectory of the target vehicle at the twelfth second can be determined according to the first target prediction trajectory and the second target prediction trajectory. The target prediction trajectory at the twelfth second can include a trajectory from the tenth second to the twelfth second and a trajectory in a preset time period after the twelfth second.

[0105] In summary, the target prediction trajectory of the target vehicle is determined by combining the two methods, thereby ensuring the accuracy of trajectory prediction.

[0106] In specific implementation, the determination of the target prediction trajectory of the target vehicle according to the first target prediction trajectory and the second target prediction trajectory includes:

[0107] calculating a first trajectory deviation degree of the fusion trajectory of the target vehicle and the first target prediction trajectory, and a second trajectory deviation degree of the fusion trajectory of the target vehicle and the second target prediction trajectory;

[0108] determining the target prediction trajectory of the target vehicle according to a comparison result of the first trajectory deviation degree and the second trajectory deviation degree.

[0109] Specifically, when the target prediction trajectory of the target vehicle is determined according to the first target prediction trajectory and the second target prediction trajectory, the first trajectory deviation degree of the fusion trajectory of the target vehicle and the first target prediction trajectory can be calculated, the second trajectory deviation degree of the fusion trajectory of the target vehicle and the second target prediction trajectory can be calculated, and the first trajectory deviation degree and the second trajectory deviation degree can be compared. According to the comparison result, the trajectory with smaller trajectory deviation degree is taken as the target prediction trajectory.

[0110] Correspondingly, when the associated prediction trajectory of the associated vehicle is determined according to the fusion trajectory of the associated vehicle, the trajectory prediction model can also be used for determination, and the specific implementation manner is as follows:

[0111] The determination of the associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle includes:

[0112] inputting the fusion trajectory of the associated vehicle into the trajectory prediction model to obtain the associated prediction trajectory of the associated vehicle.

[0113] However, since the positioning unit included in the terminal device can only determine the position of the target vehicle, the position of the associated vehicle cannot be determined, so when determining the associated prediction track of the associated vehicle, the driving information of the associated vehicle can also be determined according to the fusion track of the associated vehicle, and the associated prediction track is determined according to the driving information, and the specific implementation manner is as follows:

[0114] The associated prediction track of the associated vehicle is determined according to the fusion track of the associated vehicle, including:

[0115] The driving information of the associated vehicle is determined according to the fusion track of the associated vehicle.

[0116] The associated prediction track of the associated vehicle is determined according to the driving information.

[0117] Specifically, the driving information such as the driving speed, driving position, and driving habit of the driver of the associated vehicle can be analyzed according to the fusion track of the associated vehicle, and the associated prediction track of the associated vehicle is predicted according to the driving information.

[0118] In addition, the trajectory deviation degree between the associated prediction track determined according to the two ways and the fusion track of the associated vehicle can also be compared in combination with the above two ways of determining the associated prediction track, and the associated prediction track is determined according to the comparison result, and the specific implementation manner is as follows:

[0119] The associated prediction track of the associated vehicle is determined according to the fusion track of the associated vehicle, including:

[0120] The fusion track of the associated vehicle is input into a trajectory prediction model to obtain a first associated prediction track of the associated vehicle.

[0121] The driving information of the associated vehicle is determined according to the fusion track of the associated vehicle.

[0122] The second associated prediction track of the associated vehicle is determined according to the driving information.

[0123] The third trajectory deviation degree between the fusion track of the associated vehicle and the first associated prediction track, and the fourth trajectory deviation degree between the fusion track of the associated vehicle and the second associated prediction track are calculated.

[0124] The associated prediction track of the associated vehicle is determined according to the comparison result of the third trajectory deviation degree and the fourth trajectory deviation degree.

[0125] Specifically, the first associated predicted trajectory can be determined by using the trajectory prediction model, the driving information of the associated vehicle can be determined by using the fusion trajectory of the associated vehicle, and the second associated predicted trajectory can be determined according to the driving information. The third trajectory deviation degree between the fusion trajectory of the associated vehicle and the first associated predicted trajectory is calculated, the fourth trajectory deviation degree between the fusion trajectory of the associated vehicle and the second associated predicted trajectory is calculated, the third trajectory deviation degree and the fourth trajectory deviation degree are compared, and the trajectory with smaller trajectory deviation degree is determined as the associated predicted trajectory according to the comparison result.

[0126] In summary, by using two ways to determine the associated predicted trajectory, the accuracy of the associated predicted trajectory is further ensured, thereby providing accurate data basis for subsequent determination of driving strategy or driving route.

[0127] In actual application, there can be multiple associated vehicles around the target vehicle. At this time, the fusion trajectory of each associated vehicle can be obtained from the cloud platform, and the associated predicted trajectory of each associated vehicle can be determined according to the fusion trajectory of each associated vehicle, and the specific implementation manner is as follows:

[0128] The associated vehicles are at least two;

[0129] Correspondingly, the associated predicted trajectory of the associated vehicle is determined according to the fusion trajectory of the associated vehicle, including:

[0130] The associated predicted trajectory of each associated vehicle is determined according to the fusion trajectory of each associated vehicle in the at least two associated vehicles.

[0131] Specifically, the process of determining the associated predicted trajectory of each associated vehicle is similar to the foregoing, which will not be repeated here.

[0132] In actual application, after the target predicted trajectory and the associated predicted trajectory are determined, the target predicted trajectory and the associated predicted trajectory can be displayed through the display interface of the terminal device, and route planning can also be performed according to the target predicted trajectory and the associated predicted trajectory, so as to determine a navigation route, and the specific implementation manner is as follows:

[0133] After the associated predicted trajectory of the associated vehicle is determined, the method further includes:

[0134] The target predicted trajectory and the associated predicted trajectory are rendered and displayed through the display interface,

[0135] According to the target predicted trajectory and the associated predicted trajectory, a navigation route of the target vehicle is determined.

[0136] Specifically, the target prediction trajectory and the associated prediction trajectory can be rendered and displayed through the display interface, route planning can be performed according to the target prediction trajectory and the associated prediction trajectory, the navigation route of the target vehicle can be determined, and the navigation route can be broadcast through the voice unit.

[0137] In addition, the target vehicle and the associated vehicle can also be rendered and displayed through the display interface, or online map rendering can be performed to improve the viewing experience of the driver.

[0138] In summary, through rendering and display on the display interface and planning of the navigation route, the driver can directly observe the road conditions on the display interface, ensuring safe driving in extreme weather. The technical development route of vehicle-road cooperation can integrate vehicles, roads, people, and real-time traffic information, collect data at the roadside, and push it to surrounding vehicles in real time through mobile communication technology, providing early risk warnings and further decision-making and control by vehicles. At the same time, the roadside can sense global vehicles and road conditions for active traffic control, such as notifying vehicles to change lanes in advance when an accident occurs, which can further reduce the rate of secondary accidents and improve vehicle traffic efficiency.

[0139] In actual applications, after determining the associated prediction trajectory of the associated vehicle, the method further includes:

[0140] In a case where the distance between the target vehicle and the associated vehicle meets a second preset distance threshold according to the target prediction trajectory and the associated prediction trajectory, generating an early warning information.

[0141] The second preset distance threshold can be understood as a distance threshold that is pre-set and in which the target vehicle and the associated vehicle have a risk of collision.

[0142] Based on this, the early warning information can be generated in a case where the distance between the target vehicle and the associated vehicle reaches a distance threshold in which the target vehicle and the associated vehicle have a risk of collision according to the target prediction trajectory and the associated prediction trajectory. In addition, the early warning information can be broadcast through the voice unit to remind the driver of the collision.

[0143] In actual applications, the distance between the target vehicle and the associated vehicle can be determined according to the positioning unit of the terminal device.

[0144] In summary, by monitoring the distance between the target vehicle and the associated vehicle and generating the early warning information in a case where the distance reaches the second preset distance threshold, the driver is reminded of the collision, the target vehicle is prevented from colliding with the associated vehicle during driving, and the driving safety of the target vehicle is ensured.

[0145] In addition, the roadside perception unit can also be used to perceive event information in the target area, such as a vehicle collision event, etc. And send the event information to the cloud platform, which can generate reminder information according to the event information and the current position carried in the received trajectory acquisition request, and send it to the terminal device.

[0146] In summary, the above method can obtain the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle (i.e. the vehicle around the target vehicle) associated with the target vehicle by obtaining the fusion trajectory set corresponding to the initial position from the cloud platform according to the initial position of the target vehicle. And due to the time delay of the communication link with the cloud platform, it is impossible to obtain real-time fusion trajectory. Based on this, the target prediction trajectory of the target vehicle and the associated prediction trajectory of the associated vehicle can be predicted according to the obtained fusion trajectory, and the time delay of the communication link is compensated by prediction, so that the target prediction trajectory and the associated prediction trajectory finally obtained have real-time and accuracy, so as to determine the motion trend of the surrounding vehicle in time and accurately, and further provide accurate data basis for subsequent determination of driving strategy or driving route. The driver or passenger can also search for POI points using the terminal device.

[0147] The following describes the vehicle trajectory processing method provided in the present specification in conjunction with the accompanying Figure 3 The vehicle trajectory processing method provided in the present specification is further described below with reference to the application of the vehicle trajectory processing method in path planning. Wherein, Figure 3 A process flow diagram of a vehicle trajectory processing method provided in an embodiment of the present specification is shown, which specifically includes the following steps.

[0148] Step 302: The cloud platform determines the initial fusion trajectory set of the regional vehicle according to the driving information of the regional vehicle in the target area collected by the roadside perception unit.

[0149] Specifically, the roadside perception unit can be deployed on both sides of the target area. The roadside perception unit can be used to collect the driving information of the regional vehicle driving in the target area, and send the driving information to the cloud platform. The cloud platform can calculate the fusion trajectory of the regional vehicle according to the received driving information of the regional vehicle, so as to obtain the initial fusion trajectory set of all vehicles in the target area.

[0150] For example, the target area is a highway from region A to region B, and regional vehicles 1, 2, 3, 4 and 5 travel on the highway. The roadside sensing unit deployed on both sides of the highway can collect the driving information of the regional vehicles 1, 2, 3, 4 and 5, and send it to the cloud platform. The cloud platform can calculate the fusion trajectory of the regional vehicle 1, the fusion trajectory of the regional vehicle 2, the fusion trajectory of the regional vehicle 3, the fusion trajectory of the regional vehicle 4 and the fusion trajectory of the regional vehicle 5 according to the driving information of the regional vehicles 1, 2, 3, 4 and 5. The initial fusion trajectory set of the regional vehicle includes the fusion trajectory of the regional vehicle 1, the fusion trajectory of the regional vehicle 2, the fusion trajectory of the regional vehicle 3, the fusion trajectory of the regional vehicle 4 and the fusion trajectory of the regional vehicle 5.

[0151] Step 304: The terminal device determines the initial position of the target vehicle, and determines the trajectory acquisition range according to the initial position and the first preset distance threshold.

[0152] Continuing with the above example, any one of the target vehicles 1 in the regional vehicle is deployed with a terminal device. The terminal device determines the initial position of the target vehicle 1, and determines the trajectory acquisition range according to the initial position and the first preset distance threshold. It can be understood that the other regional vehicles located in the trajectory acquisition range are the associated vehicles around the target vehicle 1.

[0153] Step 306: The terminal device sends a trajectory acquisition request carrying the trajectory acquisition range to the cloud platform.

[0154] Step 308: The cloud platform determines the to-be-acquired vehicles in the trajectory acquisition range, determines the fusion trajectory corresponding to the to-be-acquired vehicles in the initial fusion trajectory set of the regional vehicle, and determines the fusion trajectory corresponding to the to-be-acquired vehicles as the fusion trajectory set.

[0155] Continuing with the above example, the cloud platform can determine that the to-be-acquired vehicles in the trajectory acquisition range are the target vehicle 1, the regional vehicle 2 and the regional vehicle 3, so the regional vehicle 2 and the regional vehicle 3 are the associated vehicles around the target vehicle. The fusion trajectory of the regional vehicle 1, the fusion trajectory of the regional vehicle 2 and the fusion trajectory of the regional vehicle 3 can be obtained in the initial fusion trajectory set of the regional vehicle, and the fusion trajectories of the three regional vehicles are determined as the fusion trajectory set.

[0156] Step 310: The cloud platform sends the fusion trajectory set to the terminal device.

[0157] Step 312: The terminal device determines the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle associated with the target vehicle in the fusion trajectory set. According to the fusion trajectory of the target vehicle, the target prediction trajectory of the target vehicle is determined. According to the fusion trajectory of the associated vehicle, the associated prediction trajectory of the associated vehicle is determined.

[0158] With the above example, the terminal device can determine the fusion trajectory of the target vehicle 1 according to the initial position of the target vehicle in the received fusion trajectory set, so as to determine the fusion trajectory of the associated vehicle 2 and the fusion trajectory of the associated vehicle 3. And according to the fusion trajectory of the target vehicle 1, the target prediction trajectory of the target vehicle 1 is determined. According to the fusion trajectory of the associated vehicle 2, the associated prediction trajectory of the associated vehicle 2 is determined. According to the fusion trajectory of the associated vehicle 3, the associated prediction trajectory of the associated vehicle 3 is determined.

[0159] Step 314: The terminal device renders and displays the target prediction trajectory and the associated prediction trajectory through the display device, and determines the navigation route of the target vehicle according to the target prediction trajectory and the associated prediction trajectory.

[0160] In summary, the above method can obtain the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle (i.e. the vehicle around the target vehicle) associated with the target vehicle by obtaining the fusion trajectory set corresponding to the initial position from the cloud platform according to the initial position of the target vehicle. And due to the time delay of the communication link with the cloud platform, real-time fusion trajectory cannot be obtained. Based on this, the target prediction trajectory of the target vehicle and the associated prediction trajectory of the associated vehicle can be predicted according to the obtained fusion trajectory, and the time delay of the communication link is compensated through prediction, so that the finally obtained target prediction trajectory and associated prediction trajectory have real-time and accuracy, so as to timely and accurately determine the motion trend of the surrounding vehicle, and further provide accurate data basis for subsequent determination of driving strategy or driving route.

[0161] Corresponding to the above method embodiment, the present specification also provides a vehicle trajectory processing device embodiment, Figure 4 The structure schematic diagram of a vehicle trajectory processing device provided by an embodiment of the present specification is shown. As shown in the figure, Figure 4 The device comprises:

[0162] The first determination module 402 is configured to determine the initial position of the target vehicle;

[0163] The communication module 404 is configured to send a trajectory acquisition request carrying the initial position to the cloud platform, and receive the fusion trajectory set corresponding to the initial position returned by the cloud platform according to the trajectory acquisition request, wherein the fusion trajectory set comprises the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle associated with the target vehicle;

[0164] The second determination module 406 is configured to determine the target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle, and determine the associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle.

[0165] In an optional embodiment, the second determining module 406 is further configured to:

[0166] determine a first target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle and the position at the current time;

[0167] input the fusion trajectory of the target vehicle into a trajectory prediction model to obtain a second target prediction trajectory of the target vehicle;

[0168] determine a target prediction trajectory of the target vehicle according to the first target prediction trajectory and the second target prediction trajectory.

[0169] In an optional embodiment, the second determining module 406 is further configured to:

[0170] calculate a first trajectory deviation degree of the fusion trajectory of the target vehicle and the first target prediction trajectory, and a second trajectory deviation degree of the fusion trajectory of the target vehicle and the second target prediction trajectory;

[0171] determine a target prediction trajectory of the target vehicle according to a comparison result of the first trajectory deviation degree and the second trajectory deviation degree.

[0172] In an optional embodiment, the second determining module 406 is further configured to:

[0173] input the fusion trajectory of the associated vehicle into a trajectory prediction model to obtain an associated prediction trajectory of the associated vehicle.

[0174] In an optional embodiment, the second determining module 406 is further configured to:

[0175] determine driving information of the associated vehicle according to the fusion trajectory of the associated vehicle;

[0176] determine an associated prediction trajectory of the associated vehicle according to the driving information.

[0177] In an optional embodiment, the second determining module 406 is further configured to:

[0178] input the fusion trajectory of the associated vehicle into a trajectory prediction model to obtain a first associated prediction trajectory of the associated vehicle;

[0179] determine driving information of the associated vehicle according to the fusion trajectory of the associated vehicle;

[0180] determine a second associated prediction trajectory of the associated vehicle according to the driving information;

[0181] compute a third trajectory deviation degree of the fusion trajectory of the associated vehicle and the first associated predicted trajectory, and a fourth trajectory deviation degree of the fusion trajectory of the associated vehicle and the second associated predicted trajectory;

[0182] determine the associated predicted trajectory of the associated vehicle according to a comparison result of the third trajectory deviation degree and the fourth trajectory deviation degree.

[0183] In an optional embodiment, the first determining module 402 is further configured to:

[0184] determine a trajectory acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and an associated vehicle associated with the target vehicle;

[0185] Correspondingly, the communication module 404 is further configured to send a trajectory acquisition request carrying the trajectory acquisition range to a cloud platform, and receive a fusion trajectory set corresponding to the trajectory acquisition range returned by the cloud platform according to the trajectory acquisition request.

[0186] In an optional embodiment, the fusion trajectory of the target vehicle is obtained by splicing initial trajectories of the target vehicle in the acquisition ranges of each shooting positioning device included in the roadside perception unit, and the initial trajectories of the target vehicle in the acquisition ranges of each shooting positioning device included in the roadside perception unit are calculated according to the driving information of the target vehicle sent by each shooting positioning device.

[0187] In an optional embodiment, the associated vehicle is at least two;

[0188] The second determining module 406 is further configured to:

[0189] determine the associated predicted trajectory of each associated vehicle according to the fusion trajectory of each associated vehicle among the at least two associated vehicles.

[0190] In an optional embodiment, the apparatus further includes a display module configured to:

[0191] render and display the target predicted trajectory and the associated predicted trajectory through a display interface,

[0192] determine a navigation route of the target vehicle according to the target predicted trajectory and the associated predicted trajectory.

[0193] In an optional embodiment, the apparatus further includes a generation module configured to:

[0194] In a case where the distance between the target vehicle and the associated vehicle meets a second preset distance threshold according to the target prediction trajectory and the associated prediction trajectory, a warning information is generated.

[0195] In summary, the device can obtain the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle associated with the target vehicle (i.e., the vehicle around the target vehicle) by obtaining the fusion trajectory set corresponding to the initial position of the target vehicle from the cloud platform according to the initial position of the target vehicle. Due to the time delay of the communication link with the cloud platform, real-time fusion trajectories cannot be obtained. Based on this, the target prediction trajectory of the target vehicle and the associated prediction trajectory of the associated vehicle can be predicted according to the obtained fusion trajectory. The time delay of the communication link is compensated through prediction, so that the finally obtained target prediction trajectory and associated prediction trajectory have real-time and accuracy, so that the motion trend of the surrounding vehicle can be determined in time and accurately, and accurate data basis is further provided for subsequent determination of driving strategy or driving route.

[0196] The above is a schematic scheme of a vehicle trajectory processing device according to an embodiment. It should be noted that the technical scheme of the vehicle trajectory processing device belongs to the same concept as the technical scheme of the vehicle trajectory processing method described above. The details of the technical scheme of the vehicle trajectory processing device that are not described in detail can be referred to the description of the technical scheme of the vehicle trajectory processing method.

[0197] Referring to Figure 5 , Figure 5 A flowchart of another vehicle trajectory processing method according to an embodiment of the present specification is shown, which is applied to a cloud platform and specifically includes the following steps.

[0198] Step 502: receiving a trajectory acquisition request sent by a terminal device, wherein the trajectory acquisition request carries an initial position of a target vehicle;

[0199] Step 504: determining a trajectory acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and an associated vehicle associated with the target vehicle;

[0200] Step 506: determining a fusion trajectory set corresponding to the initial position according to the trajectory acquisition range, wherein the fusion trajectory set includes a fusion trajectory of the target vehicle and a fusion trajectory of the associated vehicle associated with the target vehicle;

[0201] Step 508: sending the fusion trajectory set to the terminal device.

[0202] In specific implementation, before the fusion trajectory set corresponding to the initial position is determined according to the trajectory acquisition range, the following steps are further included:

[0203] The receiving roadside perception unit comprises driving information of regional vehicles collected by each shooting positioning device, wherein the regional vehicles are vehicles driving in a target region, the regional vehicles comprise the target vehicle, the roadside perception unit is deployed in the target region, and the roadside perception unit comprises at least two shooting positioning devices.

[0204] According to the driving information of the regional vehicles collected by each shooting positioning device, an initial trajectory of the regional vehicles in the collection range of each shooting positioning device is calculated.

[0205] The initial trajectories of the regional vehicles in the collection range of each shooting positioning device are spliced to obtain an initial fusion trajectory set of the regional vehicles.

[0206] Correspondingly, the fusion trajectory set corresponding to the initial position is determined according to the trajectory acquisition range, comprising:

[0207] Determine the vehicle to be acquired in the trajectory acquisition range.

[0208] In the initial fusion trajectory set of the regional vehicles, determine the fusion trajectory corresponding to the vehicle to be acquired.

[0209] The fusion trajectory corresponding to the vehicle to be acquired is determined as the fusion trajectory set corresponding to the initial position.

[0210] In summary, the above method can obtain the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle (i.e. the vehicle around the target vehicle) associated with the target vehicle by acquiring the fusion trajectory set corresponding to the initial position from the cloud platform according to the initial position of the target vehicle. And due to the time delay of the communication link with the cloud platform, real-time fusion trajectory cannot be obtained. Based on this, the target prediction trajectory of the target vehicle and the associated prediction trajectory of the associated vehicle can be predicted according to the obtained fusion trajectory, and the time delay of the communication link is compensated by prediction, so that the target prediction trajectory and the associated prediction trajectory finally obtained have real-time and accuracy, so that the motion trend of the surrounding vehicle can be determined in time and accurately, and further accurate data basis is provided for subsequent determination of driving strategy or driving route.

[0211] Corresponding to the above method embodiment, the present specification also provides a vehicle trajectory processing device embodiment, Figure 6 The structure schematic diagram of another vehicle trajectory processing device provided by an embodiment of the present specification is shown. As shown in the figure, Figure 6 The device comprises:

[0212] The receiving module 602 is configured to receive a trajectory acquisition request sent by a terminal device, wherein the trajectory acquisition request carries an initial position of a target vehicle;

[0213] The first determining module 604 is configured to determine a trajectory acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and an associated vehicle associated with the target vehicle;

[0214] The second determining module 606 is configured to determine a fusion trajectory set corresponding to the initial position according to the trajectory acquisition range, wherein the fusion trajectory set includes a fusion trajectory of the target vehicle and a fusion trajectory of the associated vehicle associated with the target vehicle;

[0215] The sending module 608 is configured to send the fusion trajectory set to the terminal device.

[0216] In an optional embodiment, the apparatus further includes a calculating module configured to:

[0217] receive driving information of regional vehicles collected by each shooting positioning device included in a roadside perception unit, wherein the regional vehicles are vehicles driving in a target region, the regional vehicles include the target vehicle, the roadside perception unit is deployed in the target region, and the roadside perception unit includes at least two shooting positioning devices;

[0218] calculate initial trajectories of the regional vehicles in a collection range of each shooting positioning device according to the driving information of the regional vehicles collected by each shooting positioning device;

[0219] splice the initial trajectories of the regional vehicles in the collection range of each shooting positioning device to obtain an initial fusion trajectory set of the regional vehicles.

[0220] In an optional embodiment, the second determining module 606 is further configured to:

[0221] determine a to-be-acquired vehicle in the trajectory acquisition range;

[0222] determine a fusion trajectory corresponding to the to-be-acquired vehicle in the initial fusion trajectory set of the regional vehicles;

[0223] determine the fusion trajectory corresponding to the to-be-acquired vehicle as the fusion trajectory set corresponding to the initial position.

[0224] In summary, the device obtains the fusion track of the target vehicle and the fusion track of the associated vehicle (i.e., the vehicle around the target vehicle) associated with the target vehicle by obtaining the fusion track set corresponding to the initial position of the target vehicle from the cloud platform according to the initial position of the target vehicle. Due to the time delay of the communication link between the cloud platform, the real-time fusion track cannot be obtained. Based on this, the target prediction track of the target vehicle and the associated prediction track of the associated vehicle can be predicted according to the obtained fusion track. The time delay of the communication link is compensated by prediction, so that the target prediction track and the associated prediction track finally obtained have real-time and accuracy, so that the motion trend of the surrounding vehicle can be determined in time and accurately, and accurate data basis is further provided for subsequent determination of the driving strategy or the driving route.

[0225] Referring to Figure 7 , Figure 7 A flowchart of a third vehicle track processing method according to an embodiment of the present specification is shown, which is applied to a vehicle track processing system including a terminal device and a cloud platform, and specifically includes the following steps.

[0226] Step 702: The terminal device determines the initial position of the target vehicle and sends a track acquisition request carrying the initial position to the cloud platform.

[0227] Step 704: The cloud platform determines a track acquisition range according to the initial position and a first preset distance threshold, determines a fusion track set corresponding to the initial position according to the track acquisition range, and sends the fusion track set to the terminal device, wherein the fusion track set includes the fusion track of the target vehicle and the fusion track of the associated vehicle associated with the target vehicle.

[0228] Step 706: The terminal device determines the target prediction track of the target vehicle according to the fusion track of the target vehicle, and determines the associated prediction track of the associated vehicle according to the fusion track of the associated vehicle.

[0229] Corresponding to the above method embodiment, the present specification also provides a vehicle track processing system embodiment, Figure 8 A structural schematic diagram of a vehicle track processing system according to an embodiment of the present specification is shown. As Figure 8 shown, the system 800 includes a terminal device 802 and a cloud platform 804, wherein

[0230] The terminal device 802 is configured to determine the initial position of the target vehicle and send a track acquisition request carrying the initial position to the cloud platform.

[0231] The cloud platform 804 is configured to determine a trajectory acquisition range according to the initial position and a first preset distance threshold, determine a fusion trajectory set corresponding to the initial position according to the trajectory acquisition range, and send the fusion trajectory set to the terminal device, wherein the fusion trajectory set includes a fusion trajectory of the target vehicle and fusion trajectories of associated vehicles associated with the target vehicle.

[0232] The terminal device 802 is further configured to determine a target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle, and determine an associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle.

[0233] In summary, the system described above can obtain the fusion trajectory of the target vehicle and the fusion trajectories of the associated vehicles (i.e., vehicles around the target vehicle) associated with the target vehicle by obtaining the fusion trajectory set corresponding to the initial position of the target vehicle from the cloud platform according to the initial position of the target vehicle. Due to the time delay of the communication link with the cloud platform, real-time fusion trajectories cannot be obtained. Based on this, the target prediction trajectory of the target vehicle and the associated prediction trajectory of the associated vehicle can be predicted according to the obtained fusion trajectories, and the time delay of the communication link is compensated by prediction, so that the target prediction trajectory and the associated prediction trajectory finally obtained have real-time and accuracy, so that the motion trend of the surrounding vehicles can be determined in time and accurately, and accurate data basis is further provided for subsequent determination of driving strategy or driving route.

[0234] Figure 9 A structural block diagram of a computing device 900 according to one embodiment of the present specification is shown. The components of the computing device 900 include but are not limited to a memory 910 and a processor 920. The processor 920 is connected to the memory 910 through a bus 930, and a database 950 is used to save data.

[0235] The computing device 900 also includes an access device 940 that enables the computing device 900 to communicate via one or more networks 960. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or combinations of such networks, such as the Internet. The access device 940 can include one or more of any type of network interface (for example, a network interface card (NIC)) such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, or the like.

[0236] In one embodiment of the present application, the above-mentioned components of the computing device 900, as well as other components not shown in FIG. 9, can be connected to each other by a bus. It should be understood that Figure 9 the components of the computing device 900 can be connected to each other by a bus. It should be understood that Figure 9 The computing device structure diagram shown is merely for the purpose of example, and is not a limitation on the scope of the present application. Those skilled in the art can add or replace other components as needed.

[0237] The computing device 900 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 900 can also be a mobile or stationary server.

[0238] The processor 920 is configured to execute computer-executable instructions, which, when executed by the processor, implement the steps of the vehicle trajectory processing method described above.

[0239] The above is a schematic scheme of the computing device of the embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the vehicle trajectory processing method described above belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can be referred to the description of the technical scheme of the vehicle trajectory processing method.

[0240] An embodiment of the present specification further provides a computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are executed by a processor to implement the steps of the vehicle trajectory processing method.

[0241] The above is a schematic scheme of the computer readable storage medium of the embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the vehicle trajectory processing method described above belong to the same concept, and the details of the technical scheme of the storage medium that are not described in detail can be referred to the description of the technical scheme of the vehicle trajectory processing method.

[0242] An embodiment of the present specification further provides a computer program, and when the computer program is executed in a computer, the computer program causes the computer to execute the steps of the vehicle trajectory processing method.

[0243] The above is a schematic scheme of the computer program of the embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the vehicle trajectory processing method described above belong to the same concept, and the details of the technical scheme of the computer program that are not described in detail can be referred to the description of the technical scheme of the vehicle trajectory processing method.

[0244] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than the order in which they are recited and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0245] The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, software distribution medium, etc. It should be noted that the computer readable medium can include appropriate additions or deletions according to the requirements of patent practice, for example, according to the patent practice in some regions, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0246] It should be noted that for the foregoing method embodiments, in order to facilitate description, they are all expressed as a combination of a series of actions, but those skilled in the art should know that the embodiments of the present specification are not limited by the order of the described actions, because according to the embodiments of the present specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of the present specification.

[0247] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0248] The preferred embodiments of the present specification disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details and limit the invention to the specific embodiments described. Obviously, according to the content of the embodiments of the present specification, many modifications and changes can be made. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of the present specification, so that those skilled in the art can well understand and use the present specification. The present specification is limited by the claims and their entire scope and equivalents.

Claims

1. A vehicle trajectory processing method applied to a terminal device deployed on a target vehicle, comprising: determining an initial position of the target vehicle; sending a trajectory acquisition request carrying the initial position to a cloud platform, and receiving a fusion trajectory set corresponding to the initial position returned by the cloud platform according to the trajectory acquisition request, wherein the fusion trajectory set comprises a fusion trajectory of the target vehicle and a fusion trajectory of an associated vehicle associated with the target vehicle; determining a first target predicted trajectory of the target vehicle according to the fusion trajectory of the target vehicle and a current position; inputting the fusion trajectory of the target vehicle into a trajectory prediction model to obtain a second target predicted trajectory of the target vehicle; calculating a first trajectory deviation degree of the fusion trajectory of the target vehicle and the first target predicted trajectory, and a second trajectory deviation degree of the fusion trajectory of the target vehicle and the second target predicted trajectory; determining a target predicted trajectory of the target vehicle according to a comparison result of the first trajectory deviation degree and the second trajectory deviation degree, and determining an associated predicted trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle. 2.The method of claim 1, wherein determining the associated predicted trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle comprises: inputting the fusion trajectory of the associated vehicle into a trajectory prediction model to obtain the associated predicted trajectory of the associated vehicle. 3.The method of claim 1, wherein determining the associated predicted trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle comprises: determining driving information of the associated vehicle according to the fusion trajectory of the associated vehicle; determining the associated predicted trajectory of the associated vehicle according to the driving information. 4.The method of claim 1, wherein determining the associated predicted trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle comprises: inputting the fusion trajectory of the associated vehicle into a trajectory prediction model to obtain a first associated predicted trajectory of the associated vehicle; determining driving information of the associated vehicle according to the fusion trajectory of the associated vehicle; determining a second associated predicted trajectory of the associated vehicle according to the driving information; calculating a third trajectory deviation degree of the fusion trajectory of the associated vehicle and the first associated predicted trajectory, and a fourth trajectory deviation degree of the fusion trajectory of the associated vehicle and the second associated predicted trajectory; determining the associated predicted trajectory of the associated vehicle according to a comparison result of the third trajectory deviation degree and the fourth trajectory deviation degree. 5.The method of claim 1, wherein after determining the initial position of the target vehicle, the method further comprises: determining a trajectory acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and the associated vehicle associated with the target vehicle; sending a trajectory acquisition request carrying the trajectory acquisition range to a cloud platform, and receiving a fusion trajectory set corresponding to the trajectory acquisition range returned by the cloud platform according to the trajectory acquisition request. 6.The method of claim 1, wherein the fused trajectory of the target vehicle is spliced according to initial trajectories of the target vehicle within a capture range of each shooting positioning device included in a roadside perception unit, and the initial trajectories of the target vehicle within the capture range of each shooting positioning device included in the roadside perception unit are calculated according to driving information of the target vehicle sent by each shooting positioning device. 7.The method of claim 1, wherein the associated vehicles are at least two. Accordingly, the determining the associated prediction trajectory of the associated vehicles according to the fused trajectories of the associated vehicles comprises: determining the associated prediction trajectory of each associated vehicle according to the fused trajectory of each associated vehicle among the at least two associated vehicles. 8.The method of claim 1, further comprising, after the determining the associated prediction trajectory of the associated vehicles: generating a warning information in a case that a distance between the target vehicle and the associated vehicles determined according to the target prediction trajectory and the associated prediction trajectory satisfies a second preset distance threshold. 9.A vehicle trajectory processing method applied to a cloud platform, comprising: receiving a trajectory acquisition request sent by a terminal device, wherein the trajectory acquisition request carries an initial position of a target vehicle; determining a trajectory acquisition range according to the initial position and a first preset distance threshold, wherein the first preset distance threshold is a distance threshold between the target vehicle and associated vehicles associated with the target vehicle; determining a fused trajectory set corresponding to the initial position according to the trajectory acquisition range, wherein the fused trajectory set includes a fused trajectory of the target vehicle and fused trajectories of the associated vehicles associated with the target vehicle; sending the fused trajectory set to the terminal device, wherein the terminal device is configured to determine a first target prediction trajectory of the target vehicle according to the fused trajectory of the target vehicle and a current position, input the fused trajectory of the target vehicle into a trajectory prediction model to obtain a second target prediction trajectory of the target vehicle, calculate a first trajectory deviation degree of the fused trajectory of the target vehicle and the first target prediction trajectory and a second trajectory deviation degree of the fused trajectory of the target vehicle and the second target prediction trajectory, and determine a target prediction trajectory of the target vehicle according to a comparison result of the first trajectory deviation degree and the second trajectory deviation degree. 10.The method of claim 9, further comprising, before the determining the fused trajectory set corresponding to the initial position according to the trajectory acquisition range: receiving driving information of regional vehicles collected by each shooting positioning device included in a roadside perception unit, wherein the regional vehicles are vehicles driving in a target region, the regional vehicles include the target vehicle, the roadside perception unit is deployed in the target region, and the roadside perception unit includes at least two shooting positioning devices; calculating initial trajectories of the regional vehicles within a capture range of each shooting positioning device according to the driving information of the regional vehicles collected by each shooting positioning device. Splice the initial trajectories of the regional vehicle in the collection range of each shooting positioning device to obtain an initial fusion trajectory set of the regional vehicle; Correspondingly, the fusion trajectory set corresponding to the initial position is determined according to the trajectory acquisition range, including: Determine the vehicle to be acquired in the trajectory acquisition range; Determine the fusion trajectory corresponding to the vehicle to be acquired in the initial fusion trajectory set of the regional vehicle; Determine the fusion trajectory corresponding to the vehicle to be acquired in the initial fusion trajectory set of the regional vehicle.

11. A vehicle trajectory processing method applied to a vehicle trajectory processing system, the vehicle trajectory processing system comprising a terminal device and a cloud platform, the method comprising: The terminal device determines the initial position of the target vehicle and sends a trajectory acquisition request carrying the initial position to the cloud platform; The cloud platform determines the trajectory acquisition range according to the initial position and a first preset distance threshold, determines the fusion trajectory set corresponding to the initial position according to the trajectory acquisition range, and sends the fusion trajectory set to the terminal device, wherein the fusion trajectory set comprises the fusion trajectory of the target vehicle and the fusion trajectory of the associated vehicle associated with the target vehicle; The terminal device determines the first target prediction trajectory of the target vehicle according to the fusion trajectory of the target vehicle and the position at the current time, inputs the fusion trajectory of the target vehicle into a trajectory prediction model to obtain the second target prediction trajectory of the target vehicle, calculates the first trajectory deviation degree of the fusion trajectory of the target vehicle and the first target prediction trajectory and the second trajectory deviation degree of the fusion trajectory of the target vehicle and the second target prediction trajectory, determines the target prediction trajectory of the target vehicle according to the comparison result of the first trajectory deviation degree and the second trajectory deviation degree, and determines the associated prediction trajectory of the associated vehicle according to the fusion trajectory of the associated vehicle.

Images