Trajectory prediction method and device, vehicle and readable storage medium

Abstract

The invention provides a trajectory prediction method and device, a vehicle and a readable storage medium, and relates to the technical field of unmanned driving. The method is applied to vehicle-mounted equipment of a first vehicle, a second vehicle runs around the first vehicle, and the method comprises the steps that position information of the second vehicle is determined; according to the position information of the second vehicle, the driving frequency of a historical vehicle in a lane where the second vehicle is currently located along each driving track is obtained; and predicting a driving track of the second vehicle by using a deep learning algorithm and the frequency. According to the technical scheme provided by the invention, the accuracy of predicting the driving track of the second vehicle by the first vehicle can be improved, and meanwhile, the driving safety of the first vehicle is also improved.

Description

Technical Field

[0001] The present application relates to the field of unmanned driving technology, and in particular to a trajectory prediction method, device, vehicle and readable storage medium. Background Art

[0002] Autonomous driving technology is developing rapidly in my country. Trajectory prediction technology is one of the key technologies of autonomous driving. It can predict the driving trajectory of surrounding vehicles so that autonomous vehicles can take appropriate driving actions according to the prediction results to avoid traffic accidents. For example, when it is predicted that the target vehicle needs to change lanes during the maneuver, the autonomous vehicle will slow down and give way.

[0003] At present, vehicles usually predict the target vehicle's driving trajectory based on the target vehicle's road structure information, location information, and high-precision map information. However, this method is prone to large errors between the predicted driving trajectory and the target vehicle's actual driving trajectory, thereby reducing the safety of autonomous driving vehicles. Summary of the invention

[0004] The embodiments of the present application provide a trajectory prediction method, device, vehicle and readable storage medium, which are used to solve the problem in the prior art that there is a large error between the predicted driving trajectory and the actual driving trajectory of the target vehicle.

[0005] In order to solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0006] First aspect: An embodiment of the present application provides a trajectory prediction method, which is applied to an on-board device of a first vehicle, where a second vehicle is traveling around the first vehicle. The method includes: determining the position information of the second vehicle; obtaining, based on the position information of the second vehicle, the frequency of historical vehicles traveling along various driving trajectories in a lane where the second vehicle is currently located; and predicting the driving trajectory of the second vehicle using a deep learning algorithm and frequency.

[0007] In some embodiments, a deep learning algorithm and frequency are used to predict the driving trajectory of the second vehicle, including: using a deep learning algorithm to determine a first probability that the second vehicle travels along each driving trajectory; multiplying the first probability of each driving trajectory by the corresponding frequency to obtain a second probability of each trajectory; and using the driving trajectory corresponding to the largest second probability as the predicted result of the driving trajectory of the second vehicle.

[0008] In some embodiments, a deep learning algorithm is used to determine a first probability that the second vehicle travels along each driving trajectory, including: obtaining prediction-related information, the prediction-related information including the second vehicle's current driving information, historical driving information, road structure information, map information, and location information; using a deep learning algorithm to determine a first probability that the second vehicle travels along each driving trajectory based on the prediction-related information.

[0009] In some embodiments, the driving information includes: speed information, acceleration information, and heading angle information.

[0010] In some embodiments, determining the position information of the second vehicle includes: determining the position information of the first vehicle; determining the relative position relationship between the second vehicle and the first vehicle; and determining the position information of the second vehicle based on the position information of the first vehicle and the relative position relationship.

[0011] In some embodiments, based on the position information of the second vehicle, the frequency of historical vehicles traveling along various trajectories in the lane where the second vehicle is currently located is obtained, including: sending the position information of the second vehicle to a server; and receiving the frequency of historical vehicles traveling along various trajectories in the lane where the second vehicle is currently located returned by the server.

[0012] In some embodiments, the frequency of historical vehicles in the lane where the second vehicle is currently located traveling along various trajectories is determined based on a preset time period and the driving trajectories of historical vehicles in the lane where the second vehicle is currently located.

[0013] In a second aspect, an embodiment of the present application provides a trajectory prediction device, which is applied to an on-board device of a first vehicle, where a second vehicle is traveling around the first vehicle. The device includes: a determination module: used to determine the position information of the second vehicle; an acquisition module: used to obtain the frequency of historical vehicles traveling along various driving trajectories in the lane where the second vehicle is currently located according to the position information of the second vehicle; a prediction module: used to predict the driving trajectory of the second vehicle using a deep learning algorithm and frequency.

[0014] In a third aspect, an embodiment of the present application provides a vehicle, comprising an on-board device, wherein the on-board device is configured to execute the trajectory prediction method as described in the first aspect above.

[0015] In a fourth aspect, an embodiment of the present application provides a chip, comprising at least one processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the trajectory prediction method in the first aspect described above.

[0016] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed on a first vehicle, the first vehicle executes the trajectory prediction method in the first aspect described above.

[0017] In a sixth aspect, an embodiment of the present application provides a computer program product, which, when executed on a first vehicle, enables a mobile device to execute the steps of the method described in the first aspect.

[0018] The trajectory prediction method provided by the present application is that when predicting the driving trajectory of the second vehicle, the first vehicle will obtain the frequency of historical vehicles traveling along various driving trajectories in the lane where the second vehicle is currently located according to the determined position information of the second vehicle, so that the first vehicle can predict the driving trajectory of the second vehicle through the deep learning algorithm and the obtained frequency. Since the prediction result fully considers the frequency of historical vehicles traveling along various driving trajectories in the current lane of the second vehicle, the accuracy of the first vehicle's prediction of the driving trajectory of the second vehicle is improved, and the safety of the first vehicle's driving is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 It is a schematic diagram of an application scenario of the trajectory prediction method provided in the application embodiment;

[0021] Figure 2 This is a schematic diagram of the process of the trajectory prediction method provided in the embodiment of the present application. Figure 1 ;

[0022] Figure 3 is a schematic diagram of the frequency of historical vehicles traveling along various trajectories in the second lane provided by an embodiment of the present application;

[0023] Figure 4 This is a schematic diagram of the process of the trajectory prediction method provided in the embodiment of the present application. Figure 2 ;

[0024] Figure 5 is a schematic diagram of the structure of a trajectory prediction device provided in an embodiment of the present application;

[0025] Figure 6 It is a schematic diagram of the structure of the chip provided in the embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. And the terms used in this specification of the application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of the application and the appended claims, unless the context clearly indicates otherwise, the singular forms of "one", "an" and "the" are intended to include plural forms. The terms "first", "second", "third", etc. are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0028] Autonomous driving, also known as unmanned driving, computer driving or wheeled mobile robots, is a cutting-edge technology that relies on computers and artificial intelligence technology to complete complete, safe and effective driving without human control. Autonomous driving vehicles rely on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to work together, allowing computers to automatically and safely operate motor vehicles without any active human operation.

[0029] Among them, trajectory prediction technology is one of the key technologies for autonomous driving, which can predict the driving trajectory of surrounding vehicles so that the autonomous driving vehicle can take appropriate driving behavior according to the prediction results to avoid traffic accidents. For example, when it is predicted that the target vehicle needs to change lanes during the maneuver, the autonomous driving vehicle will slow down and give way. At present, vehicles usually predict the driving trajectory of the target vehicle based on the road structure information, location information, and high-precision map information where the target vehicle is located. However, this method is prone to large errors between the predicted driving trajectory and the actual driving trajectory of the target vehicle, thereby reducing the safety of the autonomous driving vehicle.

[0030] To this end, an embodiment of the present application provides a trajectory prediction method that can improve the accuracy of predicting the target vehicle's driving trajectory, thereby improving the safety of autonomous driving vehicles.

[0031] It should be noted that the trajectory prediction method provided in the embodiment of the present application is applied to the on-board equipment in the first vehicle. The first vehicle may be an autonomous driving vehicle, a non-autonomous driving vehicle, or a combination of autonomous / non-autonomous driving vehicles. The embodiment of the present application does not limit the specific type and function of the first vehicle.

[0032] Figure 1 is a schematic diagram of an application scenario of the trajectory prediction method provided in the embodiment of the present application, see Figure 1 As shown, a first vehicle is traveling in a first lane, and a plurality of second vehicles are traveling around the first vehicle. The plurality of second vehicles may be traveling in the same lane as the first vehicle, or in a second lane and a third lane in the same direction as the first lane. Figure 1 As shown, a second vehicle is traveling in the first lane, the second lane, and the third lane. The lane in the opposite direction of the first lane is called the opposite lane. It should be noted that in the embodiment of the present application, the first, second, and third limited lanes are used to distinguish different lanes, and the relative positions of the first lane, the second lane, and the third lane are not restricted in this embodiment.

[0033] In the embodiments of the present application, the attributes of the lane line generally include line type and color, wherein the line type of the lane line generally includes dashed line and solid line, the color of the lane line generally includes yellow and white, and the number of lines in each lane line generally includes one or two. Figure 1 As shown in the figure, the two yellow lines in the middle of the road are the central double yellow lines, which are used to separate lanes in different directions. The white dotted lines in the road are used to separate different lanes in the same direction.

[0034] It is understandable that during the driving process, the first vehicle needs to predict the driving trajectory of the surrounding second vehicle so that it can take appropriate driving behavior according to the prediction result to avoid traffic accidents and improve its own driving safety.

[0035] The trajectory prediction method provided by the embodiment of the present application is exemplarily described below in conjunction with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the solution of the present application and are not used to limit the present application.

[0036] Figure 2 This is a schematic diagram of the process of the trajectory prediction method provided in the embodiment of the present application. Figure 1 , the method specifically comprises the following steps:

[0037] S210: Determine the position information of the second vehicle.

[0038] In some embodiments, the first vehicle first determines its own location information, and then determines the location information of the second vehicle based on its own location information.

[0039] It should be noted that the first vehicle may determine its own position information through a global navigation satellite system (GNSS), a real-time kinematic carrier phase differential technology (RTK), or an inertial navigation positioning system (INS), etc., and the embodiments of the present application do not limit this. It is understandable that the position information may also be referred to as the latitude and longitude information of the first vehicle.

[0040] Among them, the first vehicle determines the position information of the second vehicle based on its own position information. Specifically, the first vehicle can determine the relative position relationship between the second vehicle and itself based on the position information of the second vehicle in its own vehicle coordinate system and its own position information, and then determine the position information of the second vehicle based on the relative position relationship and its own position information, that is, the latitude and longitude information of the second vehicle.

[0041] S220: Obtain, based on the position information of the second vehicle, the frequency of historical vehicles traveling along each driving trajectory in the lane where the second vehicle is currently located.

[0042] In some embodiments, after the first vehicle determines the position information of the second vehicle, it can send the position information of the second vehicle to the server, so that the server sends the frequency of historical vehicles traveling along various trajectories in the lane where the second vehicle is currently located to the first vehicle based on the position information.

[0043] For example, when the first vehicle Figure 1 After the position information of the second vehicle in the second lane is sent to the server, the frequency of historical vehicles traveling along each trajectory in the second lane returned by the server will be received.

[0044] Among them, the frequency of historical vehicles in the second lane traveling along various trajectories can be determined by the server based on a preset time period and the driving trajectories of historical vehicles in the second lane. The various driving trajectories can be understood as historical vehicles turning left at the intersection, turning right at the intersection, and maintaining straight driving in the second lane; accordingly, the frequency of historical vehicles in the second lane traveling along various trajectories can be understood as the frequency of vehicles traveling in the second lane turning left at the intersection, turning right at the intersection, and maintaining straight driving within the preset time period.

[0045] It should be noted that the preset time period may be in units of days, months, or years, etc., and this embodiment of the present application does not limit this. Figure 3 is a schematic diagram of the frequency of historical vehicles traveling along various trajectories in the second lane provided by an embodiment of the present application, Figure 3It can be seen that the preset time period is in months, A represents the historical vehicles in the second lane turning left at the intersection, B represents the historical vehicles in the second lane driving straight, and C represents the historical vehicles in the second lane turning right at the intersection. Among them, in January, the frequency of historical vehicles in the second lane turning left at the intersection is A 1 , the frequency of maintaining straight-line driving is B 1 and the frequency of right turns at the intersection is C 1 In February, the frequency of vehicles turning left at the intersection in the second lane was A 2 , the frequency of maintaining straight-line driving is B 2 and the frequency of right turns at the intersection is C3; in March, the frequency of left turns at the intersection by historical vehicles in the second lane is A 3 , the frequency of maintaining straight-line driving is B 3 and the frequency of right turns at the intersection is C 3 .

[0046] S230: Predicting the driving trajectory of the second vehicle using a deep learning algorithm and frequency.

[0047] It can be understood that the deep learning algorithm and the frequencies determined in the above embodiments are used to determine the probabilistic driving prediction results of straight going, left turning and right turning, so that the first vehicle can determine the final driving trajectory of the second vehicle based on each probabilistic driving trajectory.

[0048] In the embodiments of the present application, Figure 4 As shown, in step S230, the deep learning algorithm and frequency are used to predict the driving trajectory of the second vehicle, which specifically includes the following steps:

[0049] S231: Determine a first probability that the second vehicle travels along each driving trajectory using a deep learning algorithm.

[0050] It should be noted that the first vehicle uses a deep learning algorithm to determine the first probability that the second vehicle travels along each driving trajectory as follows: the first vehicle can first obtain prediction-related information about the second vehicle, and the prediction-related information includes the second vehicle’s current driving information, historical driving information, road structure information, map information, and location information.

[0051] The driving information may include the speed information, acceleration information and heading angle information of the second vehicle; the road structure information may include traffic signal signs, road driving rules and the spatial position of static obstacles on the road. After the first vehicle obtains the above-mentioned prediction-related information about the second vehicle, it uses a deep learning algorithm combined with the prediction-related information to determine the first probability that the second vehicle travels along each driving trajectory.

[0052] S232: Multiply the first probability of each driving trajectory by the corresponding frequency to obtain the second probability of each trajectory.

[0053] For example, the first vehicle determines that the first probability that the second vehicle in the second lane turns left at the intersection is A 4 %, the first probability of straight-line driving is B 4 % and the first probability of turning right at the intersection is C 4 %.

[0054] Taking January as an example, Figure 3 It can be seen that the frequency of historical vehicles turning left at the intersection in the second lane in January is A 1 The frequency of straight-line driving is B 1 and the frequency of right turns at the intersection is C 1 Therefore, A 4 %、B 4 % and C 4 % respectively with the corresponding A 1 , B 1 and C 1 Multiplication (A 4 %×A 1 =A%,B 4 %×B 1 =B%,C 3 %×C 1 =C%), and obtain the second probability of each trajectory, namely A%, B% and C%.

[0055] S233: Taking the driving trajectory corresponding to the largest second probability as the prediction result of the driving trajectory of the second vehicle.

[0056] Exemplarily, when A% in the second probability of the above step S232 is the maximum probability, the first vehicle will predict that the second vehicle will turn left at the intersection in the future, that is, the second vehicle will change lanes to the first lane. At this time, the first vehicle will slow down and give way according to the prediction result to avoid a traffic accident; when B% in the second probability of the above step S232 is the maximum probability, the first vehicle will predict that the second vehicle will continue to drive in a straight line in the future, that is, the second vehicle will continue to drive in the second lane. At this time, the first vehicle will continue to move forward at a constant speed according to the prediction result.

[0057] In summary, the trajectory prediction method provided by the present application is that when the first vehicle predicts the driving trajectory of the second vehicle, it will obtain the frequency of historical vehicles traveling along various driving trajectories in the lane where the second vehicle is currently located according to the determined position information of the second vehicle, so that the first vehicle can predict the driving trajectory of the second vehicle through the deep learning algorithm and the obtained frequency. Since the prediction result fully considers the frequency of historical vehicles traveling along various driving trajectories in the current lane of the second vehicle, the accuracy of the first vehicle's prediction of the driving trajectory of the second vehicle is improved, and the safety of the first vehicle's driving is also improved, thereby reducing the possibility of traffic accidents.

[0058] Based on the same inventive concept, as an implementation of the above method, an embodiment of the present application provides a trajectory prediction device, which is applied to an on-board device of a first vehicle, and a second vehicle is traveling around the first vehicle. The device embodiment corresponds to the above method embodiment. For ease of reading, the device embodiment will no longer repeat the details of the above method embodiment one by one, but it should be clear that the device in this embodiment can correspond to and implement all the contents in the above method embodiment.

[0059] Figure 5 A schematic diagram of the structure of the trajectory prediction device provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, the device includes: a determination module 501, an acquisition module 502 and an acquisition module 503.

[0060] Wherein, the determination module is used to determine the position information of the second vehicle.

[0061] Acquisition module: used to acquire the frequency of historical vehicles traveling along various driving trajectories in the lane where the second vehicle is currently located according to the position information of the second vehicle.

[0062] Acquisition module: used to predict the driving trajectory of the second vehicle using a deep learning algorithm and frequency.

[0063] The trajectory prediction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0064] Optionally, the acquisition module uses a deep learning algorithm and frequency to predict the driving trajectory of the second vehicle. Specifically, the deep learning algorithm is used to determine the first probability of the second vehicle traveling along each driving trajectory; the first probability of each driving trajectory is multiplied by the corresponding frequency to obtain the second probability of each trajectory; and the driving trajectory corresponding to the largest second probability is used as the prediction result of the driving trajectory of the second vehicle.

[0065] Optionally, an acquisition module uses a deep learning algorithm to determine the first probability that the second vehicle travels along each driving trajectory by acquiring prediction-related information, where the prediction-related information includes the second vehicle's current driving information, historical driving information, road structure information, map information, and location information; and uses a deep learning algorithm to determine the first probability that the second vehicle travels along each driving trajectory based on the prediction-related information.

[0066] Optionally, the driving information includes: speed information, acceleration information and heading angle information.

[0067] Optionally, the determination module determines the position information of the second vehicle by specifically determining the position information of the first vehicle; determining the relative position relationship between the second vehicle and the first vehicle; and determining the position information of the second vehicle based on the position information of the first vehicle and the relative position relationship.

[0068] Optionally, the acquisition module obtains the frequency of historical vehicles traveling along various driving trajectories in the lane where the second vehicle is currently located based on the position information of the second vehicle. Specifically, the position information of the second vehicle is sent to the server; and the frequency of historical vehicles traveling along various trajectories in the lane where the second vehicle is currently located is received from the server.

[0069] Optionally, the frequency of historical vehicles in the lane where the second vehicle is currently located traveling along various trajectories is determined based on a preset time period and the driving trajectories of historical vehicles in the lane where the second vehicle is currently located.

[0070] Based on the same inventive concept, an embodiment of the present application further provides a vehicle, which includes an on-board device, and the on-board device is configured to execute the trajectory prediction method shown in the above-mentioned embodiments.

[0071] It should be noted that the vehicles in this embodiment (including the first vehicle and the first vehicles around it) can be internal combustion engine vehicles using an engine as a power source, hybrid vehicles using an engine and an electric motor as power sources, electric vehicles using an electric motor as a power source, and other vehicles with driving functions. This embodiment does not impose specific restrictions on the type of vehicle.

[0072] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the trajectory prediction method shown in the above embodiments is implemented.

[0073] An embodiment of the present application further provides a computer program product, in which a computer program is stored. When the computer program is executed by a first vehicle, the first vehicle can execute the trajectory prediction method shown in the above embodiments.

[0074] Based on the same inventive concept, the present application embodiment also provides a chip, see Figure 6 As shown, the chip includes a processor and a memory, in which a computer program is stored. When the computer program is executed by the processor, the trajectory prediction method shown in the above embodiments is implemented.

[0075] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] It should be understood that the processor mentioned in the embodiments of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0077] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (doubledatarate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM), and direct rambus RAM (DR RAM).

[0078] In the embodiments provided in the present application, the division of each framework or module is only a logical function division. There may be other division methods in actual implementation. For example, multiple frameworks or modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0079] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0081] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0082] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A trajectory prediction method, It is characterized in that The vehicle-mounted device is applied to a first vehicle, and a second vehicle is traveling around the first vehicle. The method includes: determining the position information of the second vehicle; According to the position information of the second vehicle, obtaining the frequency of historical vehicles traveling along each driving trajectory in the lane where the second vehicle is currently located; Using a deep learning algorithm and the frequency, a driving trajectory of the second vehicle is predicted.

2. The method according to claim 1, It is characterized in that The using the deep learning algorithm and the frequency to predict the driving trajectory of the second vehicle includes: Determine a first probability that the second vehicle travels along each driving trajectory using the deep learning algorithm; Multiplying the first probability of each driving trajectory by the corresponding frequency to obtain a second probability of each trajectory; The driving trajectory corresponding to the largest second probability is used as the prediction result of the driving trajectory of the second vehicle.

3. The method according to claim 2, It is characterized in that The using the deep learning algorithm to determine a first probability that the second vehicle travels along each driving trajectory includes: Acquiring prediction related information, the prediction related information including current driving information, historical driving information, road structure information, map information, and location information of the second vehicle; Using a deep learning algorithm, a first probability of the second vehicle traveling along each driving trajectory is determined based on the prediction related information.

4. The method according to claim 3, It is characterized in that The driving information includes: speed information, acceleration information and heading angle information.

5. The method according to any one of claims 1 to 4, It is characterized in that The determining the position information of the second vehicle includes: determining the position information of the first vehicle; determining a relative position relationship between the second vehicle and the first vehicle; The position information of the second vehicle is determined according to the position information of the first vehicle and the relative position relationship.

6. The method according to claim 5, It is characterized in that The acquiring, according to the position information of the second vehicle, the frequency of historical vehicles traveling along each track in the lane where the second vehicle is currently located, comprises: Sending the location information of the second vehicle to the server; Receive the frequency of historical vehicles traveling along various trajectories in the lane currently located by the second vehicle returned by the server.

7. The method according to claim 6, It is characterized in that The frequency of historical vehicles in the lane where the second vehicle is currently located traveling along various trajectories is determined based on a preset time period and the driving trajectories of historical vehicles in the lane where the second vehicle is currently located.

8. A trajectory prediction device, It is characterized in that An on-board device applied to a first vehicle, wherein a second vehicle is traveling around the first vehicle, comprises: Determining module: used to determine the position information of the second vehicle; An acquisition module: used for acquiring the frequency of historical vehicles traveling along various driving trajectories in the lane where the second vehicle is currently located according to the position information of the second vehicle; Prediction module: used to predict the driving trajectory of the second vehicle using a deep learning algorithm and the frequency.

9. A vehicle, It is characterized in that The vehicle comprises an on-board device configured to execute the method as claimed in any one of claims 1 to 7.

10. A chip, It is characterized in that The method comprises at least one processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the method as claimed in any one of claims 1 to 7.

11. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program runs on a chip, the chip executes the method according to any one of claims 1 to 7.

Images