Navigation path planning method and device, vehicle and storage medium

Abstract

The invention relates to the technical field of path planning, and discloses a navigation path planning method and device, a vehicle and a storage medium, and the method comprises the steps: carrying out the matching of the return identification data of the vehicle in the historical travel with the road identification data of a first road sequence, analyzing the passing map position of the vehicle in the historical travel, and obtaining a navigation path; therefore, the historical driving track of the vehicle is obtained. And finally, determining the current position of the vehicle positioned on the map road, performing path planning in combination with the historical driving track of the vehicle in the first road sequence, and generating a target driving path to assist the vehicle in driving. According to the method, the navigation path is planned by using the historical driving track of the vehicle, the application scene is wide, a large amount of data is not required to be used for model training and reasoning, the processing efficiency is high, and the storage and calculation resources of the vehicle are greatly saved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a navigation path planning method, device, vehicle and storage medium. Background Art

[0002] Navigation path planning for autonomous driving refers to the process of determining a safe, efficient and traffic-compliant route for a vehicle from its starting point to its destination, guiding the vehicle to drive accurately in a complex traffic environment.

[0003] At present, there are two main types of navigation path planning schemes in autonomous driving: static path planning and dynamic path planning. Static navigation path planning collects more road-related information, such as the geographical environment around the road, the length of the road, etc., and then calculates the navigation path in combination with traffic rules and other conditions; dynamic navigation path planning is based on static navigation path planning and adds real-time traffic information to obtain a better driving navigation path. Static navigation path planning is relatively simple, but it does not have much practical significance for actual complex and changeable traffic scenarios; dynamic navigation path planning requires a large amount of data and training to handle all known and unknown autonomous driving scenarios, so as to achieve the safety and reliability required by autonomous driving. The processing time is long and the resource allocation requirements for the vehicle are high. Summary of the invention

[0004] In view of this, the present invention provides a navigation path planning method, device, vehicle and storage medium to solve the problems that the existing static path planning has poor applicability in complex and changeable traffic scenarios, and the dynamic navigation path planning has low processing efficiency and high requirements for resource allocation.

[0005] In a first aspect, the present invention provides a navigation path planning method, the method comprising:

[0006] Acquire historical return data in the historical travel of the vehicle, and acquire a first road sequence and road identification data matching the first road sequence;

[0007] Extracting feedback identification data from historical feedback data, matching the feedback identification data with road identification data, and obtaining a historical driving trajectory of the vehicle on the roads of the first road sequence;

[0008] The current position of the vehicle is determined, and a navigation path is planned according to the current position, the first road sequence, and the historical driving trajectory to generate a target driving path for the vehicle.

[0009] Beneficial effects: The present invention matches the feedback identification data of the vehicle in the historical journey with the road identification data of the first road sequence, and analyzes the map locations passed by the vehicle in the historical journey, thereby obtaining the historical driving trajectory of the vehicle. Finally, the current position of the vehicle on the map road is determined, and the path planning is performed in combination with the historical driving trajectory of the vehicle in the first road sequence, and the target driving path is generated to assist vehicle driving. The present invention uses the historical driving trajectory of the vehicle for navigation path planning, which is applicable to a wide range of scenarios, and does not require the use of a large amount of data for model training and reasoning, with high processing efficiency, which greatly saves the vehicle's storage and computing resources.

[0010] In some optional implementations, performing navigation path planning according to the current position, the first road sequence, and the historical driving trajectory to generate a target driving path for the vehicle includes:

[0011] Obtaining a second road sequence according to roads within a preset surrounding range of the current position;

[0012] Based on the second road sequence, a search is performed in the historical driving trajectory corresponding to the first road sequence to obtain a target historical driving trajectory, and based on the target historical driving trajectory, a target driving path of the vehicle is generated.

[0013] Beneficial effects: The present invention screens roads within a preset surrounding range of the current position of the vehicle to obtain a second road sequence that the vehicle will travel within a certain range in the future, then retrieves the trajectory of the second road sequence in the historical driving trajectory to obtain the target historical driving trajectory, and then generates a navigation path to provide driving guidance for the vehicle. It can navigate the vehicle for the user based on the user's usage habits, is suitable for most navigation scenarios, has high processing efficiency, and consumes less resources on the vehicle.

[0014] In some optional implementations, based on the second road sequence, searching in the historical driving trajectory corresponding to the first road sequence to obtain the target historical driving trajectory includes:

[0015] Generate the target road sequence according to the information used to generate the target road sequence; wherein the information used to generate the target road sequence is one of the following: the second road sequence or the first road and the last road of the second road sequence;

[0016] The historical driving trajectory of the target road sequence is retrieved from the historical driving trajectory corresponding to the first road sequence to obtain the target historical driving trajectory.

[0017] Beneficial effects: The present invention retrieves a target road sequence that is completely consistent with the second road sequence, or that is consistent with the second road sequence from beginning to end, in the first road sequence, to ensure that the starting point and end point of the navigation path planning meet the vehicle driving requirements. Finally, the navigation path is planned according to the target historical driving trajectory associated with the target road sequence, and the target driving path within a certain range in the future of the vehicle is obtained to assist the vehicle in driving, and the target driving path meets the user's historical travel habits, which is conducive to improving the user experience.

[0018] In some optional implementations, matching the returned identification data with the road identification data to obtain a historical driving trajectory of the vehicle on the roads of the first road sequence includes:

[0019] Performing shape matching between the returned identification data and the road identification data to determine the historical position of the vehicle when the returned identification data was collected during the historical trip; wherein the identification data includes at least some of the following items: lane lines, road boundaries, stop lines, and arrows;

[0020] The historical positions of the roads in the first road sequence are spliced ​​to obtain the historical driving trajectory.

[0021] Beneficial effect: The present invention determines the historical locations of the vehicle by matching the shapes and positions of various identification data sent back in the vehicle's historical travel with the road identification data of the map, and then splices the historical locations to form a historical driving trajectory, so as to analyze the user's travel needs and usage habits, provide a basis for navigation path planning, and facilitate finding the fastest and most economical navigation route.

[0022] In some optional implementations, determining the current position of the vehicle includes:

[0023] Get the current feedback data of the vehicle;

[0024] The current position of the vehicle is obtained by matching the current returned data with the road sign data.

[0025] Beneficial effect: The present invention matches the current feedback identification data contained in the current feedback data of the vehicle with the road identification data, locates the vehicle position, and obtains the current road position of the vehicle, so as to use the current position of the vehicle as the navigation starting point for path planning.

[0026] In some optional implementations, acquiring the first road sequence includes:

[0027] Obtain the vehicle map and collect the road network structure data and road attribute information in the vehicle map;

[0028] Based on the historical feedback data and road attribute information, the road network structure data is screened to obtain the first road sequence.

[0029] Beneficial effects: The present invention utilizes the vehicle map to obtain road network structure data and road attribute information, improves data collection efficiency and the applicability of navigation scenarios, and then constructs the first road sequence by removing road scenes with lower road grades and less returned data, and actively selecting some special scenes, so as to improve the safety and reliability of navigation results when performing navigation path planning.

[0030] In some optional implementations, the road network structure data is screened based on the historical feedback data and the road attribute information to obtain a first road sequence, including:

[0031] The roads whose road attribute information in the road network structure data does not meet the road grade condition and / or the roads whose historical return data in the road network structure data does not meet the return data volume condition are removed to obtain a first road sequence.

[0032] Beneficial effects: The present invention removes road scenes with lower road grades and less returned data, and actively selects some special scenes to construct the first road sequence, thereby ensuring the safety and reliability of navigation path planning.

[0033] In a second aspect, the present invention provides a navigation path planning device, the device comprising:

[0034] An acquisition module, used to acquire historical returned data in the historical travel of the vehicle, and to acquire a first road sequence and road identification data matching the first road sequence;

[0035] A processing module, used for extracting feedback identification data from the historical feedback data, matching the feedback identification data with the road identification data, and obtaining a historical driving track of the vehicle on the roads of the first road sequence;

[0036] The generation module is used to determine the current position of the vehicle, perform navigation path planning according to the current position, the first road sequence and the historical driving trajectory, and generate a target driving path for the vehicle.

[0037] In a third aspect, the present invention provides a vehicle, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the navigation path planning method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the navigation path planning method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 is a flowchart of a navigation path planning method according to an embodiment of the present invention;

[0041] Figure 2 is a flowchart of another navigation path planning method according to an embodiment of the present invention;

[0042] Figure 3 is a flowchart of another navigation path planning method according to an embodiment of the present invention;

[0043] Figure 4 is a structural block diagram of a navigation path planning device according to an embodiment of the present invention;

[0044] Figure 5 Schematic diagram of the hardware structure of a vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0046] At present, there are two main types of navigation path planning solutions in autonomous driving: static path planning and dynamic path planning. Static navigation path planning refers to finding the optimal or feasible path from the starting point to the target point for the vehicle when the environmental map information is known and does not change. It calculates the navigation path by collecting more road-related information, such as the geographical environment around the road, the road length, etc., and combining traffic rules and other conditions. Static navigation path planning is relatively simple, but it does not have much practical significance for actual complex and changeable traffic scenes.

[0047] Dynamic navigation path planning is based on static navigation path planning and adds real-time traffic information to obtain a better driving navigation path. It needs to consider dynamic factors such as real-time changes in traffic conditions, the sudden appearance or movement of obstacles, road construction, etc. It needs to rely on a large amount of data and training to handle all known and unknown autonomous driving scenarios to achieve the safety and reliability required for autonomous driving. Therefore, dynamic navigation path planning has high requirements on the resolution of map data, the processing efficiency of the model and the resource allocation of the vehicle.

[0048] Therefore, an embodiment of the present invention provides a navigation path planning method, which can convert the data sent back by the vehicle in the historical formation to the corresponding position of the road, form a historical driving trajectory, and assist the vehicle in navigation path planning, thereby making full use of the prior knowledge of the historical feedback data. It can be used in most driving scenarios and does not need to rely on a large amount of data and models for training, and has low requirements for resource allocation.

[0049] According to an embodiment of the present invention, a navigation path planning method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0050] In this embodiment, a navigation path planning method is provided, which can be used for vehicles performing navigation path planning, such as unmanned vehicles, etc. Figure 1 is a flowchart of a navigation path planning method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0051] Step S101 : acquiring historical feedback data of a vehicle in its historical travel, and acquiring a first road sequence and road identification data matching the first road sequence.

[0052] In some optional implementations, a vehicle map may be obtained, and road network structure data and road attribute information in the vehicle map may be collected. Then, based on the historical feedback data and the road attribute information, the road network structure data may be screened to obtain a first road sequence. Roads whose road attribute information in the road network structure data does not meet the road grade condition, and / or roads whose historical feedback data in the road network structure data does not meet the feedback data volume condition may be removed to obtain the first road sequence.

[0053] Specifically, the Standard Definition Map (SD Map) is generally called the on-board map in the field of vehicle path planning. Compared with the depiction accuracy of the HD map, the accuracy of the on-board map is relatively low, and the details of its road attribute information are generally only the road name, road grade, road connection relationship and road direction. Since the navigation path planning only needs to generate the final navigation route for the vehicle to assist in driving, the on-board map can provide sufficient road network structure data and can be applied to most navigation scenarios. The data collection efficiency is also high, and the SD road network, that is, the road network structure data in the SD map, can be directly obtained by using the road connection relationship.

[0054] Exemplarily, the road grades in the road attribute information can be divided into expressways, first-class highways, second-class highways, third-class highways, fourth-class highways and off-grade highways, among which expressways are multi-lane highways that are specially used for vehicles to travel in different directions and lanes, and fully control the entry and exit; first-class highways are multi-lane highways that are used for vehicles to travel in different directions and lanes, and can control the entry and exit as needed, and the number of lanes is generally four or six lanes in both directions; second-class highways are trunk roads in medium-sized and above cities or roads leading to large industrial and mining areas and ports; third-class highways are general trunk roads connecting counties and cities above the county level; fourth-class highways are branch roads connecting townships, villages, etc.; off-grade highways refer to highways that have been determined to have not reached or have not fully reached the national highway technical standards during the 1979 highway census. The above road classification method is only an example, and the present invention is not limited to this.

[0055] Furthermore, road data with road grades lower than Class IV highways and vehicle feedback data below the data volume threshold can be removed. In addition, special scene roads such as intersections and crossroads can be actively selected to ensure the safety and reliability of navigation path planning.

[0056] In an embodiment of the present invention, the vehicle map is used to obtain road network structure data and road attribute information to improve data collection efficiency and the scope of application of navigation scenarios. Then, by removing road scenes with lower road grades and less returned data and actively selecting some special scenes to construct a first road sequence, the safety and reliability of navigation results are improved when performing navigation path planning.

[0057] Step S102: extracting feedback identification data from the historical feedback data, matching the feedback identification data with the road identification data, and obtaining the historical driving trajectory of the vehicle on the roads of the first road sequence.

[0058] Specifically, the first road sequence is a sequence containing multiple SDRoads, where SDRoad refers to a road in the SD road network. The identification data contains a database of road elements that can be used for matching, such as road boundaries, stop lines, arrows, etc. By matching the identification data sent back by the vehicle in the historical trip with the road identification data corresponding to the SD road network, the map location passed by the vehicle in the previous trip can be obtained, thereby obtaining the historical driving trajectory of the vehicle.

[0059] Step S103, determining the current position of the vehicle, performing navigation path planning according to the current position, the first road sequence and the historical driving trajectory, and generating a target driving path for the vehicle.

[0060] Specifically, the vehicle position in the present invention is not the latitude and longitude position in the traditional sense, but the positioning position of the vehicle on the road in the vehicle map. The current position of the vehicle can also be obtained by matching the identification data currently transmitted back by the vehicle with the road identification data of the SD road network. In this way, the current position of the vehicle in the vehicle map can be obtained, and the path planning can be performed in combination with the historical driving trajectory and the first road sequence associated with the historical driving trajectory to obtain the target driving path.

[0061] The navigation path planning method provided in this embodiment matches the returned identification data of the vehicle in the historical journey with the road identification data of the first road sequence, analyzes the map locations passed by the vehicle in the historical journey, and thus obtains the historical driving trajectory of the vehicle. Finally, the current position of the vehicle located on the map road is determined, and the path planning is performed in combination with the historical driving trajectory of the vehicle in the first road sequence, and the target driving path is generated to assist the vehicle driving. The present invention uses the historical driving trajectory of the vehicle for navigation path planning, which is applicable to a wide range of scenarios, and does not require the use of a large amount of data for model training and reasoning, with high processing efficiency, which greatly saves the vehicle's storage and computing resources.

[0062] In this embodiment, a navigation path planning method is provided, which can be used for vehicles performing navigation path planning, such as unmanned vehicles, etc. Figure 2 is a flowchart of a navigation path planning method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0063] Step S201, obtaining historical return data of the vehicle's historical trip, and obtaining a first road sequence and road identification data matching the first road sequence. Figure 1 The description of step S101 of the illustrated embodiment will not be repeated here.

[0064] Step S202: extracting feedback identification data from the historical feedback data, matching the feedback identification data with the road identification data, and obtaining the historical driving trajectory of the vehicle on the roads of the first road sequence.

[0065] Specifically, the above step S202 includes:

[0066] Step S2021, extracting the feedback identification data from the historical feedback data.

[0067] Specifically, the historical feedback data includes road image information. By identifying the road image information, the feedback identification data contained therein can be extracted, wherein the identification data includes at least some of the following items: lane lines, road boundaries, stop lines, and arrows.

[0068] Step S2022, shape matching is performed on the returned identification data and the road identification data to determine the historical position of the vehicle when the returned identification data was collected in the historical journey.

[0069] Specifically, the historical position of the vehicle on the map road is determined by performing shape matching on elements such as road boundaries, stop lines, arrows, etc. in the returned identification data with corresponding elements in the road identification data. The shape matching method includes but is not limited to point-line matching, 2D-2D matching, line-line matching, line-surface matching, or feature-based matching, and the present invention is not limited thereto.

[0070] In some optional implementations, point-line matching is mainly based on the distance relationship between a point in the calculation space (corresponding to the identification position point in the identification data transmitted back by the vehicle, which can be represented by coordinates) and a line (representing the road segment in the road identification data, such as lane lines, road boundaries, etc., a broken line composed of a series of continuous coordinate points), to determine whether the point is located on or near this line, so as to determine whether the vehicle is on the corresponding road. If the point is located on or near this line, the location of the corresponding road identification data is used as the corresponding historical location.

[0071] In some optional embodiments, 2D-2D matching generally refers to matching data with two-dimensional shape features represented by the vehicle's return identification on a two-dimensional plane (such as the two-dimensional plane shape of a certain area around the vehicle scanned by a vehicle-mounted camera or radar, etc.) with the part of the road sign data that also has two-dimensional shape features (such as shapes depicted by polygons, such as arrows), and determining the road and historical position of the vehicle by measuring the similarity and relative position relationship between the two.

[0072] In some optional implementations, line-to-line matching is mainly performed by matching the stop line, road boundary and other line data in the identification data transmitted back by the vehicle with the lines in the road identification data (which are also lines composed of continuous coordinate points, which may be a combination of single or multiple roads, etc.), and by comparing the geometric features of the two lines (such as length, curvature, direction, etc.) and the relative spatial position relationship, etc. to determine whether the two lines correspond, and then determine the road and historical position of the vehicle.

[0073] Step S2023: splicing the historical positions of the roads in the first road sequence to obtain a historical driving trajectory.

[0074] Specifically, the timestamp on the returned identification data can be obtained, and the historical positions can be spliced ​​according to the corresponding time sequence relationship to obtain a continuous historical driving trajectory.

[0075] The embodiment of the present invention determines the historical locations where the vehicle has passed by by matching the shapes and positions of various identification data returned from the vehicle's historical travel with the road identification data of the map, and then splices the historical locations to form a historical driving trajectory, thereby analyzing the user's travel needs and usage habits, providing a basis for navigation path planning, and facilitating finding the fastest and most economical navigation route.

[0076] Step S203, determining the current position of the vehicle, performing navigation path planning according to the current position, the first road sequence and the historical driving trajectory, and generating a target driving path for the vehicle.

[0077] Specifically, the above step S203 includes:

[0078] Step S2031, obtaining the current feedback data of the vehicle, matching the current feedback data with the road sign data, and obtaining the current position of the vehicle.

[0079] Specifically, the vehicle's current return data contains currently returned identification data, which is matched with the road identification data to locate the vehicle's position and obtain the vehicle's current road position, so that the vehicle's current position can be used as the navigation starting point for path planning.

[0080] Step S2032: Obtain a second road sequence based on roads within a preset surrounding range of the current location.

[0081] Specifically, with the current position as the center, the roads within the surrounding range are screened to obtain a second road sequence that the vehicle will travel within a certain range in the future.

[0082] Step S2033: Based on the second road sequence, a search is performed in the historical driving trajectory corresponding to the first road sequence to obtain a target historical driving trajectory, and based on the target historical driving trajectory, a target driving path of the vehicle is generated.

[0083] Specifically, the target road sequence is generated according to the information used to generate the target road sequence, wherein the information used to generate the target road sequence is one of the following: the second road sequence or the first road and the last road of the second road sequence. Then, the historical driving trajectory of the target road sequence is retrieved from the historical driving trajectory corresponding to the first road sequence to obtain the target historical driving trajectory.

[0084] In the embodiment of the present invention, a target road sequence that is completely consistent with the second road sequence or consistent with the second road sequence from beginning to end is retrieved from the first road sequence to ensure that the starting point and end point of the navigation path planning meet the vehicle driving requirements. Finally, the navigation path is planned according to the target historical driving trajectory associated with the target road sequence to obtain the target driving path within a certain range in the future of the vehicle, which assists the vehicle in driving, and the target driving path meets the user's historical travel habits, which is conducive to improving the user experience.

[0085] The navigation path planning method provided in this embodiment screens roads within a preset surrounding range of the current position of the vehicle to obtain a second road sequence that the vehicle will travel within a certain range in the future, then retrieves the trajectory of the second road sequence in the historical driving trajectory to obtain the target historical driving trajectory, and then generates a navigation path to provide driving guidance for the vehicle. It can navigate the vehicle for the user based on the user's usage habits, is applicable to most navigation scenarios, has high processing efficiency, and consumes less resources on the vehicle.

[0086] The navigation path planning method of the present invention is described in detail below with reference to a specific application example. Figure 3 As shown, the application example includes the following steps:

[0087] Step 1: Data screening based on the road grade of the SD road network and user feedback data.

[0088] Specifically, it is possible to remove data of low-grade roads, actively select roads in special scenarios such as intersections and forks, and remove scenarios with little data sent back by users.

[0089] Step 2: Add user tracks by matching with the localization layer.

[0090] Specifically, the positioning layer stores a database of road elements that can be used for matching, such as road boundaries, stop lines, arrows, etc. First, obtain the first SDRoad sequence for which the user trajectory needs to be laid, and obtain the positioning layer associated with the first SDRoad sequence and the user data that passes through the relevant SDRoad in the first SDRoad sequence. Then, by matching the road boundaries, stop lines, arrows and other elements in the user data with the corresponding elements in the positioning layer, the matching methods include but are not limited to point-line, 2D-2D, line-line, etc., the relative positioning position of the user data in the positioning layer is obtained, and the relative positioning position is recorded as a historical trajectory.

[0091] Step 3: Generate a trajectory layer containing a large number of historical trajectories, each trajectory is associated with a different first SDRoad sequence.

[0092] Step 4: The real vehicle plans the navigation path based on the historical trajectory.

[0093] Specifically, the second SDRoad sequence that the vehicle will travel within a certain range in the future is obtained according to the navigation, and the historical trajectory that is consistent with the second SDRoad sequence or the first and last roads are consistent with the second SDRoad is obtained from the trajectory layer. The vehicle obtains the current positioning position by matching with the positioning layer, and the navigation path planning is performed with reference to the vehicle positioning result and the historical trajectory, and the driving path of the vehicle within a certain range in the future is calculated.

[0094] The present invention converts the trajectory of the user data into the relative position of the positioning layer as the historical trajectory to assist in navigation path planning. It is applicable to a wide range of scenarios and does not require the use of a large amount of data for model training and reasoning. The processing efficiency is high, which greatly saves the vehicle's storage and computing resources.

[0095] In the present embodiment, a navigation path planning device is also provided, and the device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description that has been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0096] This embodiment provides a navigation path planning device, such as Figure 4 As shown, including:

[0097] An acquisition module 401 is used to acquire historical returned data in a historical travel of a vehicle, and to acquire a first road sequence and road identification data matching the first road sequence;

[0098] The processing module 402 is used to extract the feedback identification data in the historical feedback data, match the feedback identification data with the road identification data, and obtain the historical driving trajectory of the vehicle on the roads of the first road sequence;

[0099] The generation module 403 is used to determine the current position of the vehicle, perform navigation path planning according to the current position, the first road sequence and the historical driving trajectory, and generate a target driving path for the vehicle.

[0100] In some optional implementations, the acquisition module 401 is further used to:

[0101] Obtain the vehicle map and collect the road network structure data and road attribute information in the vehicle map;

[0102] Based on the historical feedback data and road attribute information, the road network structure data is screened to obtain the first road sequence.

[0103] In some optional implementations, the acquisition module 401 is further used to:

[0104] The roads whose road attribute information in the road network structure data does not meet the road grade condition and / or the roads whose historical return data in the road network structure data does not meet the return data volume condition are removed to obtain a first road sequence.

[0105] In some optional implementations, the processing module 402 is further configured to:

[0106] Performing shape matching between the returned identification data and the road identification data to determine the historical position of the vehicle when the returned identification data was collected during the historical trip; wherein the identification data includes at least some of the following items: lane lines, road boundaries, stop lines, and arrows;

[0107] The historical positions of the roads in the first road sequence are spliced ​​to obtain the historical driving trajectory.

[0108] In some optional implementations, the generating module 403 is further configured to:

[0109] Get the current feedback data of the vehicle;

[0110] The current position of the vehicle is obtained by matching the current returned data with the road sign data.

[0111] In some optional implementations, the generating module 403 is further configured to:

[0112] Obtaining a second road sequence according to roads within a preset surrounding range of the current position;

[0113] Based on the second road sequence, a search is performed in the historical driving trajectory corresponding to the first road sequence to obtain a target historical driving trajectory, and based on the target historical driving trajectory, a target driving path of the vehicle is generated.

[0114] In some optional implementations, the generating module 403 is further configured to:

[0115] Generate the target road sequence according to the information used to generate the target road sequence; wherein the information used to generate the target road sequence is one of the following: the second road sequence or the first road and the last road of the second road sequence;

[0116] The historical driving trajectory of the target road sequence is retrieved from the historical driving trajectory corresponding to the first road sequence to obtain the target historical driving trajectory.

[0117] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0118] The navigation path planning device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0119] The embodiment of the present invention further provides a vehicle having the above Figure 4 The navigation path planning device shown.

[0120] See also Figure 5 , Figure 5 is a schematic diagram of a vehicle structure provided by an optional embodiment of the present invention, such as Figure 5 As shown, the vehicle includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the vehicle, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0121] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0122] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0123] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created according to the use of the vehicle, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the vehicle via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0124] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0125] The vehicle further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0126] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0127] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0128] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0129] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A navigation path planning method, characterized in that: The method comprises: Acquire historical return data of a historical trip of the vehicle, and acquire a first road sequence and road identification data matching the first road sequence; Extracting feedback identification data from historical feedback data, matching the feedback identification data with road identification data, and obtaining a historical driving trajectory of the vehicle on the roads of the first road sequence; The current position of the vehicle is determined, and a navigation path is planned according to the current position, the first road sequence, and the historical driving trajectory to generate a target driving path for the vehicle.

2. The method according to claim 1, characterized in that The method of performing navigation path planning according to the current position, the first road sequence and the historical driving trajectory to generate a target driving path for the vehicle includes: Obtaining a second road sequence according to roads within a preset surrounding range of the current position; Based on the second road sequence, a search is performed in the historical driving trajectories corresponding to the first road sequence to obtain a target historical driving trajectory, and based on the target historical driving trajectory, a target driving path of the vehicle is generated.

3. The method according to claim 2, characterized in that The step of searching the historical driving trajectories corresponding to the first road sequence based on the second road sequence to obtain the target historical driving trajectory includes: Generate the target road sequence according to the information used to generate the target road sequence; wherein the information used to generate the target road sequence is one of the following: the second road sequence or the first road and the last road of the second road sequence; The historical driving trajectory of the target road sequence is retrieved from the historical driving trajectory corresponding to the first road sequence to obtain the target historical driving trajectory.

4. The method according to claim 1, characterized in that: The matching of the returned identification data with the road identification data to obtain the historical driving trajectory of the vehicle on the roads of the first road sequence includes: Performing shape matching on the returned identification data and the road identification data to determine the historical position of the vehicle when the returned identification data was collected in the historical journey; wherein the identification data includes at least some of the following items: lane lines, road boundaries, stop lines, and arrows; The historical positions of the roads in the first road sequence are spliced ​​to obtain the historical driving trajectory.

5. The method according to claim 4, characterized in that Determining the current position of the vehicle includes: Get the current feedback data of the vehicle; The current position of the vehicle is obtained by matching the current returned data with the road sign data.

6. The method according to any one of claims 1 to 5, characterized in that The step of acquiring the first road sequence comprises: Obtain the vehicle map and collect the road network structure data and road attribute information in the vehicle map; Based on the historical feedback data and road attribute information, the road network structure data is screened to obtain the first road sequence.

7. The method according to claim 6, characterized in that The road network structure data is screened based on the historical feedback data and the road attribute information to obtain a first road sequence, including: The roads whose road attribute information in the road network structure data does not meet the road grade condition and / or the roads whose historical return data in the road network structure data does not meet the return data volume condition are removed to obtain a first road sequence.

8. A navigation path planning device, characterized in that: The device comprises: An acquisition module, used to acquire historical returned data in a historical trip of the vehicle, and to acquire a first road sequence and road identification data matching the first road sequence; A processing module, used for extracting feedback identification data from the historical feedback data, matching the feedback identification data with the road identification data, and obtaining a historical driving track of the vehicle on the roads of the first road sequence; The generation module is used to determine the current position of the vehicle, perform navigation path planning according to the current position, the first road sequence and the historical driving trajectory, and generate a target driving path for the vehicle.

9. A vehicle, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the navigation path planning method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the navigation path planning method according to any one of claims 1 to 7.

Images