Vehicle driving path planning, system, device and medium

Abstract

The invention relates to a vehicle driving path planning, system, device and medium. The method comprises the following steps: acquiring a starting point and an ending point of a driving path, and determining road nodes from the starting point to the ending point; based on the road nodes, segmenting a driving path from the starting point to the ending point to obtain a plurality of sub-paths, and determining corresponding lane models and lane attributes according to the types of lanes included in the sub-paths; wherein each sub-path comprises a plurality of lanes; when the vehicle runs to each road node, inputting the running data of the vehicle on the previous sub-path and the lane attribute of the next sub-path into the lane model corresponding to each lane in the next sub-path, and correspondingly predicting the passing time of the vehicle on each lane in the next sub-path; the lane with the shortest passing time is selected as a target lane, and the shortest passing time is saved; and guiding the vehicle to change the lane or keep to the target lane, and storing the actual passing time. According to the invention, the accuracy of lane passing time prediction is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to vehicle driving path planning, a system, a device and a medium. Background Art

[0002] As we all know, the rapid development of intelligent driving technology has enabled autonomous driving vehicles to gradually move from simulated roads to ordinary municipal roads. However, most existing intelligent driving systems rely on high-precision maps to achieve lane recognition, path planning, and dynamic driving decisions. High-precision maps can provide detailed static information such as lane lines, traffic signs, slopes, and curvatures, providing basic driving references for autonomous vehicles. However, with the complexity of actual application scenarios, intelligent driving can hardly cope with real-time and diverse road conditions by relying solely on the static characteristics of high-precision maps.

[0003] For most office workers, their daily driving routes are mostly relatively fixed between two points (home and company). Users are no longer focusing on the length of the route or the overall planning, but on how to quickly pass through congested areas and avoid accident-prone areas on specific sections of the road, thereby achieving a more efficient and safer commuting experience. Traditional high-precision map technology is obviously difficult to meet this demand. Therefore, it is necessary to provide a vehicle driving path planning, system, equipment and medium. Summary of the invention

[0004] In view of the shortcomings of the prior art mentioned above, the purpose of the present invention is to provide a vehicle driving path planning, system, equipment and medium, which improves the problem that the prior art is difficult to accurately predict real-time, complex and changeable road environments due to the static characteristics of high-precision maps.

[0005] To achieve the above-mentioned purpose and other related purposes, the present invention provides a vehicle driving path planning, including: obtaining the starting point and the end point of the driving path, and determining the road nodes between the starting point and the end point; based on the road nodes, dividing the driving path between the starting point and the end point to obtain multiple sub-paths, and determining the corresponding lane model and lane attributes according to the type of lanes included in the sub-path; wherein each sub-path includes multiple lanes; when the vehicle travels to each road node, the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path are input into the lane model corresponding to each lane in the next sub-path, and the travel time of the vehicle in each lane in the next sub-path is predicted accordingly, and the lane with the shortest travel time is selected as the target lane, and the shortest travel time is saved; the vehicle is guided to change lanes or stay in the target lane, and the actual travel time is saved.

[0006] In one embodiment of the present invention, the lane model is dynamically updated based on a preset number of historical driving data. For each type of lane, the process of dynamically updating the lane model includes: calculating the difference between each historically saved shortest travel time and the corresponding actual travel time; updating the parameters of the lane model based on the calculated difference, and dynamically updating the lane model.

[0007] In one embodiment of the present invention, for each sub-path, the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path are input into the lane model corresponding to each lane in the next sub-path, and the travel time of the vehicle in each lane in the next sub-path is predicted accordingly, and the lane with the shortest travel time is selected as the target lane, and the shortest travel time is saved, including: for each lane: inputting the driving data of the vehicle in the previous sub-path and the lane attributes of the lane in the next sub-path into the lane model corresponding to the lane, and predicting the travel time of the vehicle in the lane in the next sub-path; sorting the travel time of each lane in the next sub-path, and selecting the lane with the shortest travel time as the target lane; wherein, when the previous sub-path is the first sub-path, the driving data is the average of the pre-stored historical driving data of the driving path.

[0008] In one embodiment of the present invention, the driving data of the vehicle in the previous sub-path and the lane attributes of the lane in the next sub-path are input into the lane model corresponding to the lane, and the travel time of the vehicle in the lane in the next sub-path is predicted accordingly, including: data cleaning of the driving data of the vehicle in the previous sub-path; inputting the cleaned driving data and the lane attributes of the lane in the next sub-path into the lane model corresponding to the lane in the next sub-path, and predicting the travel time of the vehicle in the lane in the next sub-path.

[0009] In one embodiment of the present invention, the data cleaning of the vehicle's driving data on the previous sub-path includes: determining whether there are missing values ​​in the driving data of the vehicle on the previous sub-path: if so, performing linear interpolation processing on the driving data to obtain interpolated driving data, and performing data alignment on the interpolated driving data to obtain cleaned driving data; if not, performing data alignment on the driving data to obtain cleaned driving data.

[0010] In one embodiment of the present invention, the lane model is a time series model.

[0011] In one embodiment of the present invention, the time series model is LSTM.

[0012] In one embodiment of the present invention, a vehicle driving path planning system is also provided, the system comprising: a data acquisition module, used to acquire the starting point and the end point of the driving path, and determine the road nodes between the starting point and the end point; a lane division module, used to divide the driving path between the starting point and the end point based on the road nodes to obtain multiple sub-paths, and determine the corresponding lane model and lane attributes according to the type of lanes included in the sub-path; wherein each sub-path includes multiple lanes; a travel time prediction module, used to input the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path into the lane model corresponding to each lane in the next sub-path when the vehicle travels to each road node, and correspondingly predict the travel time of the vehicle in each lane in the next sub-path, and select the lane with the shortest travel time as the target lane, and save the shortest travel time; a lane change module, used to guide the vehicle to change lanes or stay in the target lane, and save the actual travel time.

[0013] In one embodiment of the present invention, an electronic device is also provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the vehicle driving path planning described in any one of the above items.

[0014] In one embodiment of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes any of the above-mentioned vehicle driving path planning.

[0015] As described above, the planning, system, equipment and medium of a vehicle driving path of the present invention have the following beneficial effects: the driving path is divided according to the road nodes to obtain multiple sub-paths, and the corresponding lane model is matched according to the lane type of the sub-path, so that the traffic characteristics of each section of the road can be accurately obtained, thereby improving the accuracy of the prediction. During the driving of the vehicle, the travel time of each lane is dynamically predicted based on the driving data of the previous sub-path and the lane attributes of the next sub-path, and the lane with the shortest travel time is selected as the target lane in real time, so that the vehicle is always on the optimal driving path to improve the traffic efficiency. In addition, by saving the actual travel time and the predicted shortest travel time, the lane model is continuously optimized. It can adapt to the sudden change of traffic environment, break through the static limitations of high-precision maps, and effectively improve the accuracy of travel time prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a process flow for planning a vehicle driving path provided by an embodiment of the present invention;

[0017] Figure 2Shown is a structural block diagram of a vehicle driving system provided by an embodiment of the present invention;

[0018] Figure 3 Shown is a structural schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0021] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0022] The present invention provides a vehicle driving path planning, which divides the driving path according to road nodes to obtain multiple sub-paths, and matches the corresponding lane model according to the lane type of the sub-path, so as to accurately obtain the traffic characteristics of each section of the road, thereby improving the accuracy of the prediction. During the vehicle driving, the travel time of each lane is dynamically predicted according to the driving data of the previous sub-path and the lane attributes of the next sub-path, and the lane with the shortest travel time is selected as the target lane in real time, so that the vehicle is always in the optimal driving path to improve the traffic efficiency. In addition, by saving the actual travel time and the predicted shortest travel time, the lane model is continuously optimized. It can adapt to the sudden change of traffic environment, break through the static limitations of high-precision maps, and effectively improve the accuracy of travel time prediction.

[0023] See also Figure 1 , the vehicle driving path planning includes the following steps:

[0024] S1. Obtain a starting point and an end point of a driving path, and determine a road node between the starting point and the end point.

[0025] The solution of the present invention is applicable to intelligent driving path planning for fixed routes, that is, the driving path has been traveled many times in advance, so the shortest travel time can be predicted based on the lane model. Specifically, after the vehicle is started, the starting point and the end point are entered in the high-precision map, and the driving path from the starting point to the end point can be obtained, and the road nodes between the starting point and the end point can be extracted from the high-precision map, where the road nodes include but are not limited to ramps, intersections, traffic light control points, toll booths, roundabouts, merging lanes, merging lanes, etc. Since such road nodes will affect the vehicle's driving path selection and travel time, the driving path can be dynamically optimized in combination with historical driving data and real-time vehicle driving data, and the travel time of each sub-path can be predicted to ensure that the vehicle completes the journey in the shortest time.

[0026] S2. Based on the road node, the path between the starting point and the end point is divided to obtain multiple sub-paths, and the corresponding lane model and lane attribute are determined according to the type of lanes included in the sub-path; wherein each sub-path includes multiple lanes.

[0027] According to the road nodes between the starting point and the end point, the entire driving path from the starting point to the end point is divided into a plurality of continuous sub-paths, each sub-path is composed of a road section between two adjacent road nodes, and each sub-path includes a plurality of parallel lanes. Since the lane characteristics of different road sections are different, for example, the fast lane requires a faster driving speed, and the slow lane can be driven at a low speed or pass special vehicles. Therefore, for each sub-path: according to the type of lane included in the sub-path, the corresponding lane model is matched, wherein each type of lane corresponds to a lane model. Further, considering that the types of lanes are different, their lane attributes are also different, resulting in the vehicle travel time being affected. Therefore, the present invention also determines the lane attributes of each type of lane according to the lane type included in the sub-path for each sub-path. Lane attributes include, but are not limited to, information such as lane width, lane slope, lane curvature and speed limit. The type names and corresponding lane attributes of each type of lane can be pre-stored in the database, and the corresponding lane attributes can be retrieved according to the lane type.

[0028] In one embodiment of the present invention, in order to predict the travel time of each lane based on historical driving data and real-time driving data, the lane model is a time series model. The time series model includes but is not limited to LSTM, RNN, Transformer series models, etc. Furthermore, considering that LSTM can effectively learn the lane passing state at different time steps, so as to more accurately predict the vehicle passing time, the time series model is LSTM.

[0029] In one embodiment of the present invention, the lane model is dynamically updated based on a preset amount of historical driving data. For each type of lane, the process of dynamically updating the lane model includes:

[0030] Calculate the difference between each historically saved shortest travel time and the corresponding actual travel time;

[0031] The parameters of the lane model are updated based on the calculated difference, and the lane model is dynamically updated.

[0032] Considering the dynamic and uncertain nature of the traffic environment, the lane model of the present invention is not static, but is based on a dynamic update mechanism to adapt to the traffic conditions under different time periods and road conditions, so as to improve the accuracy of path planning. Specifically, the lane model for each type of lane is processed as follows: after each vehicle travels, the predicted shortest travel time of the lane model on the corresponding sub-path will be saved, and the actual travel time will be saved at the same time. After accumulating and saving the driving records of a preset number of vehicles, the prediction error of the lane model is measured by calculating the difference between each predicted travel time and the actual travel time. Based on the calculated difference, the parameters of the road model are reversely updated by the gradient descent method so that the future travel time can be predicted more accurately. Through this dynamic update mechanism, the lane model can adapt to different road conditions and real-time traffic conditions, thereby improving the path planning capability.

[0033] S3. When the vehicle travels to each road node, the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path are input into the lane model corresponding to each lane in the next sub-path, and the travel time of the vehicle in each lane in the next sub-path is predicted accordingly, and the lane with the shortest travel time is selected as the target lane, and the shortest travel time is saved.

[0034] Driving data refers to dynamic information collected by sensors, on-board computing systems, GPS and other devices during the driving process of the vehicle, which is used to describe the driving status of the vehicle. Driving data includes but is not limited to vehicle status data such as speed, acceleration, braking status, and the frequency of vehicles passing through adjacent lanes. When the vehicle drives to each road node (take it as the current road node), for the road node currently reached: the driving data of the sub-path between the road node just passed and the current road node (i.e., the previous sub-path) and the lane attributes of each lane in the sub-path between the current road node and the next road node (i.e., the next sub-path) are input into the lane model corresponding to each lane in the next sub-path. For each lane: the lane model of the corresponding lane will predict the estimated travel time of the vehicle in the lane in the next sub-path. After all lanes are predicted, the lane with the shortest travel time will be selected as the target lane from all optional lanes to optimize driving efficiency. In addition, in order to facilitate the subsequent training of the model, the shortest travel time of the sub-path will be saved to the historical record to continuously optimize the prediction ability of the lane model and ensure that more accurate path planning and lane selection can be provided when driving on the same route in the future.

[0035] In one embodiment of the present invention, for each sub-path, the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path are input into the lane model corresponding to each lane in the next sub-path, and the travel time of the vehicle in each lane in the next sub-path is predicted accordingly, and the lane with the shortest travel time is selected as the target lane, and the shortest travel time is saved, including:

[0036] For each lane: the driving data of the vehicle in the previous sub-path and the lane attributes of the lane in the next sub-path are input into the lane model corresponding to the lane, and the travel time of the vehicle in the lane in the next sub-path is predicted accordingly;

[0037] The travel time of each lane in the next sub-path is sorted, and the lane with the shortest travel time is selected as the target lane; wherein, when the previous sub-path is the first sub-path, the driving data is the average of the pre-stored historical driving data of the driving path.

[0038] For each sub-path, according to the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path, the corresponding lane model is used to predict the travel time of the vehicle in each lane in the next sub-path to select the optimal lane. Specifically, for each lane in the next sub-path, the following process is followed: the driving data of the previous sub-path and the attributes of the lane in the next sub-path are input into the lane model corresponding to the lane to generate the estimated travel time of the lane. After the estimated travel time of all lanes in the sub-path is predicted, all the estimated travel times are sorted and the lane with the shortest travel time is selected as the target lane to ensure the maximum travel efficiency. In order to facilitate the dynamic training and updating of the subsequent model, the predicted shortest travel time and actual travel time of the sub-path are also saved. Furthermore, if the previous sub-path is the first sub-path, since there is no driving data to refer to, the mean of the pre-stored historical driving data is used as the input of the road prediction model of the sub-path to predict the predicted travel time of each lane in the first sub-path. Among them, the mean of the historical driving data refers to the average travel time of the vehicle passing through the same driving path several times in the past. The present invention divides a complete driving path into multiple sub-paths, determines the boundaries of each sub-path based on adjacent road nodes, and matches the corresponding lane model to the lane type of each sub-path, so as to more accurately predict the travel time of each lane.

[0039] In one embodiment of the present invention, the step of inputting the driving data of the vehicle in the previous sub-path and the lane attributes of the lane in the next sub-path into the lane model corresponding to the lane, and correspondingly predicting the travel time of the vehicle in the lane in the next sub-path, includes:

[0040] Clean the driving data of the vehicle on the previous sub-path;

[0041] The cleaned driving data and the lane attributes of the lane in the next sub-path are input into the lane model corresponding to the lane in the next sub-path, and the travel time of the vehicle in the lane in the next sub-path is predicted accordingly.

[0042] In order to more accurately predict the predicted travel time of the vehicle in each lane in the next sub-path, it is necessary to clean the driving path of the previous sub-path to eliminate the influence of sensor noise and ensure the accuracy of the input data. The data cleaning method includes but is not limited to removing duplicate values, filling missing values, and data alignment. The cleaned driving data and the lane attributes of the lane in the next sub-path are input into the lane model corresponding to the lane in the next sub-path to predict the predicted travel time through the lane.

[0043] In one embodiment of the present invention, the step of cleaning the driving data of the vehicle on the previous sub-path includes:

[0044] Determine whether there are missing values ​​in the driving data of the vehicle in the previous sub-path:

[0045] If yes, linear interpolation is performed on the driving data to obtain interpolated driving data, and data alignment is performed on the interpolated driving data to obtain cleaned driving data;

[0046] If not, the driving data is aligned to obtain cleaned driving data.

[0047] Since the driving data of the previous sub-path is a series of data obtained according to the preset time length, in order to ensure the integrity of the data, it is necessary to first check whether there are missing values ​​in the same type of driving data obtained. If there are, they are supplemented based on linear interpolation. If there are no missing values, or they have been supplemented by interpolation, the driving data can be aligned to ensure that the timestamps of different types of driving data are unified and generate cleaned driving data.

[0048] S4. Guiding the vehicle to change lanes or stay in the target lane, and saving the actual travel time.

[0049] When the vehicle reaches the next road node, the target lane is determined based on the predicted shortest travel time, and the vehicle is guided to change lanes or stay in the target lane to ensure that the vehicle travels on the path with the highest travel efficiency. After the vehicle enters the target lane, its travel time is continuously recorded until the vehicle reaches the next road node, and the accumulated travel time during this period is recorded as the actual travel time.

[0050] The present invention takes into account that during rush hour, traditional intelligent driving technology cannot produce effective congestion avoidance experience according to the changes in the distribution of daily road vehicle congestion because high-precision map information often cannot reflect certain dynamic factors. These dynamic factors in the driving process include but are not limited to: the traffic efficiency of multiple lanes in congested sections, the impact of accidents and construction, dynamic adjustment of traffic management and specific laws of the city. Among them, the traffic efficiency of multiple lanes in congested sections means that not all lanes in congested sections are blocked, and the traffic efficiency of each lane is different, but there is a regularity. The impact of accidents and construction means that some lanes may have a reduced traffic capacity due to sudden traffic accidents, temporary closures, etc. Dynamic adjustment of traffic management means that traffic police regularly adjust lane directions or traffic restrictions according to actual road conditions, but high-precision maps cannot perceive these dynamic adjustments of traffic management. Specific laws in the city refer to the operating time, frequency and path of special vehicles such as tow trucks or sprinklers, which will have intermittent effects on some lanes.

[0051] To improve the above problems, the present invention dynamically records and analyzes the traffic patterns of multiple lanes in congested sections by having vehicles travel on the same road multiple times; records and analyzes the lane layout of the navigation route where accidents and construction have occurred; analyzes and records the objective laws of dynamic adjustment of traffic management in time and space; and analyzes and records the operation time, frequency and path of special vehicles such as tow trucks and sprinkler trucks in the navigation route. During actual driving, in a single sampling, the braking depth, duration, and frequency of the vehicle in front of the current lane, as well as the number of vehicles passing through the left and right lanes at the same time, the speed of the current vehicle and other driving data are detected to dynamically evaluate the traffic efficiency of each lane. Among them, the traffic efficiency Ei(t) of lane i is defined as (taking into account the influence of static and dynamic variables): Hi is the basic lane capacity (static value) provided by the high-precision map; X k (t) is a set of dynamic variables, including: accident probability Paccident(t), traffic management adjustment Ptraffic(t) and tow truck operation impact Pmaintenance(t); α k is the weight of the dynamic variable on the traffic efficiency. Since the vehicle's driving path at time t consists of N segments, each segment contains M i When training the lane traffic model, the goal is to minimize the total travel time. x ij Either 0 or 1. Travel time T i Can be defined as Among them, L i and V i (t) represent lane length and lane average speed respectively.

[0052] This method is applicable to all vehicle driving solutions using intelligent driving. For example, the road section where the vehicle is driving is divided into five sections, including accident sections, traffic management sections, and obstacle clearance sections. The detailed steps of the vehicle driving method based on road learning are as follows:

[0053] Step S21: After the vehicle system is powered on, the instrument system is started first, and the central control system is started normally. The user uses the high-precision map to complete the commuting trip multiple times according to the navigation route.

[0054] Step S22: During the driving process, the data collection module collects lane data in real time: lane environment data (construction lanes and traffic accident occurrence patterns), lane dynamic data (brake pedaling depth and frequency of the front vehicle and the number of vehicles in the left and right lanes), and lane external data (traffic police road condition adjustment time, road cleaning vehicle operation patterns, etc.). These variables are input parameters for subsequent models and can change over time.

[0055] Step S23: The data extraction module extracts key variables such as the traffic efficiency, congestion time distribution and driving speed distribution of each lane of each road section from the collected lane data. The module calculates the travel time of each road section based on the length of each road section and these key variables.

[0056] Step S24: Check whether the vehicle supports local model training. If yes, jump to step S25; otherwise, end.

[0057] Step S25: The data modeling module combines the high-precision map information with the variable data (from step S22 and step S23), takes the minimum travel time of each road section as the goal, and uses artificial intelligence hardware to train the dynamic lane driving model.

[0058] Step S26: Whether the current dynamic lane training model can predict the lane, if yes, jump to step S27.

[0059] Step S27: Based on the model prediction results, the vehicle can dynamically adjust the lane selection strategy to avoid lanes with high accident frequency and lanes where vehicles are working for construction or cleaning. According to the congestion situation of each road section, the module can also output reasonable lane change decisions to obtain the best lane selection strategy for the current road section.

[0060] Step S28: After each commute, the strategy feedback module compares the actual driving results with the model prediction results, adjusts the model training parameters, and gradually improves the decision accuracy of step S27.

[0061] See also Figure 2 , the vehicle driving path planning system 100 includes: a data acquisition module 110, a lane division module 120, a travel time prediction module 130 and a lane change module 140. The data acquisition module 110 is used to obtain the starting point and the end point of the driving path, and determine the road nodes between the starting point and the end point. The lane division module 120 is used to divide the driving path between the starting point and the end point based on the road nodes to obtain multiple sub-paths, and determine the corresponding lane model and lane attributes according to the type of lanes included in the sub-path; wherein each sub-path includes multiple lanes. The travel time prediction module 130 is used to input the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path into the lane model corresponding to each lane in the next sub-path when the vehicle travels to each road node, and correspondingly predict the travel time of the vehicle in each lane in the next sub-path, and select the lane with the shortest travel time as the target lane, and save the shortest travel time. The lane change module 140 is used to guide the vehicle to change lanes or stay in the target lane, and save the actual travel time.

[0062] For the specific definition of the vehicle driving path planning system, please refer to the definition of the vehicle driving path planning method mentioned above, which will not be repeated here. Each module in the above-mentioned vehicle driving path planning system can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware format, or can be stored in the memory of the computer device in software format, so that the processor can call the corresponding operations of each of the above modules.

[0063] It should be noted that, in order to highlight the innovative part of the present invention, the present embodiment does not introduce modules that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other modules in the present embodiment.

[0064] See also Figure 3 The electronic device 1 may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a vehicle driving path planning program.

[0065] The memory 12 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 12 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 12 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 12 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code for planning the vehicle's driving path, but may also be used to temporarily store data that has been output or is to be output.

[0066] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect various components of the entire electronic device 1, and executes or executes programs or modules stored in the memory 12 (such as a vehicle driving path planning program, etc.), and calls data stored in the memory 12 to execute various functions of the electronic device 1 and process data.

[0067] The processor 13 executes the operating system and various installed applications of the electronic device 1. The processor 13 executes the applications to implement the steps in the above-mentioned vehicle driving path planning.

[0068] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a data acquisition module 110, a lane division module 120, a travel time prediction module 130, and a lane change module 140.

[0069] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium, and the computer-readable storage medium can be non-volatile or volatile. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to perform part of the functions of planning the vehicle driving path described in each embodiment of the present application.

[0070] In summary, the present invention discloses a vehicle driving path planning, system, equipment and medium, which divides the driving path according to the road nodes to obtain multiple sub-paths, and matches the corresponding lane model according to the lane type of the sub-path, so as to accurately obtain the traffic characteristics of each section of the road, thereby improving the accuracy of the prediction. During the driving of the vehicle, the travel time of each lane is dynamically predicted according to the driving data of the previous sub-path and the lane attributes of the next sub-path, and the lane with the shortest travel time is selected as the target lane in real time, so that the vehicle is always in the optimal driving path to improve the traffic efficiency. In addition, by saving the actual travel time and the predicted shortest travel time, the lane model is continuously optimized. It can adapt to the sudden change of traffic environment, break through the static limitations of high-precision maps, and effectively improve the accuracy of travel time prediction. The present invention can not only make up for the static deficiencies of high-precision maps, but also provide more personalized and efficient intelligent driving solutions, especially in dealing with congested sections during peak hours, and has great application potential. Based on the user's commonly used routes, the intelligent driving solution is optimized to enhance the exclusive sense of driving experience. Therefore, the present invention effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0071] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A vehicle driving path planning method, characterized in that: The method comprises: Obtaining the starting point and the end point of the driving path, and determining the road nodes between the starting point and the end point; Based on the road node, the driving path between the starting point and the end point is divided to obtain a plurality of sub-paths, and a corresponding lane model and lane attribute are determined according to the type of lanes included in the sub-paths; wherein each sub-path includes a plurality of lanes; When the vehicle travels to each road node, the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path are input into the lane model corresponding to each lane in the next sub-path, and the travel time of the vehicle in each lane in the next sub-path is predicted accordingly, and the lane with the shortest travel time is selected as the target lane, and the shortest travel time is saved; The vehicle is guided to change lanes or remain in a target lane, and actual travel time is saved.

2. The vehicle driving path planning according to claim 1, characterized in that: The lane model is dynamically updated based on a preset amount of historical driving data. For each type of lane, the process of dynamically updating the lane model includes: Calculate the difference between each historically saved shortest travel time and the corresponding actual travel time; The parameters of the lane model are updated based on the calculated difference, and the lane model is dynamically updated.

3. The vehicle driving path planning according to claim 1, characterized in that: For each sub-path, the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path are input into the lane model corresponding to each lane in the next sub-path, and the travel time of the vehicle in each lane in the next sub-path is predicted accordingly, and the lane with the shortest travel time is selected as the target lane, and the shortest travel time is saved, including: For each lane: the driving data of the vehicle in the previous sub-path and the lane attributes of the lane in the next sub-path are input into the lane model corresponding to the lane, and the travel time of the vehicle in the lane in the next sub-path is predicted accordingly; The travel time of each lane in the next sub-path is sorted, and the lane with the shortest travel time is selected as the target lane; wherein, when the previous sub-path is the first sub-path, the driving data is the average of the pre-stored historical driving data of the driving path.

4. The vehicle driving path planning according to claim 3, characterized in that: The step of inputting the driving data of the vehicle in the previous sub-path and the lane attributes of the lane in the next sub-path into the lane model corresponding to the lane, and correspondingly predicting the travel time of the vehicle in the lane in the next sub-path includes: Clean the driving data of the vehicle on the previous sub-path; The cleaned driving data and the lane attributes of the lane in the next sub-path are input into the lane model corresponding to the lane in the next sub-path, and the travel time of the vehicle in the lane in the next sub-path is predicted accordingly.

5. The vehicle driving path planning according to claim 4, characterized in that: The step of cleaning the driving data of the vehicle on the previous sub-path includes: Determine whether there are missing values ​​in the driving data of the vehicle in the previous sub-path: If yes, linear interpolation is performed on the driving data to obtain interpolated driving data, and data alignment is performed on the interpolated driving data to obtain cleaned driving data; If not, the driving data is aligned to obtain cleaned driving data.

6. The vehicle driving path planning according to claim 1, characterized in that: The lane model is a time series model.

7. The vehicle driving path planning according to claim 6, characterized in that: The time series model is LSTM.

8. A vehicle driving path planning system, characterized in that: The system comprises: A data acquisition module, used to acquire the starting point and the end point of the driving path, and determine the road nodes between the starting point and the end point; A lane division module, for dividing the driving path between the starting point and the end point based on the road node to obtain a plurality of sub-paths, and determining a corresponding lane model and lane attribute according to the type of lanes included in the sub-paths; wherein each sub-path includes a plurality of lanes; A travel time prediction module is used for inputting the driving data of the vehicle in the previous sub-path and the lane attributes of the next sub-path into the lane model corresponding to each lane in the next sub-path when the vehicle travels to each road node, and correspondingly predicting the travel time of the vehicle in each lane in the next sub-path, and selecting the lane with the shortest travel time as the target lane, and saving the shortest travel time; The lane changing module is used to guide the vehicle to change lanes or stay in the target lane and save the actual travel time.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the planning of the vehicle driving path as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is enabled to execute the planning of the vehicle driving path as described in any one of claims 1 to 7.

Images