Method for generating recommended lane, vehicle, storage medium and computer program product

Abstract

The invention provides a method for generating a recommended lane, a vehicle, a storage medium and a computer program product. The method comprises the following steps: identifying a target road structure scene, and determining a target road range; local lane information in the target road range is obtained from the crowdsourcing data, and the local lane information is used for prompting lane passing directions and / or road structure changes; constructing a target lane level topological relation based on the local lane information; and generating a recommended lane for the target vehicle by using the target lane-level topological relation and the navigation trajectory of the target vehicle. The technical problems of crowdsourcing data redundancy and complex crowdsourcing data processing process in a recommended lane generation method in related technologies are solved.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle data processing, and in particular, to a method for generating recommended lanes, a vehicle, a storage medium, and a computer program product. Background Art

[0002] In intelligent transportation systems and autonomous driving technologies, crowdsourced data is primarily used to construct high-precision maps. This crowdsourced data contains detailed road geometry and lane-level topology to support accurate vehicle positioning and path planning. This process typically involves extracting lane information from a large amount of crowdsourced data, performing data fusion, alignment, and clustering, and ultimately fitting lane centerlines to construct a complete lane-level road topology model. However, existing technologies for generating lane-level information based on crowdsourced data have the following major drawbacks:

[0003] (1) Complex crowdsourcing data processing: Existing technologies require the use of lane-level topological relationships across the entire road section to generate recommended lanes. Therefore, crowdsourcing data processing requires precise spatial alignment and clustering.

[0004] (2) Crowdsourcing data information redundancy: Existing technologies focus on the spatial geometric position of lane lines, that is, the absolute position information, which increases the complexity of map data and the use of storage space.

[0005] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0006] The embodiments of the present disclosure provide a method for generating recommended lanes, a vehicle, a storage medium, and a computer program product to at least address the technical issues of crowdsourced data redundancy and complex crowdsourced data processing in the methods for generating recommended lanes in related technologies.

[0007] According to one embodiment of the present disclosure, a method for generating recommended lanes is provided, comprising: identifying a target road structure scene to determine a target road range; obtaining local lane information within the target road range from crowdsourced data, wherein the local lane information is used to indicate lane travel direction and / or road structure changes; constructing a target lane-level topological relationship based on the local lane information; and generating a recommended lane for the target vehicle using the target lane-level topological relationship and the navigation trajectory of the target vehicle.

[0008] Optionally, the target road structure scenario includes one of the following: a road structure scenario in which the number of lanes changes; a road structure scenario in which roads diverge and merge; and a road structure scenario in which roads meet at intersections.

[0009] Optionally, the crowdsourced data includes: multiple data packets, and obtaining local lane information within the target road range from the crowdsourced data includes: intercepting initial road data within the target road range from the multiple data packets respectively; extracting local identification information from the initial road data, and spatially clustering the local identification information to obtain clustering results corresponding to the multiple data packets; performing data alignment on the clustering results corresponding to the multiple data packets to obtain data alignment results; extracting local lane information from the data alignment results, wherein the local lane information includes: category turning information of multiple identification groups within the target road range, and the multiple identification groups each include multiple indicator signs along the direction of travel of the road.

[0010] Optionally, constructing a target lane-level topological relationship based on local lane information includes: establishing a connection between multiple identification groups contained in the local lane information to obtain an initial lane-level topological relationship; filtering the initial lane-level topological relationship based on preset filtering conditions to obtain a target lane-level topological relationship, wherein the preset filtering conditions are determined based on road traffic conditions and / or lane crossing driving experience within the target road range.

[0011] Optionally, establishing a connection between multiple identification groups included in the local lane information to obtain an initial lane-level topological relationship includes: using a full connection method to establish a connection between every two adjacent identification groups in the multiple identification groups included in the local lane information to obtain an initial lane-level topological relationship.

[0012] Optionally, generating a recommended lane for the target vehicle using the target lane-level topological relationship and the navigation trajectory of the target vehicle includes: selecting candidate identifications from multiple indication identifications included in multiple identification groups using the target lane-level topological relationship and the navigation trajectory of the target vehicle; determining candidate lanes based on the candidate identifications; and generating a recommended lane for the target vehicle from the candidate lanes according to preset lane recommendation criteria, wherein the preset lane recommendation criteria is determined based on the smoothness of traffic and / or lane change flexibility of the candidate lanes.

[0013] Optionally, the method for generating recommended lanes also includes: using preset interface elements to display the candidate identification and the recommended identification corresponding to the recommended lane, wherein the preset interface elements adopt a grid arrangement, and the multiple rows of grids in the grid arrangement correspond to multiple identification groups respectively, and the multiple rows of grids each contain multiple cells, and the multiple cells contained in the same row of grids correspond to multiple indicator identifications contained in the same identification group respectively.

[0014] Optionally, using a preset interface element to display the candidate identification and the recommended identification corresponding to the recommended lane includes: in the preset interface element, using a first cell display method to display the candidate identification, and using a second cell display method to display the recommended identification, wherein the first cell display method and the second cell display method respectively use different special effects to distinguish different identification objects.

[0015] According to one embodiment of the present disclosure, a device for generating recommended lanes is also provided, including: an identification module for identifying a target road structure scene and determining a target road range; an acquisition module for acquiring local lane information within the target road range from crowdsourced data, wherein the local lane information is used to indicate lane travel direction and / or road structure changes; a construction module for constructing a target lane-level topological relationship based on the local lane information; and a generation module for generating a recommended lane for the target vehicle by utilizing the target lane-level topological relationship and the navigation trajectory of the target vehicle.

[0016] Optionally, the target road structure scenario includes one of the following: a road structure scenario in which the number of lanes changes; a road structure scenario in which roads diverge and merge; and a road structure scenario in which roads meet at intersections.

[0017] Optionally, the acquisition module is also used to: intercept initial road data within the target road range from multiple data packets respectively; extract local identification information from the initial road data, and spatially cluster the local identification information to obtain clustering results corresponding to each of the multiple data packets; perform data alignment on the clustering results corresponding to each of the multiple data packets to obtain data alignment results; extract local lane information from the data alignment results, wherein the local lane information includes: category turning information of multiple identification groups within the target road range, and the multiple identification groups all contain multiple indicator signs along the direction of travel of the road.

[0018] Optionally, the construction module is also used to: build connections between multiple identification groups contained in the local lane information to obtain an initial lane-level topological relationship; filter the initial lane-level topological relationship based on preset filtering conditions to obtain a target lane-level topological relationship, wherein the preset filtering conditions are determined based on the road traffic conditions and / or lane crossing driving experience within the target road range.

[0019] Optionally, the construction module is further configured to: establish a connection between every two adjacent identification groups in the plurality of identification groups included in the local lane information in a fully connected manner, so as to obtain an initial lane-level topological relationship.

[0020] Optionally, the generation module is also used to: utilize the target lane-level topological relationship and the navigation trajectory of the target vehicle to select candidate identifications from multiple indicator identifications contained in multiple identification groups; determine candidate lanes based on the candidate identifications; and generate a recommended lane for the target vehicle from the candidate lanes according to preset lane recommendation criteria, wherein the preset lane recommendation criteria is determined based on the smoothness of traffic and / or lane change flexibility of the candidate lanes.

[0021] Optionally, the device for generating recommended lanes also includes a display module for displaying the candidate identification and the recommended identification corresponding to the recommended lane using preset interface elements, wherein the preset interface elements are arranged in a grid, and the multiple rows of grids in the grid arrangement correspond to multiple identification groups respectively, and the multiple rows of grids each contain multiple cells, and the multiple cells contained in the same row of grids correspond to multiple indicator identifications contained in the same identification group respectively.

[0022] Optionally, the display module is also used to: in the preset interface elements, display candidate logos using a first cell display method, and display recommended logos using a second cell display method, wherein the first cell display method and the second cell display method respectively use different special effects to distinguish different logo objects.

[0023] According to one embodiment of the present disclosure, an electronic device is further provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present disclosure when running.

[0024] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present disclosure.

[0025] According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present disclosure is implemented.

[0026] According to another aspect of an embodiment of the present disclosure, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present disclosure is implemented.

[0027] In the disclosed embodiment, a target road structure scene is identified, the target road range is determined, and local lane information within the target road range is obtained from crowdsourced data. A target lane-level topological relationship is constructed based on the local lane information, and a recommended lane is generated for the target vehicle using the target lane-level topological relationship and the navigation trajectory of the target vehicle. By utilizing the local sparse features and local lane information in the crowdsourced data to generate recommended lanes for the target vehicle, the purpose of quickly and efficiently generating recommended lanes is achieved, thereby achieving the technical effect of simplifying lane line information and reducing the complexity of the lane line processing process, and further solving the technical problems of crowdsourced data redundancy and complex crowdsourced data processing process in the method of generating recommended lanes in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0029] Figure 1 is a hardware structure diagram of a data processing method according to one embodiment of the present disclosure;

[0030] Figure 2 is a flowchart of a method for generating a recommended lane according to one embodiment of the present disclosure;

[0031] Figure 3 is a schematic diagram of a method for generating a recommended lane according to one embodiment of the present disclosure;

[0032] Figure 4A is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0033] Figure 4B is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0034] Figure 4C is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0035] Figure 5A is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0036] Figure 5B is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0037] Figure 6A is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0038] Figure 6B is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0039] Figure 7A is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0040] Figure 7B is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure;

[0041] Figure 8 The present invention is a block diagram of a device for generating a recommended lane according to one embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0043] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] According to an embodiment of the present disclosure, a method embodiment of a method for generating a recommended lane 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.

[0045] The method embodiment can be executed in an electronic device or similar computing device including a memory and a processor. Taking running on a computer terminal as an example, the computer terminal may include one or more processors (processors may include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a programmable logic device (Field Programmable Gate Array, FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, etc.) and a memory for storing data. Optionally, the above-mentioned computer terminal may also include a transmission device, an input and output device, and a display device for communication functions. It will be understood by those skilled in the art that the above-mentioned structural description is only illustrative and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include more or fewer components than the above-mentioned structural description, or have a configuration different from the above-mentioned structural description.

[0046] The memory can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the method for generating recommended lanes in the embodiments of the present disclosure. The processor executes the computer program stored in the memory to perform various functional applications and data processing, thereby implementing the above-mentioned method for generating recommended lanes. The memory can include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0047] The transmission device is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the mobile terminal's communications provider. In one embodiment, the transmission device includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one embodiment, the transmission device may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0048] The display device can be, for example, a touch-screen liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display can enable the user to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and the user can interact with the GUI by finger contacts and / or gestures on the touch-sensitive surface. The human-computer interaction functions here optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for performing the above-mentioned human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0049] An embodiment of the present application provides a method for generating recommended lanes. The method for generating recommended lanes can be used to provide a lane recommendation function for preset application scenarios. The above-mentioned preset application scenarios may include the following scenarios in the vehicle field: commuting autonomous driving scenarios, artificial intelligence (AI) driving scenarios for family cars, automatic parking assistance (APA) scenarios (such as memory parking for owned parking spaces in garages, smart parking for designated parking spaces in parking lots, etc.), and intelligent navigation assistance (Navigation Guided Pilot, NGP) scenarios in urban areas or highway areas. In addition, the above-mentioned preset application scenarios may also include but are not limited to: driving scenarios of smart driving trucks or unmanned trucks in the field of logistics and transportation, driving scenarios of self-driving agricultural vehicles in the field of agricultural machinery, path planning scenarios of drones, and path planning scenarios of intelligent robots (such as cleaning robots, service robots, delivery robots, etc.).

[0050] When the aforementioned preset application scenarios are scenarios in fields other than the vehicle field, those skilled in the art will appreciate that the vehicles in the aforementioned method for generating recommended lanes can be replaced with other objects (such as agricultural machinery, drones, robots, etc.). Based on this, the embodiments of this application use the vehicle technology field as an example to illustrate the specific implementation of the aforementioned method for generating recommended lanes.

[0051] Figure 1 is a hardware structure diagram of a data processing method according to one embodiment of the present disclosure, such as Figure 1 As shown, the hardware structure includes: terminal equipment, vehicles and roadside equipment.

[0052] Exemplarily, terminal devices generally refer to smart devices involved in communication, including but not limited to the target vehicle itself, mobile positioning terminals (such as smart phones, smart wearable devices, and vehicle-mounted communication systems of other vehicles), etc. The above-mentioned devices collect environmental data through built-in sensors, or collect information through user interaction, and then transmit the collected data to the cloud server or the target vehicle's on-board control unit through the network for analysis and processing. The network includes but is not limited to cellular networks (such as 4G, 5G), Wi-Fi, Bluetooth, Vehicle-to-Everything (V2X) and other technologies, which are responsible for real-time data transmission to ensure that the vehicle can promptly receive location information and status data shared by other vehicles, pedestrians, roadside equipment, etc. Roadside equipment refers to equipment installed on the side of the road for monitoring and sensing the road environment, including but not limited to radars, cameras, infrared sensors, meteorological sensors, traffic light controllers, etc. The data collected by the roadside equipment is transmitted to the vehicle or cloud server through the network for vehicle control and traffic management.

[0053] Furthermore, a terminal device can issue a driving scene switching command and send it to the vehicle via the network. Upon receiving the driving scene switching command from the terminal device, the vehicle sends an information subscription request to the roadside device. The roadside device receives the information subscription request from the vehicle and transmits the continuously collected roadside perception information back to the vehicle.

[0054] Figure 2 is a flow chart of a method for generating a recommended lane according to one embodiment of the present disclosure. Figure 2 As shown, the method includes the following steps:

[0055] Step S20, identifying the target road structure scene and determining the target road range;

[0056] Step S22: obtaining local lane information within the target road range from crowdsourced data, wherein the local lane information is used to indicate lane direction and / or road structure changes;

[0057] The crowdsourced data described above is used to represent road information collected by numerous drivers or vehicles through on-board sensors, smartphones, and other devices while driving. Crowdsourced data includes, but is not limited to: vehicle location, which is the real-time location of a vehicle obtained through GPS or other positioning technologies; vehicle trajectory, which records the vehicle's travel path and can be used to analyze common routes and driving patterns; lane information, which is lane image data captured by sensors such as on-board cameras or lidar, used to identify lane structure and boundaries; traffic signs and signals, including speed limit signs, no-entry signs, and directional arrows; and road conditions, such as road surface quality, traffic congestion, and construction areas.

[0058] Step S24, constructing a target lane-level topological relationship based on the local lane information;

[0059] The above-mentioned local lane information is used to represent the type of turning information of the arrow mark within the target road range in the lane. The type of turning information of the arrow mark is used to indicate the lane's direction of travel and / or changes in the road structure.

[0060] For example, Figure 3 is a schematic diagram of a method for generating a recommended lane according to one embodiment of the present disclosure, such as Figure 3 As shown in the figure, according to the direction of travel from right to left, there are three groups of arrows 301, 302 and 303, which are local lane information. The arrows are sorted from bottom to top, and the turning information of each group of arrows is as follows: (1) 301: turn left, go straight, go straight, go straight, turn right, turn right; (2) 302: turn left, turn left, go straight, go straight, go straight, turn right; (3) 303: turn left, turn left, go straight, go straight, go straight, turn right.

[0061] Step S26 , using the target lane-level topological relationship and the navigation trajectory of the target vehicle, a recommended lane is generated for the target vehicle.

[0062] The navigation trajectory of the target vehicle is used to represent the driving trajectory provided by the navigation system to the target vehicle.

[0063] For example, first, the target road structure scenario for which recommended lanes need to be generated is identified from the entire road network, and the target road range is determined based on the target road structure scenario. The target road structure scenario can be identified through techniques such as pattern recognition, image analysis, or location-based event detection. Then, the local lane information of the road section is extracted from the crowdsourced data, and the marking groups in the lanes are identified based on the local lane information. The spatial relationship between the marking groups is determined to construct the target lane-level topological relationship. Finally, the target lane-level topological relationship and the navigation trajectory of the target vehicle are combined to generate the recommended lanes. Lanes that are consistent with the target vehicle's driving direction, have good road conditions, and are flexible in lane changes are selected as candidate lanes, and the optimal lane is selected from them as the recommended lane based on the preset lane recommendation criteria.

[0064] Based on the above steps S20 to S26, the target road structure scene is identified, the target road range is determined, and local lane information within the target road range is obtained from crowdsourced data. A target lane-level topological relationship is constructed based on the local lane information, and the target lane-level topological relationship and the navigation trajectory of the target vehicle are used to generate recommended lanes for the target vehicle. By utilizing the local sparse features and local lane information in the crowdsourced data to generate recommended lanes for the target vehicle, the purpose of quickly and efficiently generating recommended lanes is achieved, thereby achieving the technical effect of simplifying lane line information and reducing the complexity of the lane line processing process, and thus solving the technical problems of crowdsourced data redundancy and complex crowdsourced data processing process in the method of generating recommended lanes in the related art.

[0065] Optionally, the target road structure scenario includes one of the following:

[0066] Road structure scenarios with varying number of lanes;

[0067] The above-mentioned road structure scenario with a changing number of lanes is used to represent that in a road network, the number of lanes in certain sections may increase or decrease due to changes in design requirements or road functions.

[0068] For example, lane additions typically occur at the transition point between low-density and high-density areas, or when converting from one-way to two-way roads. The goal is to increase road capacity, disperse traffic flow, and reduce congestion, particularly on roads entering city centers or near transportation hubs (such as train stations and airports).

[0069] For example, lane reduction is common when a road changes from a wide area to a narrow area, or when lanes are reduced to reserve space for specific facilities (such as bus stops and bicycle lanes). Lane reduction may cause traffic flows to merge and increase the need for drivers to change lanes.

[0070] For example, Figure 4AFIG. 1 is a schematic diagram of another method for generating recommended lanes according to one embodiment of the present disclosure, which shows a road structure scenario with a changing number of lanes. Figure 4A As shown, from Figure 4A As can be seen from the arrow direction, the number of lanes decreases along the arrow direction.

[0071] Road structure scenarios where roads diverge and merge;

[0072] The above-mentioned road structure scenario of road bifurcation and confluence is used to represent the locations in the road network where vehicle driving paths separate or merge. Among them, road bifurcation is used to represent that a road is divided into two or more roads at a certain point, and road confluence is used to represent that two or more roads are merged into one road at a certain point.

[0073] For example, Figure 4B FIG. 1 is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure, which shows a road structure scene where roads diverge and merge. Figure 4B As shown, along the direction of the solid arrow, it can be seen that the bifurcated roads along the direction of the solid arrow merge; along the direction of the dotted arrow, it can be seen that the bifurcated roads along the direction of the dotted arrow diverge.

[0074] Road structure scene at a road intersection.

[0075] The above-mentioned road intersection is used to represent the location where two or more roads intersect. The road structure scenes of road intersections include but are not limited to the following types:

[0076] (1) Intersection: Four roads intersect at right angles. There are usually lanes in four directions. Each direction may have a through lane, a left-turn lane, and a right-turn lane.

[0077] (2) T-junction: Two roads form a T-shaped intersection. Vehicles in one direction have the choice of going straight or turning, while vehicles in the other direction can usually only go straight.

[0078] (3) Five-way intersection: Five roads intersect, forming a more complex traffic structure than a crossroads. Drivers need to choose the correct driving direction according to road signs and traffic lights.

[0079] (4) Roundabout: In this type of intersection design, vehicles travel around the central island, exit the roundabout through the exit lane, and enter other roads. The lanes inside the roundabout are usually more complex and need to follow specific rules.

[0080] For example, Figure 4C FIG. 1 is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure, which shows an intersection in a road structure scene of a road intersection. Figure 4C As shown, four roads intersect at right angles. There are usually lanes in four directions, and each direction may have a through lane, a left turn lane, and a right turn lane.

[0081] Optionally, in step S22, the crowdsourced data includes: a plurality of data packets, and obtaining local lane information within the target road range from the crowdsourced data includes:

[0082] Step S221, intercepting initial road data within the target road range from multiple data packets respectively;

[0083] The above-mentioned multiple data packets include single crowdsourced data provided by the target vehicle within the target road range and other crowdsourced data provided by surrounding vehicles.

[0084] Step S222: extracting local identification information from the initial road data, and performing spatial location clustering on the local identification information to obtain clustering results corresponding to the plurality of data packets;

[0085] The above-mentioned local marking information is used to represent the arrow marking information in the lane, wherein the arrow marking information in the lane can indicate the lane's passing direction and / or changes in the road structure.

[0086] Exemplarily, the initial road data within the target road range is first intercepted from each crowdsourced data, wherein the initial road data includes but is not limited to information such as arrow marks, traffic signs, lane lines, etc. Then, the arrow mark information is extracted from the initial road data, and the arrow marks in each data packet are identified and extracted, including their direction (left turn, straight ahead, right turn, etc.) and position information in the image. Then, the local mark information is spatially clustered, and the extracted arrow marks are clustered according to their actual spatial positions on the map. Even if the image positions or angles of the arrow marks in different data packets are slightly different, as long as their positions on the map are close, they will be classified into the same group, thereby identifying the main arrow marks on each lane, that is, the clustering results corresponding to multiple data packets.

[0087] Step S223, performing data alignment on the clustering results corresponding to the plurality of data packets to obtain a data alignment result;

[0088] For example, lane line-assisted alignment is used to ensure that the position and direction information of all arrow marks correspond to each other, so as to reduce inconsistencies caused by factors such as vehicle angle, speed or sensor accuracy. That is, the lane lines within the arrow range are intercepted to align the clustering results corresponding to multiple data packets to obtain data alignment results. Alternatively, the coordinates of the arrow marks in different data packets are converted to a common reference coordinate system for easy comparison and matching. Compare the arrow marks on the same lane in different data packets, calibrate the positions of the arrow marks by matching the spatial position and steering information, and ensure that they are consistently represented on the map. For example, if part of the arrow is missing in a data packet, the data can be calibrated by comparing and supplementing the arrow information with the adjacent data packets.

[0089] Step S224 , extracting local lane information from the data alignment result, wherein the local lane information includes: category turning information of multiple sign groups within the target road range, and each of the multiple sign groups includes multiple indicator signs along the road travel direction.

[0090] For example, the arrows in the data alignment results are parsed to extract lane direction information. The arrow sequence on each lane is examined to identify consecutive arrow groups. These groups are arranged along the road's direction of travel, indicating the lane's direction of travel. For each identified arrow group, turn information is extracted, including the specific arrow type (left turn, straight ahead, right turn, etc.) and the turn direction.

[0091] For example, Figure 3 Take the arrow group information in the 301 box as an example. If the perception is complete, it is turn left, go straight, go straight, go straight and turn right, and turn right. However, due to occlusion and other reasons, the result of a single perception may be incomplete, which will inevitably lead to missing arrows. The perception result of one time may be turn left, go straight, go straight, go straight and turn right; the result of another perception may be go straight, go straight and turn right, and then the position and type can still be turned left, go straight, go straight, go straight and turn right, and turn right. If you need to use lane lines to assist in alignment, you can intercept the lane lines within the arrow range, such as Figure 3 The lane lines are framed by 301, 302, and 303. After crowdsourced data alignment, a set of arrow information is directly extracted, that is, the category and direction information of each arrow from top to bottom along the road direction are identified.

[0092] Based on the above optional embodiments, initial road data within the target road range is intercepted from multiple data packets respectively; local identification information is extracted from the initial road data, and the local identification information is spatially clustered to obtain clustering results corresponding to each of the multiple data packets; data alignment is performed on the clustering results corresponding to each of the multiple data packets to obtain data alignment results; local lane information is extracted from the data alignment results, which can comprehensively utilize crowdsourced data from different vehicles, increase data diversity and coverage, and improve the accuracy and completeness of information extraction. In addition, the extracted local identification information is spatially clustered to identify arrow signs on lanes and distinguish changes in different lanes or road structures, reducing information confusion caused by vehicle position, angle or sensor errors, and improving data reliability.

[0093] Optionally, in step S24, constructing a target lane-level topological relationship based on the local lane information includes:

[0094] Step S241: establishing connections between multiple identification groups included in the local lane information to obtain an initial lane-level topological relationship;

[0095] Exemplarily, the connection relationship between the extracted multiple sign groups (including multiple arrow signs along the road travel direction, such as left turn, straight go, and right turn arrows) is converted into a topological structure to form an initial lane-level topological relationship.

[0096] In step S242, the initial lane-level topology relationship is filtered based on a preset filtering condition to obtain a target lane-level topology relationship, wherein the preset filtering condition is determined based on the road traffic conditions within the target road range and / or the lane-crossing driving experience.

[0097] The above preset filtering conditions include but are not limited to:

[0098] (1) Road traffic rules: Consider the real and imaginary nature of lane lines, such as not being able to change lanes across solid lines.

[0099] (2) Driving experience: Avoid changing lanes continuously across multiple lanes, as this not only increases driving difficulty but also reduces driving safety.

[0100] For example, because the initially constructed lane-level topology may contain some connections that do not conform to actual road conditions or driving experience, these connections need to be filtered to ensure that the final lane-level topology is reasonable and practical. For example, lane changes across solid lines or lane changes across multiple lanes are not consistent. By applying preset filtering conditions, these unreasonable connections are deleted or corrected, and the remaining connections will form the target lane-level topology, which is more realistic.

[0101] Based on the above optional embodiment, a connection is established between multiple identification groups included in the local lane information to obtain an initial lane-level topological relationship; based on preset filtering conditions, the initial lane-level topological relationship is filtered to obtain a target lane-level topological relationship. By constructing the target lane-level topological relationship, the connection and turning relationship between lanes can be more intuitively represented, thereby simplifying the processing process of crowdsourced data. By applying preset filtering conditions to filter the initial lane-level topological relationship, it is ensured that the final target lane-level topological relationship is more in line with actual road traffic conditions and driving experience, reducing the problem of inaccurate lane connections caused by redundancy or errors in crowdsourced data, and improving the accuracy of recommended lanes.

[0102] Optionally, in step S241, establishing connections between multiple identification groups included in the local lane information to obtain an initial lane-level topological relationship includes:

[0103] In step S401 , a full connection method is used to establish a connection between every two adjacent identification groups in the plurality of identification groups included in the local lane information to obtain an initial lane-level topological relationship.

[0104] For example, along the road's travel direction, based on two adjacent groups of arrows (including multiple arrows along the road's travel direction, such as left-turn, straight-ahead, and right-turn arrows), a connection relationship between the arrows is generated, i.e., the initial lane-level topology. This process uses a fully connected approach, meaning that each arrow in the preceding group is connected to each arrow in the following group, to obtain the initial lane-level topology.

[0105] For example, Figure 5A is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure, such as Figure 5A As shown, Figure 3Connections are established between the three groups of identifiers 301, 302, and 303 in the image to obtain the initial lane-level topology. A fully connected approach is used, establishing connections between 301 and 302, and between 302 and 303. Taking the straight arrow 102 in 301 as an example, this arrow is connected to each arrow in 302, and different colors are used to indicate the possible connection relationships between the arrows. For example, green represents the most likely, yellow represents possible but with user experience issues, red represents continuous lane crossing, and black represents a complete prohibition. The corresponding connection relationships between the straight arrow in 301 and each arrow in 302 are as follows: between 102 and 201, continuous lane crossing is prohibited; between 102 and 202, it is possible but with user experience issues; between 102 and 203, it is the most likely; between 102 and 204, it is possible but with user experience issues; between 102 and 205, continuous lane crossing is prohibited; and between 102 and 206, it is completely prohibited. In the same way, a connection is established between 302 and 303. Taking the straight arrow 203 in 302 as an example, this arrow is connected to each arrow in 303, and different colors are used to represent the possible corresponding connection relationships between the arrows. The corresponding connection relationships between the straight arrows in 302 and each arrow in 303 are as follows: between 203 and 401, continuous lane crossing is prohibited, between 203 and 402, it is feasible but there will be experience problems, between 203 and 403 is the most likely, between 203 and 404, it is feasible but there will be experience problems, between 203 and 405, continuous lane crossing is prohibited, and between 203 and 406, it is completely prohibited.

[0106] For example, since the initially constructed lane-level topology may contain some connections that do not conform to actual road traffic conditions or driving experience, these connections need to be filtered to ensure that the final lane-level topology is reasonable and practical. Figure 5B is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure, such as Figure 5B As shown, Figure 5A Based on the initial lane-level topological relationship in the algorithm, the preset filtering conditions are used to filter the initial lane-level topological relationship to obtain the target lane-level topological relationship. Figure 5B The arrows shown in the figure represent the most likely connections between the arrows in the three identification groups 301, 302 and 303. Specifically, they are: 101-201-401; 101-202-402; 102-203-403; 103-204-404; 104-205-305; 104-206-306; 105-206-306.

[0107] Based on the above optional embodiment, a full connection method is adopted to establish a connection between each two adjacent identification groups in the multiple identification groups included in the local lane information to obtain an initial lane-level topological relationship. The full connection method can quickly establish connections between adjacent identification groups without the need for complex logical judgment or additional data processing steps, thereby speeding up the construction of the initial lane-level topological relationship and making the entire processing flow more efficient.

[0108] Optionally, in step S26, generating a recommended lane for the target vehicle using the target lane-level topological relationship and the navigation trajectory of the target vehicle includes:

[0109] Step S261, using the target lane-level topological relationship and the navigation trajectory of the target vehicle, respectively selecting candidate markers from a plurality of indicator markers included in a plurality of marker groups;

[0110] For example, the navigation trajectory of the target vehicle is analyzed, that is, the direction in which the target vehicle is about to travel (such as turning left, going straight, or turning right). Then, from the target lane-level topology, all indicator marks (arrow marks) that match the navigation trajectory direction are found and used as candidate marks for subsequent lane selection.

[0111] Step S262, determining a candidate lane based on the candidate identifier;

[0112] The candidate lanes are used to represent one or more lanes that the navigation system provides for the target vehicle to pass through.

[0113] For example, once a candidate marker is determined, lanes containing the candidate marker are identified based on lane-level topology. Lanes containing the candidate marker are considered candidate lanes. During this process, all possible candidate lanes are considered to prepare for the next step of lane recommendation.

[0114] Step S263: Generate a recommended lane for the target vehicle from the candidate lanes according to a preset lane recommendation criterion, wherein the preset lane recommendation criterion is determined based on the smoothness of traffic and / or lane change flexibility of the candidate lanes.

[0115] The above-mentioned preset lane recommendation criteria include but are not limited to: recommending a central lane, increasing the flexibility of the target vehicle, recommending a road with smooth traffic, and improving the driving experience.

[0116] For example, a lane candidate is selected from the candidate lanes based on pre-set lane recommendation criteria as the recommended lane for the target vehicle. These pre-set lane recommendation criteria take into account lane flow and lane change flexibility, aiming to provide an optimal driving experience. For example, a central lane is preferred because it generally increases the vehicle's maneuverability at intersections. Additionally, lanes where the vehicle can navigate smoothly are prioritized, avoiding lanes that may be congested or have poor driving conditions.

[0117] Based on the above optional embodiment, the target lane-level topological relationship and the navigation trajectory of the target vehicle are utilized to select candidate identifications from multiple indicator identifications included in multiple identification groups; candidate lanes are determined based on the candidate identifications; and according to preset lane recommendation criteria, a recommended lane is generated for the target vehicle from the candidate lanes. This not only makes full use of the local lane information in the crowdsourced data, but also combines the actual driving needs of the vehicle, making the selection of the recommended lane more accurate and efficient.

[0118] Optionally, the method for generating a recommended lane further includes:

[0119] In step S27, a preset interface element is used to display the candidate identification and the recommended identification corresponding to the recommended lane. The preset interface element is arranged in a grid. The multiple rows of grids in the grid arrangement correspond to multiple identification groups respectively. The multiple rows of grids each contain multiple cells. The multiple cells contained in the same row of grids correspond to multiple indicator identifications contained in the same identification group respectively.

[0120] For example, the current or drivable lanes on the road after a certain distance are determined according to the navigation direction. Figure 6A is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure, Figure 5B Take the arrow identification information in as an example, because the arrow information in 302 and 303 is the same, the arrows in 301 and 302 are used as an example. For the arrow information in 301, the arrow information in 301 is displayed in a grid arrangement, wherein the multiple rows of grids in the grid arrangement correspond to the arrow information in 301 respectively, and the multiple rows of grids contain multiple cells, and the multiple cells contained in the same row of grids correspond to the multiple indicator signs contained in 301 respectively. The arrow information in 301 is along the direction of travel of the road, from left to right 101-105: turn left-go straight-go straight-go straight and turn right-turn right. For the navigation trajectory of turning left, the corresponding candidate identifier is the arrow identifier 101 on the far left; for the navigation trajectory of going straight, the corresponding candidate identifiers are the three straight arrow identifiers 102-104 in the middle; for the navigation trajectory of turning right, the corresponding candidate identifier is the arrow identifier 105 on the far right with a right turn. Therefore, the candidate identifiers generated for the navigation trajectories of turning left, going straight, and turning right are as follows. Figure 6A As shown, the arrows represent multiple indicator identifiers included in the same identifier group, and the hollow arrows represent candidate identifier information.

[0121] For example, Figure 6B is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure. Figure 6BThe candidate identifiers generated by the arrow in 302. For the arrow information in 302, the arrow information in 302 is displayed in a grid arrangement, wherein the multiple rows of grids in the grid arrangement correspond to the arrow information in 302 respectively, and the multiple rows of grids contain multiple cells, and the multiple cells contained in the same row of grids correspond to the multiple indicator identifiers contained in 302 respectively. Along the direction of travel on the road, from left to right 201-206 are: turn left-turn-straight-straight-straight-right turn. For the navigation trajectory of turning left, the corresponding candidate identifiers are the arrow identifiers 201-202 for turning left on the left; for the navigation trajectory of going straight, the corresponding candidate identifiers are the three straight arrow identifiers 203-205 in the middle; for the navigation trajectory of turning right, the corresponding candidate identifier is the arrow identifier 206 with a right turn on the far right. Therefore, the candidate identifiers generated for the navigation trajectories of turning left, going straight, and turning right are as follows Figure 6B As shown, the arrows represent multiple indicator identifiers included in the same identifier group, and the hollow arrows represent candidate identifier information.

[0122] Exemplarily, the recommended identifier is determined based on the candidate identifiers, and the recommended identifier is highlighted.

[0123] Based on the above optional embodiment, preset interface elements are used to display the candidate identifiers and the recommended identifiers corresponding to the recommended lanes, so that the user can see the candidate identifiers of each lane and turn at a glance. This intuitive display method helps the user understand and make decisions more quickly.

[0124] Optionally, in step S27, using a preset interface element to display the candidate identifier and the recommended lane corresponding identifier includes:

[0125] Step S271: In the preset interface element, candidate identifiers are displayed in a first cell display mode, and recommended identifiers are displayed in a second cell display mode. The first cell display mode and the second cell display mode respectively use different special effect distinction modes for different identifier objects.

[0126] For example, in the preset interface elements, different special effects are used to distinguish candidate logos from recommended logos, so that users can intuitively see which are recommended logos and which are just candidate logos. For example, special effects such as color, border, and background are used to distinguish candidate logos from recommended logos.

[0127] For example, the recommended lane is obtained based on candidate lanes, crowdsourced data statistics, and real driving experience. For a certain navigation direction, when there is only one lane in the corresponding candidate lanes, then this lane must be the only recommended lane. When there are multiple candidate lanes for a certain navigation direction, according to the preset lane recommendation criteria, a candidate lane is selected from the candidate lanes as the recommended lane for the target vehicle. Based on the preset lane recommendation criteria, Figure 6A The recommended lanes for each navigation direction are as follows Figure 7A As shown, Figure 6B The recommended lanes for each navigation direction are as follows Figure 7B As shown, the recommended lane markers and candidate lane markers are distinguished by different special effects to remind the driver.

[0128] For example, Figure 7A is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure, Figure 6A For example, when the navigation direction is to turn left, Figure 7A The first cell in the first row of the is highlighted; when the navigation direction is straight, Figure 7A The third cell in the second row is highlighted; when the navigation direction is right, Figure 7A The fifth cell in the third row is highlighted. Figure 7A The background is turned black to indicate highlighting.

[0129] For example, Figure 7B is a schematic diagram of another method for generating a recommended lane according to one embodiment of the present disclosure, Figure 6B For example, when the navigation direction is to turn left, Figure 7B The second cell in the first row of the is highlighted; when the navigation direction is straight, Figure 7B The fourth cell in the second row is highlighted; when the navigation direction is right, Figure 7B The sixth cell in the third row is highlighted. Figure 7B The background is turned black to indicate highlighting.

[0130] Based on the above optional embodiment, in the preset interface elements, the candidate identifier is displayed in the first cell display mode, and the recommended identifier is displayed in the second cell display mode. By using different special effects to distinguish the candidate identifier and the recommended identifier, the user can intuitively see the recommended identifier and the candidate representation, which helps the user to make decisions quickly.

[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0132] According to an embodiment of the present disclosure, an embodiment of a device for generating recommended lanes is provided. It should be noted that the device can be used to execute the above-mentioned method for generating recommended lanes.

[0133] Figure 8 is a structural block diagram of a device for generating a recommended lane according to one embodiment of the present disclosure, such as Figure 8 As shown, the device includes:

[0134] Identification module 801, used to identify the target road structure scene and determine the target road range;

[0135] An acquisition module 802 is configured to acquire local lane information within a target road range from crowdsourced data, wherein the local lane information is used to indicate lane direction and / or road structure changes;

[0136] A construction module 803 is used to construct a target lane-level topological relationship based on the local lane information;

[0137] The generation module 804 is configured to generate a recommended lane for the target vehicle by utilizing the target lane-level topological relationship and the navigation trajectory of the target vehicle.

[0138] Optionally, the target road structure scenario includes one of the following: a road structure scenario in which the number of lanes changes; a road structure scenario in which roads diverge and merge; and a road structure scenario in which roads meet at intersections.

[0139] Optionally, the acquisition module 802 is also used to: intercept initial road data within the target road range from multiple data packets respectively; extract local identification information from the initial road data, and spatially cluster the local identification information to obtain clustering results corresponding to each of the multiple data packets; perform data alignment on the clustering results corresponding to each of the multiple data packets to obtain data alignment results; extract local lane information from the data alignment results, wherein the local lane information includes: category turning information of multiple identification groups within the target road range, and the multiple identification groups each include multiple indicator signs along the direction of travel of the road.

[0140] Optionally, the construction module 803 is also used to: build connections between multiple identification groups contained in the local lane information to obtain an initial lane-level topological relationship; filter the initial lane-level topological relationship based on preset filtering conditions to obtain a target lane-level topological relationship, wherein the preset filtering conditions are determined based on the road traffic conditions and / or lane crossing driving experience within the target road range.

[0141] Optionally, the construction module 803 is further configured to: establish a connection between every two adjacent identification groups in the multiple identification groups included in the local lane information in a fully connected manner, so as to obtain an initial lane-level topological relationship.

[0142] Optionally, the generation module 804 is further used to: utilize the target lane-level topological relationship and the navigation trajectory of the target vehicle to select candidate identifications from multiple indicator identifications contained in multiple identification groups; determine candidate lanes based on the candidate identifications; and generate a recommended lane for the target vehicle from the candidate lanes according to preset lane recommendation criteria, wherein the preset lane recommendation criteria is determined based on the smoothness of traffic and / or lane change flexibility of the candidate lanes.

[0143] Optionally, the device for generating recommended lanes also includes a display module 805, which is used to use preset interface elements to display the candidate identification and the recommended identification corresponding to the recommended lane, wherein the preset interface elements adopt a grid arrangement method, and the multiple rows of grids in the grid arrangement method correspond to multiple identification groups respectively, and the multiple rows of grids each contain multiple cells, and the multiple cells contained in the same row of grids correspond to multiple indicator identifications contained in the same identification group.

[0144] Optionally, the display module 805 is also used to display candidate identifiers in a preset interface element using a first cell display method and to display recommended identifiers using a second cell display method, wherein the first cell display method and the second cell display method respectively use different special effects to distinguish different identifier objects.

[0145] An embodiment of the present application further provides a vehicle, comprising: a memory storing an executable program; and a processor for running the program, wherein the method of each embodiment of the present disclosure is executed when the program is running.

[0146] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0147] Step S1, identifying the target road structure scene and determining the target road range;

[0148] Step S2: obtaining local lane information within the target road range from crowdsourced data, wherein the local lane information is used to indicate lane direction and / or road structure changes;

[0149] Step S3: constructing a target lane-level topological relationship based on the local lane information;

[0150] Step S4: Generate a recommended lane for the target vehicle using the target lane-level topological relationship and the navigation trajectory of the target vehicle.

[0151] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present disclosure.

[0152] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0153] Step S1, identifying the target road structure scene and determining the target road range;

[0154] Step S2: obtaining local lane information within the target road range from crowdsourced data, wherein the local lane information is used to indicate lane direction and / or road structure changes;

[0155] Step S3: constructing a target lane-level topological relationship based on the local lane information;

[0156] Step S4: Generate a recommended lane for the target vehicle using the target lane-level topological relationship and the navigation trajectory of the target vehicle.

[0157] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0158] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present disclosure when executed by a processor.

[0159] Optionally, in this embodiment, the computer program product may be configured as a computer program for executing the following steps:

[0160] Step S1, identifying the target road structure scene and determining the target road range;

[0161] Step S2: obtaining local lane information within the target road range from crowdsourced data, wherein the local lane information is used to indicate lane direction and / or road structure changes;

[0162] Step S3: constructing a target lane-level topological relationship based on the local lane information;

[0163] Step S4: Generate a recommended lane for the target vehicle using the target lane-level topological relationship and the navigation trajectory of the target vehicle.

[0164] In the above embodiments of the present disclosure, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0165] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0166] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0167] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0168] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0169] The above is only a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as within the scope of protection of the present disclosure.

Claims

1. A method for generating a recommended lane, characterized in that: include: Identify the target road structure scene and determine the target road range; Acquire local lane information within the target road range from crowdsourced data, wherein the local lane information is used to indicate lane travel direction and / or road structure changes; Constructing a target lane-level topological relationship based on the local lane information; A recommended lane is generated for the target vehicle by utilizing the target lane-level topological relationship and the navigation trajectory of the target vehicle.

2. The method according to claim 1, characterized in that The target road structure scenario includes one of the following: Road structure scenarios with varying number of lanes; Road structure scenes where roads diverge and merge; Road structure scene at a road intersection.

3. The method according to claim 2, characterized in that The crowdsourced data includes: a plurality of data packets, and obtaining the local lane information within the target road range from the crowdsourced data includes: intercepting initial road data within the target road range from the multiple data packets respectively; Extracting local identification information from the initial road data, and performing spatial position clustering on the local identification information to obtain clustering results corresponding to each of the plurality of data packets; Performing data alignment on the clustering results corresponding to the multiple data packets to obtain a data alignment result; The local lane information is extracted from the data alignment result, wherein the local lane information includes: category turning information of multiple sign groups within the target road range, and the multiple sign groups all include multiple indicator signs along the road travel direction.

4. The method according to claim 3, characterized in that Constructing the target lane-level topological relationship based on the local lane information includes: Establishing connections between the plurality of identification groups included in the local lane information to obtain an initial lane-level topological relationship; Based on a preset filtering condition, the initial lane-level topological relationship is filtered to obtain the target lane-level topological relationship, wherein the preset filtering condition is determined according to the road traffic conditions within the target road range and / or the lane crossing driving experience.

5. The method according to claim 4, characterized in that Establishing a connection between the multiple identification groups included in the local lane information to obtain the initial lane-level topological relationship includes: A full connection method is adopted to establish a connection between every two adjacent identification groups in the multiple identification groups included in the local lane information to obtain the initial lane-level topological relationship.

6. The method according to claim 3, characterized in that Generating the recommended lane for the target vehicle by using the target lane-level topological relationship and the navigation trajectory of the target vehicle includes: Selecting candidate markers from the multiple indicator markers included in the multiple marker groups respectively by using the target lane-level topological relationship and the navigation trajectory of the target vehicle; determining a candidate lane based on the candidate identifier; The recommended lane is generated for the target vehicle from the candidate lanes according to a preset lane recommendation criterion, wherein the preset lane recommendation criterion is determined based on the smoothness of traffic and / or the flexibility of lane change of the candidate lanes.

7. The method according to claim 6, characterized in that The method further comprises: A preset interface element is used to display the candidate identification and the recommended identification corresponding to the recommended lane, wherein the preset interface element adopts a grid arrangement, and multiple rows of grids in the grid arrangement correspond to the multiple identification groups respectively, and the multiple rows of grids each contain multiple cells, and the multiple cells contained in the same row of grids correspond to the multiple indication identifications contained in the same identification group respectively.

8. The method according to claim 7, characterized in that Using the preset interface element to display the candidate identifier and the recommended identifier corresponding to the recommended lane includes: In the preset interface element, the candidate identifier is displayed in a first cell display mode, and the recommended identifier is displayed in a second cell display mode, wherein the first cell display mode and the second cell display mode respectively use different special effect distinction modes for different identifier objects.

9. A vehicle, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program, when running, executes the method for generating a recommended lane as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method for generating a recommended lane according to any one of claims 1 to 8.

11. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for generating a recommended lane according to any one of claims 1 to 8.

Images