Vehicle path prediction method, device, equipment and medium
By acquiring vehicle location and map data for path planning and combining it with machine learning models to predict obstacle avoidance paths, the problem of autonomous vehicles being unable to effectively avoid dynamic obstacles in complex environments in existing technologies has been solved, achieving safe and efficient obstacle avoidance while adhering to traffic signs.
Patent Information
- Application Number
- CN202511518960.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-22
- Publication Date
- 2026-02-03
AI Technical Summary
Existing autonomous vehicle path planning methods cannot effectively address the need to avoid dynamic obstacles, and lack flexibility and intelligence in complex environments, failing to ensure compliance with traffic signs and avoidance behavior.
By acquiring vehicle location, map data, and road information, path planning is performed to determine the path type. When the planned path contains obstacles and traffic signs, machine learning models are used to predict obstacle avoidance paths, taking into account the constraints of road traffic signs, and optimizing the avoidance strategy.
It enables vehicles to safely and efficiently avoid obstacles while adhering to traffic signs, reducing detour time and improving the flexibility and intelligence of route planning.
Smart Images
Figure CN121453071A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] Embodiments of the present application relate to the technical field of path planning, and in particular to a vehicle path prediction method, device, equipment and medium. BACKGROUND
[0002] With the continuous development of automatic driving technology, intelligent transportation systems have been gradually applied to various traffic scenarios. In the path planning and control process of autonomous vehicles, static maps and simple path algorithms are mainly relied on, which usually cannot effectively cope with the need to avoid dynamic obstacles.
[0003] In a complex environment with traffic rules restrictions, the avoidance behavior of vehicles often lacks flexibility and intelligence, and cannot ensure that the avoidance of obstacles is completed while complying with traffic signs. SUMMARY
[0004] Embodiments of the present application provide a vehicle path prediction method, device, equipment and medium to ensure that the avoidance of obstacles is completed while complying with traffic signs.
[0005] In a first aspect, embodiments of the present application provide a vehicle path prediction method, the method comprising:
[0006] obtaining a current vehicle position of a vehicle, map data and road surface information detected by the vehicle, the map data including destination information;
[0007] performing path planning according to the vehicle position, the destination information and the road surface information to obtain path planning information of the vehicle from the vehicle position to the destination, the path planning information including a planned path and a path type;
[0008] if the path type represents that the planned path contains an obstacle, performing obstacle avoidance path prediction according to the path planning information.
[0009] In a second aspect, embodiments of the present application provide a vehicle path prediction device, the device comprising:
[0010] an obtaining module configured to obtain a current vehicle position of a vehicle, map data and road surface information detected by the vehicle, the map data including destination information;
[0011] a planning module configured to perform path planning according to the vehicle position, the destination information and the road surface information to obtain path planning information of the vehicle from the vehicle position to the destination, the path planning information including a planned path and a path type;
[0012] a prediction module configured to, if the path type represents that the planned path contains an obstacle, perform obstacle avoidance path prediction according to the path planning information.
[0013] In a third aspect, the embodiments of the present application further provide a vehicle path prediction system, comprising one or more processors and a storage device;
[0014] The storage device is configured to store one or more programs.
[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle path prediction method provided by any of the embodiments of the present application.
[0016] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the vehicle path prediction method provided by any of the embodiments of the present application.
[0017] The technical solution of the embodiments of the present application obtains the current vehicle position of the vehicle, map data and road surface information detected by the vehicle, the map data comprising destination information; performs path planning according to the vehicle position, the destination information and the road surface information to obtain path planning information of the vehicle from the vehicle position to the destination, the path planning information comprising a planned path and a path type; and performs obstacle avoidance path prediction according to the path planning information if the path type represents that the planned path contains obstacles and road traffic signs. Based on this, the type of the initially planned path is determined, so that the obstacle avoidance path prediction can be performed considering the road traffic signs when the planned path contains obstacles and road traffic signs, thereby ensuring the avoidance of obstacles on the premise of complying with traffic signs. BRIEF DESCRIPTION OF DRAWINGS
[0018] Figure 1 A flowchart of a vehicle path prediction method provided for Embodiment One of the present application;
[0019] Figure 2 A structural diagram of a vehicle path prediction device provided for Embodiment Two of the present application;
[0020] Figure 3 A structural diagram of an electronic device provided for Embodiment Three of the present application. DETAILED DESCRIPTION
[0021] The present application will be further described below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the structures.
[0022] Embodiment One
[0023] Figure 1A flowchart of a vehicle path prediction method provided for an embodiment of the present application. It should be noted that the method can be run on a vehicle processor provided with the required hardware, or can be processed by the cloud. As shown in Figure 1 the method includes:
[0024] Step 101, obtaining the current vehicle position, map data and road surface information detected by the vehicle, the map data including destination information.
[0025] In this embodiment, the vehicle position, map data and road surface information can be obtained through the vehicle-mounted intelligent terminal. By analyzing the road surface information, obstacle information within the detection range of the vehicle can be obtained.
[0026] In addition, the map data can include information of the current destination to be reached (destination information), which can include latitude and longitude data of the destination. The vehicle position can also be in the form of latitude and longitude data for subsequent processing.
[0027] Step 102, path planning according to the vehicle position, destination information and road surface information, obtaining path planning information of the vehicle from the vehicle position to the destination, the path planning information including the planning path and the path type.
[0028] In this step, the vehicle position and destination information can be used to plan the path from the vehicle position to the destination; the road surface information can be used to determine whether there are obstacles and road traffic signs in the planning path, and the path type of the planning path can be determined according to the determination result; the path planning information of the vehicle from the vehicle position to the destination can be determined according to the planning path and the path type.
[0029] Specifically, the map data usually contains road data, and the optimal path from the vehicle position to the destination can be planned based on the map data. Then, by combining and analyzing the road surface information and the planned path, it can be analyzed whether the planned path contains obstacles and road traffic signs, and the planned path can be classified based on the specific circumstances.
[0030] It should be noted that the path type includes a first type, a second type and a third type; the first type represents that the planning path does not contain obstacles and road traffic signs; the second type represents that the planning path contains obstacles but does not contain road traffic signs; and the third type represents that the planning path contains obstacles and road traffic signs.
[0031] Therefore, when classifying the path, if the planned path does not contain obstacles and road traffic signs, it is classified as the first type; if the planned path contains obstacles but does not contain road traffic signs, it is classified as the second type; if the planned path contains both obstacles and road traffic signs, it is classified as the third type.
[0032] In addition, when determining the path planning information, a unique identifier ID can be assigned to the planned path, and the ID is stored in mapping with the planned path, so as to facilitate subsequent searching and obtaining of the path through the ID. Based on this, the path planning information can include a path ID, a path type, and path parameters, which can include but are not limited to path length, path distance, and the like.
[0033] Step 103, if the path type represents that the planned path contains obstacles and road traffic signs, obstacle avoidance path prediction is performed according to the path planning information.
[0034] In this step, if the path type is the first type, no prediction is needed, and subsequent control can be directly performed according to the planned path.
[0035] If the path type is the second type, obstacle avoidance path prediction is performed according to the obstacle information, and if the path type is the third type, obstacle avoidance path prediction is performed according to the obstacles and road traffic signs in the path planning information.
[0036] Specifically, for the second type, the position relationship between the obstacle and the vehicle needs to be determined according to the current position of the vehicle and the optimal route of the planned path. The current position information of the vehicle is obtained in real time by the vehicle-mounted system and contains latitude and longitude information. The related planned path information is obtained by map data and real-time path planning algorithm, and the optimal route starts from the current vehicle position and reaches the destination.
[0037] In this process, since the vehicle avoidance strategy mainly depends on the relative position of the obstacle and the vehicle, especially the lateral position relationship, the lateral distance between the vehicle and the obstacle in the path needs to be calculated first. The position information of the obstacle is obtained through the road surface information, including the minimum length and width of the obstacle. The lateral distance between the vehicle and the obstacle can be obtained by geometric calculation. If the vehicle travels along the planned path, the lateral distance is the vertical distance between the current position of the vehicle and the projection point on the road where the obstacle is located.
[0038] The calculation formula of the lateral distance is as follows:
[0039] ;
[0040] wherein, is the current longitude coordinate of the vehicle, is the longitudinal distance between the vehicle and the obstacle. The formula calculates the lateral distance between the vehicle and the obstacle in meters. The shorter the distance, the closer the vehicle is to the obstacle, and the more likely it will need to avoid the obstacle.
[0041] Then, combined with the speed information of the vehicle and the lateral distance of the obstacle, the time required for avoidance can be calculated. The estimation of avoidance time depends on the lateral distance between the vehicle and the obstacle and the speed of the vehicle. This process needs to take into account the acceleration and braking performance of the vehicle, as well as the steering angle required during the avoidance process. Assuming that the avoidance path of the vehicle is along the edge of the lane, the avoidance time can be calculated by the following formula:
[0042] ;
[0043] where, is the aforementioned calculated lateral distance, is the current speed of the vehicle in meters per second. The purpose of this formula is to calculate how long it will take for the vehicle to complete the avoidance at the current speed. The greater the lateral distance or the slower the speed, the longer the avoidance time will be.
[0044] The information obtained by the final obstacle avoidance path prediction includes the predicted planning path ID, the predicted planning path type, the predicted planning path avoidance vehicle avoidance time, the predicted planning path length, the predicted planning path distance, the predicted planning path detour distance value, and all obstacle information on the predicted planning path.
[0045] It should be noted that the other obstacle information on the predicted planning path can be provided by other vehicles on the path.
[0046] For the third type, in addition to the above-mentioned obstacle-related processing process, the limiting conditions of road traffic signs need to be considered, especially factors related to speed limits, road widths, and traffic regulations. Considering the guiding role of road traffic signs for vehicles, adjustments may be needed during the avoidance process, or even detours to another wider lane.
[0047] Specifically, the detour time of the predicted path can be calculated by a more complex model. This model not only considers the lateral distance and vehicle speed, but also introduces the influence of traffic signs. The avoidance time can be further optimized as:
[0048] ; where, represents the additional time delay due to road traffic signs (such as speed limits, turn signs, etc.). This delay is estimated by analyzing historical data through a machine learning model, and it is closely related to the type of sign, the type of vehicle, and its relative position to the sign.
[0049] Through the above formulas and algorithms, the avoidance time and path optimization strategy can be dynamically predicted based on real-time data during vehicle path planning. These calculation results can help the vehicle-mounted system to adjust the driving strategy in real time, ensuring that the vehicle can safely and efficiently avoid obstacles and minimize the detour time.
[0050] In a specific example, assuming the current vehicle speed is 10 meters per second and the obstacle is 5 meters away from the vehicle, according to the first formula, the lateral distance is 5 meters. Using the second formula, the avoidance time is: ;
[0051] If there is a turn sign on the path at this time, causing the vehicle to have to slow down and add an additional 1 second of time delay, then the optimized avoidance time is: ;
[0052] In this way, the machine learning system can optimize the avoidance strategy in real time, ensuring that the vehicle can effectively avoid obstacles and follow traffic rules in complex environments.
[0053] In addition, the machine learning system estimates the time required for the vehicle to avoid obstacles while following traffic sign constraints based on historical data, the type of traffic sign, the speed of the vehicle, and the relative position between the obstacle and the traffic sign.
[0054] It should be noted that the machine learning in this embodiment needs to consider the following factors:
[0055] Traffic sign type: such as speed limit signs, stop signs, or turn signs, etc.
[0056] Current vehicle speed : The current speed of the vehicle may be affected by the sign, especially the speed limit sign and the deceleration sign.
[0057] Relative position of vehicle and sign : The distance between the vehicle and the road traffic sign determines when the vehicle starts to slow down.
[0058] Lateral distance D between obstacle and vehicle 横 : The lateral distance between the vehicle and the obstacle affects the difficulty of avoidance.
[0059] Obstacle type and its impact on avoidance path: such as static obstacles, dynamic obstacles, and the size of the obstacle, etc.
[0060] The machine learning model can analyze historical data based on these features through regression analysis, support vector machines, etc., to establish a prediction model. The goal of this model is to learn the impact of traffic signs on avoidance time through training data, so as to predict the delay time in a specific situation.
[0061] The following calculation method of machine learning model is used in this solution: ;
[0062] where, is the additional delay time caused by traffic signs, "sign type" takes different sign types (e.g. speed limit sign is 1, turn sign is 2, etc.), is the current speed of the vehicle, is the relative distance between the vehicle and the traffic sign, is the lateral distance of the obstacle, "obstacle type" reflects the characteristics of the obstacle (e.g. static or dynamic). Parameter is the weight coefficient obtained through machine learning algorithm training, representing the contribution of each factor to the delay time.
[0063] Suppose during the training process, the model finds that the speed limit sign causes the vehicle to slow down to an average speed of 50 kilometers per hour, the distance to the traffic sign is 100 meters, the current speed of the vehicle is 80 kilometers per hour, and the distance to the obstacle is 5 meters. Through the training of the model, suppose we get the following weight coefficients:
[0064] α=1.2 (impact of speed limit sign)
[0065] β=0.05 (impact of vehicle speed)
[0066] γ=0.03 (impact of sign-vehicle distance)
[0067] δ=0.1 (impact of lateral distance)
[0068] =0.5 (impact of obstacle type)
[0069] According to these parameters, we can calculate the additional time delay caused by the traffic sign: ;
[0070] In this case, the additional time delay caused by the traffic sign is 9.2 seconds. This time is the additional time added by the vehicle when avoiding obstacles due to the restrictions of traffic signs (such as speed limit).
[0071] By analyzing historical data through machine learning models, these parameters can be continuously updated and optimized, so that in different driving situations, the system can accurately predict the time delay caused by road traffic signs and incorporate it into the entire avoidance strategy. Ultimately, this can help vehicles accurately assess the time required to avoid obstacles and traffic signs and choose the optimal avoidance path and strategy.
[0072] Finally, through the machine learning model continuously optimized during the training process, the system can make optimal decisions based on real-time vehicle and obstacle information, as well as road traffic signs and environmental changes. This process continuously loops, improving the accuracy and safety of path planning and avoidance strategies through a feedback mechanism, ensuring that the vehicle can effectively navigate complex traffic environments, avoid collisions, and reduce traffic congestion.
[0073] After the above process, a plurality of predicted results are obtained, and then the predicted results are combined to retain the path with the minimum detour distance, to obtain an optimal prediction planning path ID, a prediction planning path type, a prediction planning path vehicle avoidance time, a prediction planning path length, a prediction planning path distance, and a prediction planning path detour distance. The optimal prediction planning path ID, the prediction planning path type, the prediction planning path vehicle avoidance time, the prediction planning path length, the prediction planning path distance, and the prediction planning path detour distance are all unique values.
[0074] Then, the vehicle performs subsequent vehicle driving route control according to the optimal prediction planning path ID, the prediction planning path type, the prediction planning path vehicle avoidance time, the prediction planning path length, the prediction planning path distance, and the prediction planning path detour distance.
[0075] In this embodiment, the vehicle's current position, map data, and road surface information detected by the vehicle are obtained, and the map data includes destination information. Path planning is performed based on the vehicle position, destination information, and road surface information to obtain path planning information for the vehicle from the vehicle position to the destination. The path planning information includes a planned path and a path type. If the path type indicates that the planned path contains obstacles and road traffic signs, obstacle avoidance path prediction is performed based on the path planning information. Based on this, by judging the type of the initially planned path, obstacle avoidance path prediction can be performed considering road traffic signs when the planned path contains obstacles and road traffic signs, thereby ensuring obstacle avoidance while complying with traffic signs.
[0076] Embodiment Two
[0077] Figure 2 A structural schematic diagram of a vehicle path prediction device provided in Embodiment Two of the present application. The vehicle path prediction device provided in the present embodiment can execute the vehicle path prediction method provided in any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method. The device can be realized in software and / or hardware. As shown in Figure 2 The vehicle path prediction device specifically includes an acquisition module 201, a planning module 202, and a prediction module 203.
[0078] The acquisition module is used to acquire the vehicle's current location, map data, and road surface information detected by the vehicle. The map data includes destination information.
[0079] The planning module is used to plan routes based on vehicle location, destination information, and road information, and obtains route planning information from the vehicle's location to its destination. The route planning information includes the planned route and route type.
[0080] The prediction module is used to predict obstacle avoidance paths based on path planning information if the path type is characterized as containing obstacles in the planned path.
[0081] Furthermore, the planning module is used for:
[0082] Based on the vehicle's location and destination information, route planning is performed to obtain the planned route from the vehicle's location to its destination;
[0083] Based on the road surface information, determine whether there are obstacles and road traffic signs in the planned route, and determine the route type of the planned route based on the judgment results;
[0084] The route planning information from the vehicle's location to its destination is determined based on the planned route and route type.
[0085] Furthermore, the path types include type 1, type 2, and type 3;
[0086] The first type is characterized by the absence of obstacles and road traffic signs in the planned path;
[0087] The second type is characterized by a planned path containing obstacles but lacking road traffic signs;
[0088] The third type is characterized by the presence of obstacles and road traffic signs in the planned path.
[0089] Furthermore, the prediction module is used for:
[0090] If the path type is the second type, obstacle avoidance path prediction is performed based on the obstacles in the path planning information;
[0091] If the path type is the third type, obstacle avoidance path prediction is performed based on obstacles and road traffic signs in the path planning information.
[0092] Example 3
[0093] Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of this application, as shown below. Figure 3 As shown, the electronic device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in the electronic device can be one or more.Figure 3 The processor 310 in the electronic device is taken as an example; the processor 310, the memory 320, the input device 330 and the output device 340 in the electronic device can be connected through a bus or other means, Figure 3 The bus connection is taken as an example.
[0094] The memory 320 as a kind of computer readable storage medium, it can be used to store software program, computer executable program and module, such as the program instruction / module corresponding to the task of the application across the task of the application in the embodiment of the application. The processor 310 is by running the software program, instruction and module stored in the memory 320, thereby performing the various functional applications and data processing of electronic device, that is, realizing the vehicle path prediction method described above:
[0095] Obtain the current vehicle position of vehicle, map data and road surface information detected by vehicle, the map data includes destination information;
[0096] According to the vehicle position, destination information and road surface information, path planning is carried out, and path planning information of vehicle from vehicle position to destination is obtained, and the path planning information contains planning path and path type;
[0097] If the path type is represented as containing obstacles and road traffic signs in the planning path, obstacle avoidance path prediction is carried out according to the path planning information.
[0098] Further, according to the vehicle position, destination information and road surface information, path planning is carried out, and path planning information of vehicle from vehicle position to destination is obtained, including:
[0099] According to the vehicle position, destination information, path planning is carried out, and planning path of vehicle from vehicle position to destination is obtained;
[0100] According to the road surface information, it is judged whether there is obstacle and road traffic sign in the planning path, and the path type of the planning path is determined according to the judgment result;
[0101] According to the planning path and path type, path planning information of vehicle from vehicle position to destination is determined.
[0102] Further, the path type includes first type, second type and third type;
[0103] The first type is represented as not containing obstacles and road traffic signs in the planning path;
[0104] The second type is represented as containing obstacles and not containing road traffic signs in the planning path;
[0105] The third type is represented as containing obstacles and containing road traffic signs in the planning path.
[0106] Further, if the path type represents that the planning path contains obstacles and road traffic signs, obstacle avoidance path prediction is performed according to the path planning information, including:
[0107] If the path type is the third type, obstacle avoidance path prediction is performed according to the obstacles and road traffic signs in the path planning information.
[0108] The memory 320 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory 320 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some examples, the memory 320 can further include a memory remotely arranged with respect to the processor 310, which can be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.
[0109] Embodiment Four
[0110] The embodiment four of the present application also provides a storage medium containing computer executable instructions, which are used to execute a vehicle path prediction method when executed by a computer processor, and the method comprises:
[0111] Obtaining a current vehicle position of a vehicle, map data and road surface information detected by the vehicle, the map data including destination information;
[0112] Performing path planning according to the vehicle position, the destination information and the road surface information to obtain path planning information of the vehicle from the vehicle position to the destination, the path planning information containing a planning path and a path type;
[0113] If the path type represents that the planning path contains obstacles and road traffic signs, obstacle avoidance path prediction is performed according to the path planning information.
[0114] Further, performing path planning according to the vehicle position, the destination information and the road surface information to obtain path planning information of the vehicle from the vehicle position to the destination, including:
[0115] Performing path planning according to the vehicle position and the destination information to obtain a planning path of the vehicle from the vehicle position to the destination;
[0116] Determining whether there are obstacles and road traffic signs in the planning path according to the road surface information, and determining a path type of the planning path according to a determination result;
[0117] According to the planning path and the path type, path planning information of the vehicle from the vehicle position to the destination is determined.
[0118] Further, the path type includes a first type, a second type and a third type.
[0119] The first type is characterized by that the planning path does not contain obstacles and road traffic signs.
[0120] The second type is characterized by that the planning path contains obstacles and does not contain road traffic signs.
[0121] The third type is characterized by that the planning path contains obstacles and road traffic signs.
[0122] Further, if the path type is characterized by that the planning path contains obstacles and road traffic signs, obstacle avoidance path prediction is performed according to the path planning information, including:
[0123] If the path type is the third type, obstacle avoidance path prediction is performed according to the obstacles and road traffic signs in the path planning information.
[0124] Of course, the storage medium provided by the embodiment of the present application contains computer executable instructions, which are not limited to the above method operations, and can also perform related operations in the vehicle path prediction method provided by any embodiment of the present application.
[0125] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary general hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH memory, a hard disk or an optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of various embodiments of the present application.
[0126] It is worth noting that in the above embodiment of the device, each unit and module included is only divided according to functional logic, but is not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy distinction, and do not limit the protection scope of the present application.
[0127] Note that the above merely describes preferred embodiments of the application and the principles of the application. It will be understood by those skilled in the art that the application is not limited to the specific embodiments described herein, and that changes, modifications and substitutions can be made by those skilled in the art without departing from the scope of the application. Therefore, although the application has been described in detail by the above embodiments, the application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the application, and the scope of the application is determined by the appended claims.
Claims
1. A vehicle route prediction method, characterized in that, The method includes: The vehicle's current location, map data, and road surface information detected by the vehicle are obtained, wherein the map data includes destination information; Based on the vehicle location, destination information, and road information, route planning is performed to obtain the route planning information of the vehicle from the vehicle location to the destination. The route planning information includes the planned route and route type. If the path type is characterized as containing obstacles and road traffic signs in the planned path, obstacle avoidance path prediction is performed based on the path planning information.
2. The method according to claim 1, characterized in that, Based on the vehicle location, destination information, and road information, route planning is performed to obtain route planning information for the vehicle from its location to its destination, including: Based on the vehicle location and the destination information, a route is planned to obtain the planned route from the vehicle location to the destination; Based on the road surface information, determine whether there are obstacles and road traffic signs in the planned path, and determine the path type of the planned path based on the determination result; The route planning information for the vehicle from its location to its destination is determined based on the planned route and the route type.
3. The method according to claim 1, characterized in that, The path types include a first type, a second type, and a third type; The first type is characterized by the absence of obstacles and road traffic signs in the planned path; The second type is characterized by the planned path containing obstacles and lacking road traffic signs; The third type is characterized by the planned path containing obstacles and road traffic signs.
4. The method according to claim 3, characterized in that, If the path type is characterized as the planned path containing obstacles and traffic road signs, obstacle avoidance path prediction is performed based on the path planning information, including: If the path type is the third type, obstacle avoidance path prediction is performed based on the obstacles and road traffic signs in the path planning information.
5. A vehicle route prediction device, characterized in that, The device includes: The acquisition module is used to acquire the vehicle's current location, map data, and road surface information detected by the vehicle, wherein the map data includes destination information; The planning module is used to perform route planning based on the vehicle location, the destination information, and the road surface information to obtain the route planning information of the vehicle from the vehicle location to the destination. The route planning information includes the planned route and the route type. The prediction module is used to predict an obstacle avoidance path based on the path planning information if the path type indicates that the planned path contains obstacles.
6. The apparatus according to claim 5, characterized in that, The planning module is used for: Based on the vehicle location and the destination information, a route is planned to obtain the planned route of the vehicle from the vehicle location to the destination; Based on the road surface information, determine whether there are obstacles and road traffic signs in the planned path, and determine the path type of the planned path based on the determination result; The route planning information for the vehicle from its location to its destination is determined based on the planned route and the route type.
7. The apparatus according to claim 5, characterized in that, The path types include a first type, a second type, and a third type; The first type is characterized by the absence of obstacles and road traffic signs in the planned path; The second type is characterized by the planned path containing obstacles and lacking road traffic signs; The third type is characterized by the planned path containing obstacles and road traffic signs.
8. The apparatus according to claim 9, characterized in that, The prediction module is used for: If the path type is the second type, obstacle avoidance path prediction is performed based on the obstacles in the path planning information; If the path type is the third type, obstacle avoidance path prediction is performed based on the obstacles and road traffic signs in the path planning information.
9. An electronic device, characterized in that, include: One or more processors and storage devices; The storage device is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle path prediction method as described in any one of claims 1-4.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the vehicle path prediction method as described in any one of claims 1-4.