Navigation methods, devices, and electronic devices based on lane-level local maps

Abstract

This invention discloses a navigation method, apparatus, and electronic device based on lane-level local maps. The method includes: activating a local map navigation mode in response to receiving a local map navigation activation signal; acquiring high-precision map data and perception data; constructing a lane-level local road map based on the high-precision map data and perception data; rendering lane-level navigation guide lines in the lane-level local road map based on the high-precision map data, navigation route information, and the vehicle's current lane information; and navigating the vehicle based on the lane-level local road map and the lane-level navigation guide lines. This invention solves the technical problems of high cost in acquiring and updating high-precision maps, and the inability of high-precision maps to provide lane-level guidance in related technologies.

Description

Technical Field

[0001] This invention relates to the field of vehicle navigation technology, and more specifically, to a navigation method, apparatus, and electronic device based on lane-level local maps. Background Technology

[0002] Providing lane-level guidance in in-vehicle large-screen systems can offer users clearer navigation directions, preventing them from going into the wrong lane or taking the wrong route. Some map providers have already implemented this function in mobile navigation and in-vehicle navigation software. However, map providers often rely on high-precision city maps and route planning algorithms. High-precision maps, however, have many significant drawbacks, such as high data collection and update costs, limited coverage, and the need for frequent updates to ensure real-time performance. Existing standard-precision map navigation systems can only provide information such as turning points, distances to turning points, and lane markings at intersections, and cannot provide lane-level guidance.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a navigation method, apparatus, and electronic device for lane-level local maps, which at least solves the technical problem in the related art that high-precision map acquisition and updating costs are high, while standard-precision maps cannot complete lane-level guidance.

[0005] According to one aspect of the present invention, a navigation method using a lane-level local map is provided, comprising: activating a local map navigation mode in response to receiving a local map navigation start signal; acquiring high-precision map data and perception data, wherein the high-precision map data is used to provide road network structure data of roads surrounding the vehicle, and the perception data is used to describe the road environment of roads surrounding the vehicle; constructing a lane-level local road map based on the high-precision map data and perception data, wherein the lane-level local road map is used to display roads within a first preset distance range ahead of the vehicle that match the navigation route, and the lane-level local road map includes lane lines; rendering lane-level navigation guide lines in the lane-level local road map based on the high-precision map data, navigation route information, and information about the vehicle's current lane, wherein the lane-level navigation guide lines are located within a first preset distance range ahead of the vehicle in the navigation interface, the information about the vehicle's current lane is the lane information currently located in the lane-level local road map, and the lane-level navigation guide lines are used to provide navigation information for the vehicle in the lane-level local road map; and navigating the vehicle based on the lane-level local road map and the lane-level navigation guide lines.

[0006] Furthermore, the lane-level local road map is also used to display the road within a second preset distance range behind the vehicle, the area of ​​which is smaller than the area of ​​the first preset distance range.

[0007] Furthermore, the starting point of the lane-level navigation guide line segment is located at the front of the vehicle in the navigation interface, and the ending point of the lane-level navigation guide line segment is located on the road within a first preset distance range in front of the vehicle that matches the navigation route in the navigation interface. The display area of ​​the lane-level local road map is smaller than the display area of ​​the vehicle navigation interface.

[0008] Furthermore, constructing a lane-level local road map based on refined map data and perception data includes: determining multiple grids in the vehicle coordinate system based on the refined map data; determining the current frame lane alignment points corresponding to the current frame based on the perception data; mapping the current frame lane alignment points to multiple grids in the vehicle coordinate system to obtain the mapping relationship between the current frame lane alignment points and multiple grids, wherein the mapping relationship is used to record the grid to which any current frame lane alignment point belongs; in any grid, combining the current frame lane alignment points in any grid according to the mapping relationship to obtain the current frame segment line in any grid; and constructing a lane-level local road map based on the current frame segment line.

[0009] Furthermore, determining multiple grids under the vehicle coordinate system based on the refined map data includes: determining the grid division range of the vehicle coordinate system based on the refined map data, wherein the grid division range is from the second preset distance behind the vehicle's direction of travel to the first fork in the road or the third preset distance in front of the vehicle's direction of travel; determining the location to be divided based on the preset division interval and the road segment boundary points in the grid division range; and dividing the vehicle coordinate system based on the location to be divided to obtain multiple grids under the vehicle coordinate system.

[0010] Further, determining the location to be divided based on the road segment boundary point within the preset division interval and grid division range includes: in response to the existence of a road segment boundary point within the grid division range, determining a first division location within a first range based on the preset division interval, wherein the first range is from a second preset distance behind the vehicle's direction of travel to the road segment boundary point; determining a second division location within a second range based on the preset division interval, wherein the second range is from the road segment boundary point to the first fork in the road ahead of the vehicle's direction of travel or a third preset distance; and determining the location to be divided based on the first division location and the second division location.

[0011] Further, determining the location to be divided based on the road segment boundary points within the preset division interval and grid division range includes: in response to the existence of multiple road segment boundary points within the grid division range, determining a third division location within a third range based on the preset division interval, wherein the multiple road segment boundary points include a first road segment boundary point and a second road segment boundary point, the distance between the first road segment boundary point and the vehicle is closer than the distance between the second road segment boundary point and the vehicle, and the third range is from a second preset distance behind the vehicle in the direction of travel to the first road segment boundary point; determining a fourth division location within a fourth range based on the preset division interval, wherein the fourth range is from the first road segment boundary point to the second road segment boundary point; determining a fifth division location within a fifth range based on the preset division interval, wherein the fifth range is from the second road segment boundary point to the first fork in the road ahead of the vehicle or a third preset distance; and determining the location to be divided based on the third, fourth, and fifth division locations.

[0012] Furthermore, in any grid, the current frame lane alignment points in any grid are combined according to the mapping relationship to obtain the current frame segment line in any grid, including: determining lane lines in the road around the vehicle based on perception data; classifying lane lines based on lane line classification rules to obtain a first lane line and a second lane line, wherein the left lane of the first lane line has the same driving direction as the right lane, and the left lane of the second lane line has a different driving direction than the right lane; determining multiple target lane alignment points in any grid based on the lane alignment points of the first lane line; and combining the multiple target lane alignment points to obtain the current frame segment line in any grid.

[0013] Furthermore, constructing a lane-level local road map based on the segment lines of the current frame includes: determining the midpoint lane alignment point of the segment lines of the current frame; merging the segment lines of the current frame based on the coordinate information of the midpoint lane alignment point to obtain merged lane lines; adjusting the lane line type of the merged lane lines based on lane line type rules to obtain adjusted merged lane lines, wherein the lane line type rules are used to merge lane lines with mismatched lane line types into solid line type lane lines; and constructing a lane-level local road map based on the adjusted segment lines of the current frame.

[0014] Furthermore, based on the coordinate information of the midpoint lane alignment points, the segment lines of the current frame are merged to obtain merged lane lines, including: in response to the coordinate distance between adjacent midpoint lane alignment points being less than a preset coordinate distance, the segment lines of the current frame to which the adjacent midpoint lane alignment points belong are merged to obtain merged lane lines.

[0015] Furthermore, based on the refined map data, navigation route information, and current lane information, lane-level navigation guidance segments are rendered in the lane-level local road map to update the lane-level local road map. This includes: determining the driving path based on the refined map data, navigation route information, current lane information, and merged lane lines; determining the target lane lines constituting the driving path based on the merged lane lines; determining the coordinate information of the lane-level navigation guidance points based on the coordinate information of the midpoint lane line type points corresponding to the target lane lines; generating lane-level navigation guidance segments based on the coordinate information of the lane-level navigation guidance points; determining the lane boundary lines based on the second lane lines; and rendering the lane-level navigation guidance segments and lane boundary lines in the lane-level local road map to update the lane-level local road map.

[0016] According to another aspect of the present invention, a navigation device with a lane-level local map is also provided, applied to a vehicle, comprising: an activation module, configured to activate a local map navigation mode in response to receiving a local map navigation activation signal; an acquisition module, configured to acquire high-precision map data and perception data, wherein the high-precision map data is used to provide road network structure data of the roads surrounding the vehicle, and the perception data is used to describe the road environment of the roads surrounding the vehicle; a construction module, configured to construct a lane-level local road map based on the high-precision map data and perception data, wherein the lane-level local road map is used to display roads within a first preset distance range ahead of the vehicle that match the navigation route, and the lane-level local road map includes lane lines; a rendering module, configured to render lane-level navigation guide lines in the lane-level local road map based on the high-precision map data, navigation route information, and the current lane information of the vehicle, wherein the lane-level navigation guide lines are located within a first preset distance range ahead of the vehicle in the navigation interface, the current lane information of the vehicle is the lane information of the vehicle currently located in the lane-level local road map, and the lane-level navigation guide lines are used to provide navigation information for the vehicle in the lane-level local road map; and a navigation module, configured to navigate the vehicle based on the lane-level local road map and the lane-level navigation guide lines.

[0017] According to another aspect of the present invention, a vehicle is also provided for performing the methods of the various embodiments of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0019] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0020] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0021] In this embodiment of the invention, in response to receiving a local map navigation start signal, the local map navigation mode is first activated, and high-precision map data and perception data are acquired. Then, a lane-level local road map is constructed based on the high-precision map data and perception data. Based on the high-precision map data, navigation route information, and the vehicle's current lane information, lane-level navigation guidance lines are rendered in the lane-level local road map. Finally, the vehicle is navigated based on the lane-level local road map and the lane-level navigation guidance lines, achieving the goal of improving navigation accuracy and enhancing autonomous driving decision support. This realizes the technical effect of lane-level navigation services and solves the technical problems of high-precision map acquisition and update costs, and the inability of high-precision maps to complete lane-level guidance in related technologies. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0023] Figure 1 This is a flowchart of a navigation method using a lane-level local map according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of a lane-level local road map according to an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of another lane-level local road map according to an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of another lane-level local road map according to an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of lane line division grid in the longitudinal range of a vehicle according to an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of dividing the effective lane lines into segments according to an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram of lane line classification rules according to an embodiment of the present invention;

[0030] Figure 8 This is a schematic diagram illustrating the sorting, merging, and filtering of local lane lines within a grid according to an embodiment of the present invention;

[0031] Figure 9 This is a schematic diagram of a navigation device with a lane-level local map according to an embodiment of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] According to an embodiment of the present invention, a navigation method for lane-level local maps is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] This application provides a navigation method based on lane-level local maps. This lane-level local map navigation method can be used to provide navigation functionality for preset application scenarios. These preset application scenarios may include the following scenarios in the vehicle field: autonomous driving scenarios for commuting, artificial intelligence (AI) assisted driving scenarios for family cars, automatic parking assistance (APA) scenarios (such as memory parking for self-owned parking spaces in garages, intelligent parking for designated parking spaces in parking lots, etc.), and navigation-guided pilot (NGP) scenarios in urban or highway areas. Furthermore, these preset application scenarios may also include, but are not limited to: navigation scenarios for intelligent driving trucks or unmanned trucks in the logistics and transportation field, and navigation scenarios for autonomous agricultural vehicles in the agricultural machinery field.

[0036] When the aforementioned preset application scenario is a scenario in a field other than the vehicle field, those skilled in the art should understand that the vehicles in the above-mentioned lane-level local map navigation method can be replaced with other objects (such as agricultural machinery). Based on this, this application embodiment takes the field of vehicle navigation technology as an example to illustrate the specific implementation of the above-mentioned lane-level local map navigation method.

[0037] Figure 1 This is a flowchart of a navigation method using a lane-level local map according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0038] Step S10: In response to receiving the local map navigation start signal, the local map navigation mode is started;

[0039] In this embodiment of the invention, the local map navigation activation signal is used to indicate that the system has entered the working state of lane-level local map navigation. For example, the local map navigation activation signal may originate from various situations. For instance, when the driver selects the navigation function in the vehicle's multimedia system and selects the "lane-level navigation" option in the menu, the system will receive the local map navigation activation signal; or, in autonomous driving mode, the vehicle may automatically determine the need to activate the lane-level navigation function based on its own positioning, destination input, or environmental perception results, and will also send a local map navigation activation signal to the system in this case. No limitation is imposed here.

[0040] Local map navigation mode can be understood as a working mode that the system enters after receiving a local map navigation activation signal. For example, in local map navigation mode, the system focuses on building and using lane-level local road maps for navigation. This may include: acquiring and integrating high-resolution map data and real-time perception data to build a lane-level local road map; rendering lane-level navigation guide lines in the constructed lane-level local road map based on the high-resolution map data, the vehicle's current position, driving direction, and navigation route information, providing detailed and accurate lane-level navigation information to the driver or autonomous driving system; and using the constructed lane-level local road map and the rendered navigation guide lines to provide continuous and refined navigation for the vehicle, guiding it safely and efficiently to its destination—this is not limited to specific scenarios.

[0041] In response to receiving a local map navigation activation signal, enabling local map navigation mode can be understood as the system switching from the regular navigation mode to local map navigation mode when it detects or receives the signal. This upgrades the system from providing road-level navigation information to providing lane-level navigation information and guidance.

[0042] In this embodiment of the invention, by enabling the local map navigation mode, the navigation accuracy and safety in complex road environments can be improved, enabling the driver or autonomous driving system to have a clearer understanding of the current road lane layout, lane line attributes and other important information, thereby making appropriate lane changes, turns or straight-ahead operations, and avoiding driving errors caused by insufficient information.

[0043] Step S11: Obtain standard and refined map data and perception data, wherein the standard and refined map data is used to provide road network structure data of the roads around the vehicle, and the perception data is used to describe the road environment of the roads around the vehicle.

[0044] In this embodiment of the invention, the refined map data can be understood as map data between traditional low-precision maps and full high-precision maps. It should be noted that the refined map data in this embodiment can be understood as a map dataset containing basic road information but with lower detail and accuracy; that is, the refined map data in this embodiment has a smaller data volume, thus occupying less storage space and saving computing resources.

[0045] For example, the high-precision map data only provides information such as turning points, distances to turning points, and lane markings at intersections along the navigation route. In other words, the high-precision map data in this embodiment of the invention is used to provide road network structure data around the vehicle. It is understood that in traditional solutions, this high-precision map data cannot provide lane-level navigation guidance.

[0046] Perception data can be understood as real-time information about the vehicle's surrounding environment captured and processed by the vehicle's sensor systems (including but not limited to cameras, radar, lidar, ultrasonic sensors, etc.). For example, perception data may include: the position, speed, and behavior of dynamic obstacles around the vehicle, such as other vehicles, pedestrians, and bicycles; the state and position of lane markings, including the degree of wear, obstruction, and temporary alteration of lane markings; information on traffic signs and signals, such as speed limits, lane departure warnings, and traffic light status; and road surface conditions, such as slippery surfaces, potholes, and construction, which are not limited here.

[0047] Perception data, used to describe the road environment around a vehicle, can be understood as data collected in real time by sensors on the vehicle, reflecting the current state of the environment around the vehicle, including dynamic obstacles (such as other vehicles, pedestrians, and animals), the specific state of lane markings (such as whether there are temporary lane change signs or whether lane markings are clearly visible), and road surface conditions (such as wetness or damage).

[0048] Acquiring high-precision map data and perception data can be understood as the system retrieving high-precision map data from the map database, and the system activating various sensors on the vehicle to continuously collect real-time perception data of the vehicle's surrounding environment.

[0049] As can be seen, standard precision maps can only provide basic data such as turning points, distance information, and lane control panels at intersections, but cannot provide detailed lane-level navigation information. This invention supplements lane-level details with real-time sensing data, making the resulting navigation guidance more accurate and significantly improving the user experience.

[0050] In this embodiment of the invention, by acquiring both high-precision map data and real-time perception data, costs are reduced due to the low storage requirements and computational resource consumption of high-precision map data. Furthermore, acquiring real-time perception data effectively compensates for the limitations of a single data source, making lane-level navigation more accurate and real-time, significantly enhancing the adaptability and reliability of the navigation system. Especially in complex and changing road conditions, it can provide safer and more detailed guidance information for drivers or autonomous driving systems, reducing accident risks and improving driving efficiency. In addition, acquiring real-time perception data can capture unexpected situations not included in the high-precision map data, such as suddenly appearing static obstacles, pedestrians, or non-motorized vehicles. Therefore, it can more effectively identify and respond to potential hazards, taking necessary avoidance measures and significantly improving driving safety. In other words, by combining high-precision map data and real-time perception data, this embodiment of the invention maintains the requirements of low cost and low maintenance while improving the real-time performance and safety of navigation, enhancing user experience, and providing more detailed and flexible data support for subsequent route planning.

[0051] Step S12: Construct a lane-level local road map based on the standard and precision map data and perception data. The lane-level local road map is used to display the road within a first preset distance range in front of the vehicle that matches the navigation route. The lane-level local road map includes lane lines.

[0052] In this embodiment of the invention, the map data structure of the lane-level local road map mainly includes: the current number of lanes, the current left and right road boundaries, lane line attribute types, and the lane index of the vehicle, etc., which are not limited here. The current number of lanes can be understood as the total number of lanes in the road segment where the vehicle is currently located. For example, if the vehicle is traveling on a road with three lanes, the current number of lanes is 3. The current left and right road boundaries can be understood as the boundary information of the left and right sides of the road segment where the vehicle is located. The lane line attribute types include the type of lane line (such as dashed line, solid line), color, and other attributes. The lane index of the vehicle can be understood as a numerical value used to indicate which lane the vehicle is currently traveling in; lanes are usually numbered from left to right. For example, if the current number of lanes is 3 and the vehicle is traveling in the rightmost lane, the lane index of the vehicle is 2 (assuming counting starts from 0).

[0053] The area in front of a vehicle can be understood as the area in front of the vehicle's direction of travel, and can include various situations such as turning, going straight, and making a U-turn, without any restrictions here.

[0054] The first preset distance range can be understood as the road within a certain distance in front of the vehicle (not extending to the end of the road). For example, the first preset distance range can be the road within 0m-80m in front of the vehicle, or it can be the road within 0m-120m in front of the vehicle; there is no limitation here. Figure 2 This is a schematic diagram of a lane-level local road map according to an embodiment of the present invention, such as... Figure 2 As shown, the lane-level local road map displays the road within a certain distance ahead of the vehicle. This means the road ahead shown in the lane-level local road map does not extend to the end of the road. Therefore, the specific lane position of the vehicle can be accurately determined based on the lane-level local road map, leading to more accurate driving decisions. Furthermore, the lane-level local road map also includes lane line information, which helps in better understanding the current road environment. Figure 2 The remaining descriptions are provided below.

[0055] Building a lane-level local road map based on high-precision map data and perception data can be understood as generating a road map detailed down to the lane level by using the stable road structure background provided by the high-precision map and the real-time environmental status fed back by the perception data, based on the real-time location of the vehicle.

[0056] In this embodiment of the invention, by integrating high-precision maps and perception data, a lane-level local road map at a certain distance ahead of the vehicle is constructed. This map accurately depicts lane lines and other details, significantly improving navigation accuracy and safety. Especially in complex road conditions, it provides strong support for driving decisions, enabling efficient route planning and reducing potential accident risks. Simultaneously, the lane-level local road map includes lane line information, helping the autonomous driving system or driver better understand the current road environment. Particularly at complex intersections or road junctions, it accurately judges lane continuity and connectivity, avoiding incorrect route planning or lane-changing maneuvers. Furthermore, compared to traditional lane-level navigation which relies on high-precision maps, the production and maintenance of such maps are very costly. This invention, by constructing a lane-level local road map, enables lane-level navigation even without a high-precision map, greatly reducing application costs and data processing complexity.

[0057] Step S13: Based on the standard map data, navigation route information and the current lane information of the vehicle, render lane-level navigation guide lines in the lane-level local road map. The lane-level navigation guide lines are located within a first preset distance range in front of the vehicle in the navigation interface. The current lane information of the vehicle is the lane information of the vehicle in the lane-level local road map. The lane-level navigation guide lines are used to provide navigation information for the vehicle in the lane-level local road map.

[0058] In this embodiment of the invention, navigation route information can be understood as a navigation route determined based on the user's destination address. This navigation route information is not directly displayed on the lane-level local road map, but is data pre-calculated by the cloud based on the destination address and the vehicle's current location. In other words, the navigation route information is data directly obtained by the vehicle from the cloud.

[0059] Lane-level navigation guidance lines are visual elements that provide specific lane-level navigation guidance to drivers or autonomous driving systems on a lane-level local road map. Based on refined map data, the vehicle's current navigation route, and the specific lane information the vehicle is in, lane-level navigation guidance lines are rendered within a first preset distance range ahead of the vehicle in the navigation interface. Lane-level navigation guidance lines intuitively indicate how the vehicle should drive in the current and forward lanes, including but not limited to when to change lanes, to which lane to change to, and in which lane to continue driving. Lane-level navigation guidance lines make navigation guidance more refined and intuitive, helping drivers or autonomous driving systems to more accurately understand and execute navigation commands. Especially in multi-lane, complex intersection scenarios, they can significantly improve the effectiveness and safety of navigation, reducing driving errors caused by misunderstanding navigation information.

[0060] For example, such as Figure 2As shown, lane-level navigation guidance lines are rendered within a first preset distance range in front of the vehicle and do not extend to the entire edge of the in-vehicle screen. In other words, lane-level navigation guidance lines are only rendered within a certain distance range in front of the vehicle as displayed on the lane-level partial road map. This ensures that navigation guidance is effective without causing interference. It is understandable that the length of lane-level navigation guidance lines is limited; the length can correspond to an actual road distance of 80m-120m. This is only an example and is not a limitation. Figure 2 The remaining descriptions are provided below.

[0061] Based on high-precision map data, navigation route information, and the vehicle's current lane information, rendering lane-level navigation guidance segments in a lane-level local road map can be understood as the system using high-precision map data as the basic road network framework, combined with the vehicle's real-time navigation route and current lane information, to dynamically draw lane-level navigation guidance segments on the lane-level local road map. These lane-level navigation guidance segments not only indicate the optimal driving path the vehicle should follow, but also emphasize lane-level details, such as when and where to change lanes, and the target lane for the lane change.

[0062] For example, Figure 3 and Figure 4 These are schematic diagrams of two different lane-level local road maps according to embodiments of the present invention. Figure 3 and Figure 4 This illustrates how the road edge changes while the vehicle is in motion. Figure 3 This illustrates a scenario where the road edge is about to change while the vehicle is in motion, and the current lane number is 3. Figure 4 This illustrates a scenario where the roadside has changed while the vehicle is in motion; a new lane has been added to the left of the vehicle, bringing the current lane count to four. It can be seen that... Figure 3 In the scenario shown, the lane-level navigation guide line segment instructs the vehicle to travel to the third lane from the left in a three-lane road. Figure 4 In the scenario shown, lane-level navigation guide lines instruct the vehicle to move to the third lane from the left in a four-lane road. Therefore, when traveling from... Figure 3 The scene shown has changed to Figure 4 In the scenario shown, the lane-level navigation guide line segment will jitter, meaning that during this process, the lane-level navigation guide line segment will be continuously updated according to the real-time road conditions, so that it can guide the vehicle to the best driving path.

[0063] In this embodiment of the invention, through the above steps, navigation information is transformed into intuitive visual guidance, which is directly displayed within a preset distance range in front of the vehicle. This greatly improves the accuracy and ease of use of navigation, helping drivers or autonomous driving systems to make timely and correct decisions. Especially in complex traffic environments, lane-level navigation guidance lines can significantly enhance driving safety and smoothness.

[0064] Step S14: Navigate the vehicle based on the lane-level local road map and lane-level navigation guide lines.

[0065] In this embodiment of the invention, navigating a vehicle based on a lane-level local road map and lane-level navigation guidance lines can be understood as providing the vehicle with precise route guidance by utilizing a high-precision lane-level local road map and detailed lane-level navigation guidance lines.

[0066] In this embodiment of the invention, a lane-level local road map is used to meticulously depict information such as lane layout and lane line attributes of the vehicle's surrounding environment. Combined with lane-level navigation guidance lines, the lane path that the vehicle should follow in the current and subsequent driving is clearly indicated. This can effectively guide the vehicle to make correct lane changing or driving decisions in situations such as multi-lane and complex intersections, greatly improving the accuracy, safety and user experience of navigation.

[0067] It can be seen that traditional solutions use high-precision maps to provide lane-level guidance. The creation and maintenance of high-precision maps require significant resource investment, involving complex data collection and real-time update mechanisms, resulting in high costs and limited update frequency. In contrast, the standard-precision map combined with a pure vision-based solution proposed in this invention relies on the vehicle's own perception capabilities to acquire lane-level details in real time. This significantly reduces reliance on high-precision map data and allows for rapid adaptation to road changes, making it widely applicable across different regions without concerns about map update lag affecting navigation performance. Furthermore, traditional high-precision maps, due to their long update cycles, may not immediately reflect sudden changes in road conditions (such as temporary construction or road closures). In contrast, this invention, through real-time vehicle perception data, can instantly capture and analyze these changes, dynamically adjusting the content of the lane-level local road map. This ensures that lane-level navigation guidance lines accurately reflect the current road conditions, improving the real-time responsiveness and flexibility of navigation, and ensuring that driving decisions are based on the latest and most accurate information. Furthermore, by combining high-precision maps with a purely visual solution, this invention enables lane-level navigation guidance lines to be displayed intuitively on the navigation interface. This not only reduces the driver's cognitive load, allowing the driver to focus more on driving itself, but also improves the operational transparency in autonomous driving mode, making users more confident in the system's capabilities, thereby enhancing the overall user experience.

[0068] In this embodiment of the invention, in response to receiving a local map navigation start signal, the local map navigation mode is first activated, and high-precision map data and perception data are acquired. Then, a lane-level local road map is constructed based on the high-precision map data and perception data. Based on the high-precision map data, navigation route information, and the vehicle's current lane information, lane-level navigation guidance lines are rendered in the lane-level local road map. Finally, the vehicle is navigated based on the lane-level local road map and the lane-level navigation guidance lines, achieving the goal of improving navigation accuracy and enhancing autonomous driving decision support. This realizes the technical effect of lane-level navigation services and solves the technical problems of high-precision map acquisition and update costs, and the inability of high-precision maps to complete lane-level guidance in related technologies.

[0069] Optionally, the lane-level local road map is also used to display the road within a second preset distance range behind the vehicle, the area of ​​the second preset distance range being smaller than the area of ​​the first preset distance range.

[0070] In this embodiment of the invention, the second preset distance range can be understood as a specific distance interval behind the vehicle, the area or coverage of which is smaller than the first preset distance range in front of the vehicle. For example, the second preset distance range can be a road within a range of 0m-5m behind the vehicle, or it can be a road within a range of 0m-10m behind the vehicle; there is no limitation here. Figure 2 As shown, the lane-level local road map displays not only the road within a first preset distance range in front of the vehicle, but also the road within a second preset distance range behind the vehicle, with the area of ​​the second preset distance range being smaller than the area of ​​the first preset distance range. Therefore, by simultaneously presenting road information in front of and behind the vehicle on the map, the driver or autonomous driving system can obtain a more comprehensive environmental perception. This not only helps in predicting road conditions ahead but also in monitoring potential traffic conditions behind, such as the approaching speed and positional changes of vehicles behind, thereby enabling safer driving decisions. Figure 2 The remaining descriptions are provided below.

[0071] Lane-level local road maps are also used to display roads within a second preset distance range behind the vehicle. This means that lane-level local road maps not only provide detailed lane information in front of the vehicle, but also cover road conditions within a certain distance behind the vehicle, so that drivers or autonomous driving systems can simultaneously refer to the traffic environment in front and behind, and make more comprehensive and safer driving decisions.

[0072] The fact that the area of ​​the second preset distance range is smaller than that of the first preset distance range can be understood as follows: in a lane-level local road map, the coverage area of ​​road information behind the vehicle is smaller than that in front of the vehicle. By setting a smaller rear distance range, the system can concentrate more resources on the collection and processing of information ahead, while ensuring that necessary information behind is also taken into consideration, in order to achieve more efficient and safer navigation and driving assistance functions.

[0073] In this embodiment of the invention, through the above steps, not only can lane details within a first preset distance in front of the vehicle be displayed, but road information within a second preset distance behind is also covered. Moreover, the area behind is relatively small, which enhances the driver's all-around vision, especially in scenarios where attention needs to be paid to traffic dynamics behind, such as changing lanes or reversing. This improves the practicality and safety of navigation and ensures the comprehensiveness and accuracy of driving decisions.

[0074] Optionally, the starting point of the lane-level navigation guide line segment is located at the front of the vehicle in the navigation interface, and the ending point of the lane-level navigation guide line segment is located on the road within a first preset distance range in front of the vehicle that matches the navigation route in the navigation interface. The display area of ​​the lane-level local road map is smaller than the display area of ​​the vehicle navigation interface.

[0075] In this embodiment of the invention, the starting point of the lane-level navigation guide line segment is located at the front of the vehicle in the navigation interface. This can be understood as the lane-level navigation guide line segment being drawn from the front of the vehicle at its current actual position, ensuring that the navigation information is closely related to the real-time status of the vehicle and providing accurate driving direction guidance.

[0076] The endpoint of the lane-level navigation guide line segment is located on the road within a first preset distance range in front of the vehicle that matches the navigation route in the navigation interface. This can be understood as the line segment extending to a set distance on the road in front of the vehicle. This distance is sufficient to cover key driving decision points such as upcoming turning points and intersections, providing enough reaction time for the driver or the autonomous driving system.

[0077] The smaller display area of ​​a lane-level local road map compared to the vehicle navigation interface can be understood as the local map focusing only on the most relevant and important road information area around the vehicle. Its purpose is to optimize information display, reduce unnecessary visual interference, and enable the driver or system to quickly and accurately obtain and process key lane-level navigation data, thereby improving driving safety and efficiency. For example... Figure 2As shown, the in-vehicle screen can simultaneously display the existing in-vehicle navigation software interface (which usually displays the vehicle's driving path from a top-down perspective and does not show the specific road conditions) and the lane-level local road map of this invention. Moreover, the display area of ​​the lane-level local road map is smaller than that of the vehicle navigation interface, which can optimize information display, reduce unnecessary visual interference, and reduce the amount of computation required to generate the map, so that the lane-level local road map can be generated and displayed more efficiently.

[0078] In this embodiment of the invention, by setting the starting point of the lane-level navigation guide segment at the front of the vehicle and extending the ending point to a road within a first preset distance ahead that matches the navigation route, the immediacy and foresight of driving decisions are ensured. Simultaneously, the reduced display area of ​​the local road map optimizes the information density of the navigation interface, highlights key lane information, reduces visual clutter, and enhances the intuitiveness of navigation and driving safety. Especially in complex traffic environments, it effectively assists drivers or autonomous driving systems in making quick and accurate responses.

[0079] Optionally, in step S12, constructing a lane-level local road map based on the refined map data and perception data includes the following steps:

[0080] Step S121: Determine multiple grids in the vehicle coordinate system based on the standard map data;

[0081] Step S122: Determine the lane alignment points corresponding to the current frame based on the perception data;

[0082] Step S123: Map the lane alignment points of the current frame to multiple grids in the vehicle coordinate system to obtain the mapping relationship between the lane alignment points of the current frame and multiple grids. The mapping relationship is used to record the grid to which any lane alignment point of the current frame belongs.

[0083] Step S124: In any grid, combine the lane line points of the current frame in any grid according to the mapping relationship to obtain the segment line of the current frame in any grid;

[0084] Step S125: Construct a lane-level local road map based on the segment lines of the current frame.

[0085] In this embodiment of the invention, the vehicle coordinate system can be understood as a coordinate system centered on the vehicle (i.e., the vehicle driven by the user). In the vehicle coordinate system, the vehicle's position is defined as the origin (0, 0), and the vehicle's direction of travel is defined as the positive direction of the coordinate axes, which is usually aligned with the vehicle's longitudinal axis.

[0086] The lane line data points in the current frame can be understood as the lane line data captured at the current time point.

[0087] The current frame segment line is obtained by mapping the lane line shape points of the current frame to multiple grids in the vehicle coordinate system, dividing the shape points into grids, and combining the shape points in each grid.

[0088] Determining multiple grids in the vehicle coordinate system based on refined map data can be understood as using road information from the refined map data, such as lane width and road boundaries, combined with vehicle position information, to define a series of grids corresponding to the vehicle's position and covering the vehicle's surrounding environment. These grids are arranged in the vehicle coordinate system, facilitating updates and management as the vehicle moves, ensuring that road information can be quickly extracted and processed based on the vehicle's current and future travel paths.

[0089] Determining the lane line shape points corresponding to the current frame based on perception data can be understood as identifying the shape and position of the lane lines around the vehicle by using data collected by the sensors (such as cameras and radar) of the autonomous driving system in each frame, and converting them into multiple key points, namely lane line shape points. The lane line shape points of the current frame carry detailed attributes of the lane lines, such as type and color, for subsequent meshing processing and lane modeling.

[0090] Mapping the lane alignment points of the current frame to multiple grids in the vehicle coordinate system, thus obtaining the mapping relationship between the lane alignment points of the current frame and multiple grids, can be understood as accurately assigning the identified and extracted lane alignment points to the corresponding grids according to their positions in the vehicle coordinate system, forming a correspondence table between alignment points and grids. This ensures that the lane line information contained in each grid reflects the real situation around the vehicle in the current frame, facilitating subsequent grid-based processing of the lane line information. Figure 5 and Figure 6 As shown, the area from 5m behind the vehicle to 100m ahead, or to the next intersection, is divided into grids with 10m intervals. Lane alignment points are captured in real time and projected into the nearest neighboring grid based on their coordinates. This ensures that each grid reflects the instantaneous lane conditions around the vehicle, laying the data foundation for subsequent grid-based processing, such as lane line sorting, merging, and filtering. Ultimately, this facilitates the generation of lane-level navigation guidance, improving driving safety and the accuracy of autonomous driving. Simultaneously, through this mapping, the system can process lane-level information more efficiently, reducing computational load while maintaining data real-time performance and accuracy. Figure 5 and Figure 6 The rest of the description is provided below.

[0091] In any given grid, the lane alignment points of the current frame are combined according to the mapping relationship to obtain the current frame segment line in any grid. This can be understood as combining the lane alignment points mapped to that grid within each grid to form a line segment representing the lane line characteristics within that grid, i.e., the current frame segment line. This segment line can concisely and accurately describe the local attributes and direction of the lane lines, facilitating lane-level map construction and subsequent driving decisions.

[0092] Building a lane-level local road map based on the segmented lines of the current frame can be understood as using the generated segmented lines of the current frame to construct a small map containing detailed information about the lanes surrounding the vehicle, including lane width, lane line attributes, and the vehicle's position relative to the lane. The lane-level local road map is dynamically updated, ensuring that accurate lane-level navigation and driving assistance information is always provided during vehicle operation, which is crucial for achieving autonomous driving and enhancing driving safety.

[0093] In this embodiment of the invention, high-precision map data is converted to the vehicle coordinate system and divided into multiple grids. Lane alignment points captured by the perception system are then mapped onto these grids, forming a mapping relationship. Based on this mapping relationship, the alignment points within each grid are integrated into segment lines, ultimately constructing a real-time lane-level local road map. This effectively integrates static map and dynamic perception information, significantly improving navigation accuracy and response speed. Especially in complex road environments, it can provide drivers or autonomous driving systems with more intuitive and timely lane-level navigation guidance, enhancing driving safety and the navigation user experience.

[0094] Optionally, in step S121, determining multiple grids in the vehicle coordinate system based on the refined map data includes the following steps:

[0095] Step S1211: Determine the grid division range of the vehicle coordinate system based on the standard map data. The grid division range is from the second preset distance behind the vehicle in the direction of travel to the first fork in the road or the third preset distance in the direction of travel.

[0096] Step S1212: Determine the location to be divided based on the preset division interval and the road segment boundary points within the grid division range;

[0097] Step S1213: Divide the vehicle coordinate system based on the position to be divided to obtain multiple grids under the vehicle coordinate system.

[0098] In this embodiment of the invention, the grid division range is a spatial region used to construct a lane-level local map in the vehicle coordinate system, which is also the range that the vehicle can perceive.

[0099] The preset interval can be understood as the maximum grid width, for example, with an interval of 10m, which is not limited here.

[0100] Road segment boundaries can be understood as the starting and ending points of road segments in a road network, marking the boundary of a continuous road segment with the same attributes.

[0101] The location to be divided can be understood as a series of spatial coordinate points pre-calculated or determined in the vehicle coordinate system based on the preset division interval and road segment boundary points. These points indicate the specific location where the grid division should begin or end.

[0102] Determining the grid division range of the vehicle coordinate system based on standard-precision map data can be understood as defining an area centered on the vehicle's position and covering a certain distance before and after it, based on the road information provided by the standard-precision map, including road boundaries and lane layout, for subsequent gridding processing. The setting of the grid division range not only considers the vehicle's current driving state but also the traffic environment that the vehicle may encounter ahead, such as intersections, to ensure that the grid division includes key information along the vehicle's driving path.

[0103] The grid division range, defined as extending from a second preset distance behind the vehicle in the direction of travel to either the first fork in the road ahead or a third preset distance ahead, can be understood as defining a dynamic grid division area. This area begins at a certain distance behind the vehicle (the second preset distance) and ends at either the first fork in the road ahead or a pre-set distance (the third preset distance, which is typically greater than the second preset distance). For example, the grid division range can start 5m behind the vehicle and end at either the first fork in the road ahead or 100m ahead. For instance, in urban areas, if there is an intersection at 100m, the end point is the intersection; on highways, if there is no intersection at 100m, the end point is 100m. There are no restrictions here.

[0104] Determining the location to be divided based on the road segment boundary points within the preset division interval and grid division range can be understood as determining a series of division locations or coordinate points within the defined grid division range, according to the preset interval distance and key points on the road (such as road segment boundary points, which may indicate changes in the number of lanes or lane line attributes).

[0105] Dividing the vehicle coordinate system based on the location to be divided, resulting in multiple grids in the vehicle coordinate system, can be understood as using the determined division location to divide the environment around the vehicle into multiple grids, each grid representing road information within a specific distance.

[0106] In this embodiment of the invention, under the vehicle coordinate system, the above-described mesh partitioning method can achieve a structured description of the road environment, facilitating subsequent processing and analysis, such as the generation of lane-level navigation guidance and the perception and decision-making of road conditions by autonomous vehicles. The above-described mesh partitioning method can effectively manage the complexity of road information while ensuring the availability and flexibility of updating key data.

[0107] Optionally, determining the location to be divided based on the preset division interval and the road segment boundary points within the grid division range includes the following steps:

[0108] In response to the existence of a road segment boundary point within the grid division range, the first division position is determined within the first range based on a preset division interval, wherein the first range is from a second preset distance behind the vehicle's direction of travel to the road segment boundary point;

[0109] Within the second range, the second division position is determined based on the preset division interval, wherein the second range is from the road segment boundary point to the first fork in the road ahead of the vehicle's direction of travel or a third preset distance.

[0110] The position to be divided is determined based on the first and second division positions.

[0111] In this embodiment of the invention, the first range can be understood as the road area starting from a second preset distance behind the vehicle's direction of travel and extending to the first road segment boundary point encountered.

[0112] The second range can be understood as the area starting from the first road segment boundary point and continuing forward until the first fork in the road appears or the third preset distance is reached.

[0113] The first division position can be understood as the coordinate point determined along the longitudinal direction of the road within the first range, according to the preset division interval (such as every 10 meters), which is not restricted here.

[0114] The second division position can be understood as the coordinate point determined within the second range according to the same preset division interval. The second division position and the first division position together constitute all the positions to be divided in the grid, which are not restricted here.

[0115] In response to the existence of a road segment boundary point within the grid division range, determining the first division position within the first range based on a preset division interval can be understood as follows: when a road segment boundary point is detected within the grid division range, the system will start from behind the vehicle and, along the vehicle's driving direction, determine a series of position points within the first range (i.e., the road segment from the second preset distance behind the vehicle to the road segment boundary point) according to a preset division interval (such as 5 meters, 10 meters, etc.). These position points are called the first division position.

[0116] Determining the second division position based on the preset division interval within the second range can be understood as follows: after the grid division of the first range is completed, the system then starts from the road segment boundary point and extends to the first fork in the road ahead of the vehicle or the third preset distance (i.e., the second range), and determines the second division position based on the preset division interval.

[0117] Determining the position to be divided based on the first and second division positions can be understood as the system combining the first and second division positions to form the starting and ending points of the grid division, i.e., the position to be divided.

[0118] In this embodiment of the invention, based on the grid division range containing road segment boundary points, the first division position and the second division position are determined at preset intervals, thereby determining the position to be divided. By dynamically adapting the grid division to changes in road characteristics, the efficiency and accuracy of local road network mapping are significantly improved, providing real-time and detailed road information for lane-level navigation and autonomous driving strategies, while avoiding the high cost of high-precision maps and enhancing the system's flexibility and economy.

[0119] Figure 5 This is a schematic diagram of the lane line grid division within the longitudinal range of a vehicle according to an embodiment of the present invention, as shown below. Figure 5 As shown, the maximum grid width is set to 10m, and the starting and ending points of the vertical grid division are defined. The starting point is 5m behind the vehicle, and the ending point is the distance between the vehicle and the next intersection (i.e., V2 Stub data, which refers to a data type in Vehicle-to-Infrastructure (V2I) or Vehicle-to-Vehicle (V2V) communication; here, V2 Stub data refers to data associated with the vehicle and the next intersection (Stub)). The maximum forward distance is 100m. The division strategy is to divide sequentially from the starting point in 10m intervals. If a segment boundary (i.e., the specific location of the start and end of a segment) of V2 Stub data is encountered, the division continues at the segment boundary until the grid end point is reached.

[0120] Optionally, determining the location to be divided based on the preset division interval and the road segment boundary points within the grid division range includes the following steps:

[0121] In response to the existence of multiple road segment boundary points within the grid division range, the third division position is determined within the third range based on a preset division interval. The multiple road segment boundary points include the first road segment boundary point and the second road segment boundary point. The distance between the first road segment boundary point and the vehicle is closer than the distance between the second road segment boundary point and the vehicle. The third range is from the second preset distance behind the vehicle's direction of travel to the first road segment boundary point.

[0122] The fourth division position is determined based on a preset division interval within the fourth range, wherein the fourth range is from the first road segment boundary point to the second road segment boundary point;

[0123] Within the fifth range, the fifth division position is determined based on the preset division interval, wherein the fifth range is from the second road segment boundary point to the first fork in the road ahead of the vehicle or the third preset distance;

[0124] The position to be divided is determined based on the third, fourth, and fifth division positions.

[0125] In this embodiment of the invention, the third range can be understood as the area starting from the second preset distance behind the vehicle's direction of travel and ending at the first road segment boundary point (i.e., the first road segment boundary point).

[0126] The third division position can be understood as a coordinate point determined according to a preset division interval within the third range, used to indicate the start or end point of the grid division, ensuring an accurate description of the environment behind the vehicle.

[0127] The first road segment boundary can be understood as the point in the direction of vehicle travel where the road network structure changes closest to the vehicle, such as the increase or decrease in the number of lanes, road turning points, etc., and there are no restrictions here.

[0128] The second road segment boundary can be understood as the next key point on the road where structural changes occur again after the first road segment boundary, used to define the transition between the fourth and fifth ranges.

[0129] The fourth range can be understood as the road area located from the first road segment boundary point to the second road segment boundary point.

[0130] The fourth division position can be understood as the coordinate point determined based on the same preset division interval within the fourth range. It is used to guide the grid division and ensure that the road features between the first and second road segment boundary points are accurately captured. There are no restrictions here.

[0131] The fifth range can be understood as starting from the second road segment boundary point and extending to the first fork in the road ahead of the vehicle or the third preset distance.

[0132] The fifth division position can be understood as the coordinate point determined along the preset division interval within the fifth range. It is used to subdivide the grid and ensure a detailed depiction of road information at a distance, such as the lane layout at a fork in the road. There are no restrictions here.

[0133] In response to the existence of multiple road segment boundary points within the grid division range, determining the third division position within the third range based on the preset division interval can be understood as follows: when the system identifies multiple road segment boundary points, within the road area (third range) between the second preset distance behind the vehicle and the nearest first road segment boundary point, the start and end points of the grid division are set one by one according to the preset division interval, which is the third division position.

[0134] The determination of the fourth division position based on the preset division interval within the fourth range can be understood as follows: within this intermediate road segment (i.e., the fourth range) extending from the first road segment boundary point to the next road segment boundary point (the second road segment boundary point), the grid division position is also set according to the preset interval distance, i.e., the fourth division position.

[0135] The determination of the fifth division position based on the preset division interval within the fifth range can be understood as the grid division node determined according to the preset interval within the road range (i.e., the fifth range) from the second road segment boundary point to the first fork in the road ahead of the vehicle or the third preset distance, i.e., the fifth division position.

[0136] Determining the position to be divided based on the third, fourth, and fifth division positions can be understood as forming a complete grid division coordinate system, i.e., the position to be divided, by integrating the third, fourth, and fifth division positions.

[0137] In this embodiment of the invention, based on the proposed multi-boundary point grid division strategy, the invention can accurately place the division positions between different road segment boundary points, avoiding heavy reliance on high-precision maps, utilizing the vehicle's existing perception and navigation data, reducing the cost of map updates and maintenance, while maintaining high mapping accuracy and efficiency.

[0138] Optionally, in any grid, combining the lane alignment points of the current frame in any grid according to the mapping relationship to obtain the segment line of the current frame in any grid includes the following steps:

[0139] Determine lane markings in the road surrounding the vehicle based on perception data;

[0140] The lane lines are classified according to the lane line classification rules to obtain the first lane line and the second lane line. The left lane of the first lane line has the same driving direction as the right lane line, while the left lane of the second lane line has a different driving direction than the right lane line.

[0141] Based on the lane alignment points of the first lane line, determine multiple target lane alignment points in any grid;

[0142] By combining multiple target lane alignment points, the segment line of the current frame in any grid is obtained.

[0143] In this embodiment of the invention, the lane line classification rule can be understood as a method and criterion for distinguishing lane lines based on the attributes of lane lines in vehicle perception data (such as the direction, type, and connectivity of lane lines).

[0144] The first lane line can be understood as a lane line where the driving direction is the same on both the left and right sides.

[0145] The second lane line can be understood as a lane line where the driving directions of the left and right lanes are not the same, such as the dividing line between lanes. One side may be a left-turn or right-turn lane, while the other side is a straight or other turning lane.

[0146] For example, Figure 7 This is a schematic diagram of lane line classification rules according to an embodiment of the present invention, such as... Figure 7 As shown, taking lane lines as an example, the direction indicated by the arrow is the driving direction of the lane. The first lane line is the lane line where the driving directions of the left and right lanes are the same, and the second lane line is the lane line where the driving directions of the left lane and the right lane are different.

[0147] Determining lane markings in the road surrounding a vehicle based on perception data can be understood as using the vehicle's sensing elements (such as cameras and radar) and autonomous driving deep learning algorithms to analyze and identify lane marking information in the surrounding environment in real time, including the position, shape, and attributes (such as dashed lines, solid lines, and colors) of the lane markings, laying the foundation for subsequent lane marking classification and map construction.

[0148] Classifying lane lines based on lane line classification rules, resulting in first and second lane lines, can be understood as dividing perceived lane lines into two categories according to their direction and traffic flow characteristics. The first lane line specifically refers to lane lines where the travel directions of the two lanes are the same, typically representing lanes where vehicles travel in the same direction. The second lane line, on the other hand, represents lane lines where the travel directions of the two lanes are different, such as road boundaries or dividing lines between lanes traveling in different directions. This information helps to accurately describe the structure and layout of the road.

[0149] Determining multiple target lane alignment points in any grid based on lane alignment points of the first lane line can be understood as selecting key lane alignment points from the first lane line, such as the start point, midpoint, and end point, further processing and analyzing these key lane alignment points, and using these key lane alignment points as a basis to determine multiple target alignment points representing lane line characteristics in each grid of the gridded map. These target alignment points will be used to describe and construct lane information in the direction of vehicle travel.

[0150] Figure 6 This is a schematic diagram illustrating the segmentation of effective lane lines into grids according to an embodiment of the present invention, as shown below. Figure 6As shown, for example, the binary search algorithm or traversal algorithm is used to traverse the points on the effective lane lines, determine whether the longitudinal coordinates of the lane line points are within the grid division range, find the grid corresponding to the lane line points, and put the lane line points into the grid to form local lane lines. To simplify the data, the local lane lines only save the start point, end point, midpoint, lane type, and whether it is the left lane boundary or the right lane boundary. There are no restrictions here.

[0151] Combining multiple target lane alignment points to obtain the current frame segment line in any grid can be understood as connecting and combining all target lane alignment points in the same grid according to a specific algorithm to form a segment line describing the local road conditions. The above segment line represents the actual layout and characteristics of the lane lines in each grid at the current moment (i.e., the current frame), providing real-time and accurate map data support for subsequent lane changing strategies and path planning.

[0152] In this embodiment of the invention, by utilizing perception data, classifying lane lines, selecting lane line type points, and combining them into segment lines, a lane-level local map of the road surrounding the vehicle is constructed, providing key environmental perception information for the autonomous driving system and helping to improve driving safety and efficiency.

[0153] Optionally, constructing a lane-level local road map based on the segment lines of the current frame includes:

[0154] Determine the midpoint lane alignment point of the current frame segment line;

[0155] Based on the coordinate information of the midpoint lane alignment point, the segmented lines of the current frame are merged to obtain the merged lane lines;

[0156] The lane line type is adjusted based on the lane line type rule to obtain the adjusted merged lane line. The lane line type rule is used to merge lane lines with mismatched lane line types into solid line type lane lines.

[0157] A lane-level local road map is constructed based on the adjusted segment lines of the current frame.

[0158] In this embodiment of the invention, the midpoint lane line type point can be understood as a representative point selected in the current frame segment line to describe the lane line features, and this point is located at the midpoint of the segment line.

[0159] Determining the midpoint of the current frame segment line can be understood as selecting a lane alignment point located in the middle of the current frame segment line within each grid as the representative point of that lane line.

[0160] Based on the coordinate information of the midpoint lane line type points, the segment lines of the current frame are merged to obtain merged lane lines. This can be understood as comparing the abscissas of the midpoint type points of each segment line. If the abscissas of the midpoint type points of two or more segment lines are similar, then these lane lines may belong to the same lane or adjacent lanes within the grid. In this case, these segment lines can be merged into a longer lane line (i.e., merged lane line) to more accurately depict the true structure of the road. If the lane line types do not match, type adjustment will be performed based on the principle of solid line priority.

[0161] Adjusting the lane line type of merged lane lines based on lane line type rules results in merged lane lines that, if inconsistencies in lane line types are encountered during the merging process (e.g., a dashed line and a solid line), are uniformly adjusted to the higher-priority type (usually solid lines) according to preset lane line type rules (e.g., solid lines have higher priority than dashed lines), ensuring the consistency and accuracy of map data.

[0162] Constructing a lane-level local road map based on the adjusted segmented lines of the current frame can be understood as follows: after completing the merging and type adjustment of lane lines, the adjusted merged lane lines are used as input data, and a suitable data structure is used to construct a lane-level local small map describing the road conditions around the vehicle.

[0163] In this embodiment of the invention, the above steps integrate all lane line information to form an orderly, coherent and easy-to-understand map model, providing real-time lane-level navigation information for the autonomous driving system and supporting the autonomous driving system to make reasonable path planning and driving decisions.

[0164] Optionally, merging the segmented lines of the current frame based on the coordinate information of the midpoint lane alignment point to obtain the merged lane line includes the following steps:

[0165] In response to the coordinate distance between adjacent midpoint lane alignment points being less than a preset coordinate distance, the current frame segment lines to which the adjacent midpoint lane alignment points belong are merged to obtain merged lane lines.

[0166] In this embodiment of the invention, in response to the coordinate distance between adjacent midpoint lane line points being less than a preset coordinate distance, the current frame segment lines to which the adjacent midpoint lane line points belong are merged to obtain a merged lane line. This can be understood as follows: based on the lane line grid division, by calculating the coordinate distance between midpoint lane line points within the same grid or across grids, if the lateral coordinate distance between adjacent points is less than a preset threshold (i.e., a preset coordinate distance), then these two lane lines are considered to actually belong to the same lane or are very close to each other, and can be regarded as different parts of the same lane. At this time, the system will logically merge the current frame segment lines to which these midpoint points belong to generate a continuous and longer lane line, i.e., a merged lane line.

[0167] In this embodiment of the invention, the above steps help to eliminate lane line fragmentation caused by errors in the data acquisition or processing process, making the constructed lane-level local road map more coherent and accurate, and providing clearer and more consistent navigation guidance for autonomous vehicles.

[0168] Optionally, based on the refined map data, navigation route information, and current lane information, rendering lane-level navigation guide segments in the lane-level local road map to update the lane-level local road map includes the following steps:

[0169] The route to be traveled is determined based on the high-precision map data, navigation route information, current lane information, and merged lane lines;

[0170] The target lane lines that constitute the driving path are determined based on the merged lane lines.

[0171] The coordinate information of the lane-level navigation guidance point is determined based on the coordinate information of the midpoint lane alignment point corresponding to the target lane line.

[0172] Generate lane-level navigation guide lines based on the coordinate information of lane-level navigation guide points;

[0173] Determine the lane boundary lines based on the second lane line;

[0174] Render lane-level navigation guide segments and lane boundary lines in the lane-level local road map to update the lane-level local road map.

[0175] In this embodiment of the invention, determining the driving path based on standard precision map data, navigation route information, current lane information, and merging lane lines can be understood as combining standard precision map data, route information planned by the vehicle navigation system, lane information where the vehicle is currently located, and merging lane lines obtained through the above process, so that the system can intelligently analyze and determine the driving path that the vehicle should follow.

[0176] Determining the target lane line that constitutes the driving path based on merging lane lines can be understood as, after determining the driving path, further identifying which merging lane lines constitute this path, thus obtaining the target lane line. The selection of the target lane line ensures that the route planning matches real-time traffic conditions, providing the vehicle with clear driving guidance.

[0177] Determining the coordinates of lane-level navigation guidance points based on the coordinates of the midpoint lane alignment points corresponding to the target lane line can be understood as selecting the midpoint lane alignment points on the target lane line as key reference points, and using the coordinates of these points to determine a series of navigation guidance point coordinates.

[0178] Generating lane-level navigation guide segments based on the coordinate information of lane-level navigation guide points can be understood as connecting the aforementioned lane-level navigation guide points to form continuous line segments, i.e., lane-level navigation guide segments. These guide segments visually indicate the driving direction the vehicle should follow. Through dynamic updates and real-time rendering, they provide clear visual guidance for the driver or autonomous driving system, helping the vehicle to drive safely and accurately in the target lane.

[0179] Determining lane boundaries based on the second lane line can be understood as using the previously classified second lane lines (i.e., lane lines where the left and right lanes have different travel directions) to determine and mark the lane boundaries, that is, the lines that vehicles need to avoid crossing. Identifying lane boundaries helps autonomous driving systems keep vehicles within the correct lane and avoid accidents caused by mistakenly entering other traffic flows.

[0180] Rendering lane-level navigation guide segments and lane boundary lines in a lane-level local road map to update the map can be understood as adding the generated lane-level navigation guide segments and defined lane boundary line information to the lane-level local road map for visual display. By updating these key elements on the map in real time, the system can provide drivers or autonomous driving systems with the latest and most detailed lane-level navigation information, ensuring safety and accuracy during driving.

[0181] In this embodiment of the invention, the above steps combine a high-precision map, real-time navigation route, current lane information, and optimized lane line data to accurately calculate the vehicle's intended driving path, determine the target lane lines along the path, and generate lane-level navigation guidance using midpoint lane line type points to ensure the vehicle follows the correct lane. Simultaneously, lane boundaries are clearly defined, improving driving safety. By rendering navigation guidance and lane boundaries in real-time on a local map, this invention achieves lane-level navigation services without the need for high-precision maps, significantly reducing application costs, improving the flexibility and reliability of autonomous driving systems, and providing an efficient and safe solution for intelligent mobility.

[0182] Figure 8 This is a schematic diagram illustrating the sorting, merging, and filtering of local lane lines within a grid according to an embodiment of the present invention. As shown in the figure, exemplarily, based on the x and y coordinates of the midpoint of the local lane lines, the lane lines within each grid are sorted. Two pointers traverse the lane lines within each grid. If the x-coordinates or y-coordinates of the midpoints of two lane lines are similar, they can be merged. If the types do not match, solid lines are prioritized, and the merging rules are: solid line + solid line = solid line, solid line + dashed line = solid line, dashed line + dashed line = dashed line. Filtering the local lane lines includes removing lane lines within each grid that are to the left of the left boundary of the vehicle's drivable area and to the right of the right boundary of the vehicle's drivable area. After merging and filtering, the local lane line data within the grid can describe the lane-level minimap ahead and be used for subsequent path planning; no limitations are imposed here.

[0183] This application defines three classes using a coding language to construct and manage lane-level small map data structures. These classes are designed to store and process information related to road boundaries, lane lines, and entire road segments, thereby supporting lane-level navigation and autonomous driving functions. First is the SLRocalBoundary structure, which is the data structure used in this invention to describe the characteristics of lane boundaries or lane lines in a local road map. In the SLRocalBoundary structure, type indicates the boundary type, which may be the type of lane line (e.g., solid line, dashed line, etc.). startPoint is the two-dimensional coordinate of the lane line's starting point, typically represented by a Vector2 type (x, y). endPoint is the two-dimensional coordinate of the lane line's ending point, also using the Vector2 type. midPoint is the two-dimensional coordinate of the lane line's midpoint, used to provide midpoint location information when processing lane line segments. featurePointNum may represent the number of feature points on that boundary or lane line, used for lane line feature retrieval or processing in subsequent algorithms. Secondly, there is the SRRocalSegment class. The SRRocalSegment class is a data structure in this invention representing a segment of the road in front of or where the vehicle is located, with lane-level details. The boundaries in the SRRocalSegment class are a List. <srlocalboundary>This is a list of types used to store lane boundaries or lane line information within a road segment. `startDist` and `endDist` represent the start and end distances of the road segment, respectively, in meters, describing the segment's position in the vehicle's direction of travel. `curLaneNum` is the number of lanes in the current road segment, used to assist vehicle localization and route planning. The `Clean` method clears the data in the `SRLocalSegment` object, including clearing the boundary list and resetting the distance and lane number parameters to their default values. This is very useful when updating small map data, ensuring the system can rebuild the data from a clean state. Finally, there is the `SRLocalSegmentInfo` class, which is a container used in this invention to manage and store multiple `SRLocalSegment` instances. The `SRLocalSegmentInfo` class integrates lane-level information from all road segments as part of the lane-level local road map. Within the `SRLocalSegmentInfo` class, `segments` is a List. <srlocalsegment>This is a list of types used to store information about multiple road segments within the entire small map. `validSegNum` represents the number of valid road segments, i.e., the number of road segments actually used in the current small map, which helps the algorithm quickly locate and process valid data. The `Clean` method is used to clear the data in the `SRLocalSegmentInfo` object. First, the number of valid road segments is reset to 0. Then, the `segments` list is traversed, and the `Clean` method of each `SRLocalSegment` object is called to clear the entire small map data, ensuring the real-time nature and accuracy of the data.

[0184] In summary, this application constructs a lane-level minimap data model by defining three classes: SRRocalBoundary, SRRocalSegment, and SRRocalSegmentInfo. The model includes lane line types, location information (start point, end point, midpoint), the number of feature points on the lane lines, and key attributes such as the start and end distances of road segments and the number of lanes. Through these data structures, the system can efficiently store and process the information required for lane-level navigation. Simultaneously, the implementation of the Clean method ensures timely data updates and cleanup, providing a solid data foundation for real-time navigation and autonomous driving functions.

[0185] Based on perception data and navigation v2 data, this application can construct lane-level small map information in front of the vehicle, and can simplify the road topology by using a grid-based approach to construct lane-level small map information in front of the vehicle.

[0186] Furthermore, this application relies heavily on autonomous driving perception capabilities, utilizing perception data such as lane alignment points, lane type attributes, and left and right driving directions of lane lines. If further lane line topology information is available, such as left-right relationships and connectivity, this application can further construct a more accurate road grid. This application can also, based on downstream algorithm requirements, require the mapping module to provide some application programming interface (API) query interfaces. For example, obtaining the lane index of the vehicle, or obtaining the number of lanes at a given distance ahead, etc., are not limited here.

[0187] 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0188] According to an embodiment of the present invention, a navigation device for lane-level local maps is provided. It should be noted that the device can be used to execute the above-described road network mapping method.

[0189] Figure 9 This is a schematic diagram of a navigation device with a lane-level local map according to an embodiment of the present invention, such as... Figure 9 As shown, the lane-level local map navigation device 900 includes: an activation module 901, used to activate the local map navigation mode in response to receiving a local map navigation activation signal; an acquisition module 902, used to acquire high-precision map data and perception data, wherein the high-precision map data is used to provide road network structure data of the roads surrounding the vehicle, and the perception data is used to describe the road environment of the roads surrounding the vehicle; and a construction module 903, used to construct a lane-level local road map based on the high-precision map data and perception data, wherein the lane-level local road map is used to display roads within a first preset distance range ahead of the vehicle that match the navigation route. The local road map includes lane lines; the rendering module 904 is used to render lane-level navigation guide lines in the lane-level local road map based on the high-precision map data, navigation route information, and the current lane information of the vehicle. The lane-level navigation guide lines are located within a first preset distance range in front of the vehicle in the navigation interface. The current lane information of the vehicle is the lane information of the vehicle currently located in the lane-level local road map. The lane-level navigation guide lines are used to provide navigation information for the vehicle in the lane-level local road map; the navigation module 905 is used to navigate the vehicle based on the lane-level local road map and the lane-level navigation guide lines.

[0190] According to another aspect of the present invention, a vehicle is also provided for performing the methods of the various embodiments of the present invention.

[0191] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0192] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0193] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0194] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0195] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0196] The units described as separate components may or may not be physically separate. 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 can be selected to achieve the purpose of this embodiment according to actual needs.

[0197] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0198] If the integrated unit is implemented as 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, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0199] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.< / srlocalsegment> < / srlocalboundary>

Claims

1. A navigation method using lane-level local maps, applied to a vehicle, characterized in that, include: Upon receiving a local map navigation start signal, local map navigation mode is activated. Acquire high-precision map data and perception data, wherein the high-precision map data is used to provide road network structure data of the roads around the vehicle, and the perception data is used to describe the road environment of the roads around the vehicle; Based on the standard map data and the perception data, a lane-level local road map is constructed, wherein the lane-level local road map is used to display the road within a first preset distance range in front of the vehicle that matches the navigation route, and the lane-level local road map includes lane lines; Based on the high-precision map data, navigation route information, and the vehicle's current lane information, lane-level navigation guide lines are rendered in the lane-level local road map. The lane-level navigation guide lines are located within the first preset distance range in front of the vehicle in the navigation interface. The vehicle's current lane information is the lane information where the vehicle is currently located in the lane-level local road map. The lane-level navigation guide lines are used to provide the vehicle's navigation information in the lane-level local road map. Navigate the vehicle based on the lane-level local road map and the lane-level navigation guide line segments; The construction of a lane-level local road map based on the refined map data and the perception data includes: Based on the refined map data, multiple grids in the vehicle coordinate system are determined; based on the perception data, the lane alignment points corresponding to the current frame are determined; in any grid, based on the mapping relationship between the lane alignment points of the current frame and the multiple grids, the lane alignment points of the current frame in any grid are combined to obtain the segment lines of the current frame in any grid; based on the segment lines of the current frame, the lane-level local road map is constructed.

2. The method according to claim 1, characterized in that, The lane-level local road map is also used to display the road within a second preset distance range behind the vehicle, the area of ​​the second preset distance range being smaller than the area of ​​the first preset distance range.

3. The method according to claim 1, characterized in that, The starting point of the lane-level navigation guide line segment is located at the front of the vehicle in the navigation interface, and the ending point of the lane-level navigation guide line segment is located on the road within the first preset distance range in front of the vehicle that matches the navigation route in the navigation interface. The display area of ​​the lane-level local road map is smaller than the display area of ​​the vehicle navigation interface.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: The lane alignment points of the current frame are mapped to the multiple grids in the vehicle coordinate system to obtain the mapping relationship between the lane alignment points of the current frame and the multiple grids, wherein the mapping relationship is used to record the grid to which any lane alignment point of the current frame belongs.

5. The method according to claim 4, characterized in that, The step of determining multiple grids in the vehicle coordinate system based on the refined map data includes: Based on the high-precision map data, the grid division range of the vehicle coordinate system is determined, wherein the grid division range is from a second preset distance behind the vehicle's direction of travel to the first fork in the road or a third preset distance in front of the vehicle's direction of travel. The location to be divided is determined based on the preset division interval and the road segment boundary points in the grid division range; The vehicle coordinate system is divided based on the position to be divided, resulting in the multiple grids under the vehicle coordinate system.

6. The method according to claim 5, characterized in that, The step of determining the location to be divided based on the preset division interval and the road segment boundary points in the grid division range includes: In response to the existence of a road segment boundary point within the grid division range, a first division position is determined within a first range based on the preset division interval, wherein the first range is from the second preset distance behind the vehicle's driving direction to the road segment boundary point; The second division position is determined based on the preset division interval within the second range, wherein the second range is from the road segment boundary point to the first fork in the road ahead of the vehicle's direction of travel or the third preset distance; The position to be divided is determined based on the first division position and the second division position.

7. The method according to claim 5, characterized in that, The step of determining the location to be divided based on the preset division interval and the road segment boundary points in the grid division range includes: In response to the existence of multiple road segment boundary points within the grid division range, a third division position is determined within a third range based on the preset division interval. The multiple road segment boundary points include a first road segment boundary point and a second road segment boundary point. The distance between the first road segment boundary point and the vehicle is closer than the distance between the second road segment boundary point and the vehicle. The third range extends from the second preset distance behind the vehicle in the direction of travel to the first road segment boundary point. The fourth division position is determined based on the preset division interval within the fourth range, wherein the fourth range is from the first road segment boundary point to the second road segment boundary point; The fifth division position is determined based on the preset division interval within the fifth range, wherein the fifth range is from the second road segment boundary point to the first fork in the road in front of the vehicle or the third preset distance; The position to be divided is determined based on the third division position, the fourth division position, and the fifth division position.

8. The method according to claim 4, characterized in that, In any grid, combining the lane alignment points of the current frame in any grid according to the mapping relationship to obtain the segment line of the current frame in any grid includes: Based on the perceived data, lane markings in the road surrounding the vehicle are determined; The lane lines are classified according to the lane line classification rules to obtain a first lane line and a second lane line. The left lane and the right lane of the first lane line have the same driving direction, while the left lane and the right lane of the second lane line have different driving directions. Based on the lane alignment points of the first lane line, determine multiple target lane alignment points in any grid; The multiple target lane alignment points are combined to obtain the current frame segment line in any of the grids.

9. The method according to claim 8, characterized in that, The construction of a lane-level local road map based on the current frame segment lines includes: Determine the midpoint lane alignment point of the current frame segment line; Based on the coordinate information of the midpoint lane alignment point, the segmented lines of the current frame are merged to obtain merged lane lines; The lane line type is adjusted based on the lane line type rule to obtain the adjusted merged lane line. The lane line type rule is used to merge lane lines with mismatched lane line types into solid line type lane lines. The lane-level local road map is constructed based on the adjusted segment lines of the current frame.

10. The method according to claim 9, characterized in that, The process of merging the segmented lines of the current frame based on the coordinate information of the midpoint lane alignment point to obtain merged lane lines includes: In response to the fact that the coordinate distance between adjacent midpoint lane alignment points is less than a preset coordinate distance, the current frame segment lines to which the adjacent midpoint lane alignment points belong are merged to obtain the merged lane line.

11. The method according to claim 9, characterized in that, The step of rendering lane-level navigation guide segments in the lane-level local road map based on the refined map data, navigation route information, and current lane information to update the lane-level local road map includes: The route to be traveled is determined based on the refined map data, the navigation route information, the current lane information, and the merged lane lines; The target lane lines constituting the driving path are determined based on the merged lane lines. The coordinate information of the lane-level navigation guidance point is determined based on the coordinate information of the midpoint lane line corresponding to the target lane line. The lane-level navigation guide line segment is generated based on the coordinate information of the lane-level navigation guide point; Determine the lane boundary line based on the second lane line; The lane-level navigation guide segments and lane boundary lines are rendered in the lane-level local road map to update the lane-level local road map.

12. A lane-level local map navigation device, applied to a vehicle, characterized in that, include: The module is activated in response to receiving a local map navigation start signal to enable local map navigation mode. The acquisition module is used to acquire high-precision map data and perception data, wherein the high-precision map data is used to provide road network structure data of the roads around the vehicle, and the perception data is used to describe the road environment of the roads around the vehicle. A construction module is used to construct a lane-level local road map based on the standard map data and the perception data, wherein the lane-level local road map is used to display the road within a first preset distance range in front of the vehicle that matches the navigation route, and the lane-level local road map includes lane lines; The rendering module is used to render lane-level navigation guide lines in the lane-level local road map based on the high-precision map data, navigation route information, and the current lane information of the vehicle. The lane-level navigation guide lines are located within the first preset distance range in front of the vehicle in the navigation interface. The current lane information of the vehicle is the lane information of the vehicle in the lane-level local road map. The lane-level navigation guide lines are used to provide navigation information of the vehicle in the lane-level local road map. The navigation module is used to navigate the vehicle based on the lane-level local road map and the lane-level navigation guide line segments; The construction module is further configured to: determine multiple grids in the vehicle coordinate system based on the refined map data; determine the current frame lane alignment points corresponding to the current frame based on the perception data; in any grid, combine the current frame lane alignment points in any grid according to the mapping relationship between the current frame lane alignment points and the multiple grids to obtain the current frame segment line in any grid; and construct the lane-level local road map based on the current frame segment line.

13. A vehicle, characterized in that, The vehicle is used to perform the lane-level local map navigation method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the navigation method of lane-level local map as described in any one of claims 1 to 11 when run on a computer or processor.

15. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the navigation method of lane-level local map as described in any one of claims 1 to 11.

16. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the navigation method for lane-level local maps as described in any one of claims 1 to 11.

Images