Lane linear point output method and device, electronic equipment and storage medium

By restoring the lane ahead of the vehicle in the high-precision map and outputting continuous lane line point information, the problem of poor intelligent driving stability caused by incomplete lane lines in the high-precision map is solved, and the stability and user experience of intelligent driving are improved.

CN120348310APending Publication Date: 2025-07-22HAOMO TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410089274.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-01-22
Publication Date
2025-07-22

AI Technical Summary

Technical Problem

The lane lines in the existing high-precision maps are not perfect enough, resulting in poor intelligent driving stability and poor user experience when the lane lines are not obvious or there is no lane lines.

Method used

By acquiring high-precision map data, the lane within the preset distance in front of the vehicle is restored based on the map data, continuous lane line point information is output, and continuous lane lines are constructed to ensure that the vehicle can drive smoothly during intelligent driving.

Benefits of technology

It improves the stability and user experience of the intelligent driving process, ensuring that the vehicle can successfully drive intelligently based on the continuous lane lines output by the high-precision map when the lane lines are not obvious or there is no lane lines.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120348310A_ABST
    Figure CN120348310A_ABST
Patent Text Reader

Abstract

The invention provides a lane linear point output method and device, electronic equipment and a storage medium, and the method is applied to the field of vehicles, and comprises the steps: obtaining map data of a high-precision map; based on the map data, restoring lanes within a preset distance in front of the vehicle; outputting lane linear point information according to the restored lane; wherein the restored lane is a continuous lane, and the lane line shape point information is used for forming a continuous lane line. The method can improve the stability of the intelligent driving process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more specifically, to a method, device, electronic device, and storage medium for outputting lane line points in the field of vehicles. Background Art

[0002] Currently, vehicles can automatically drive along the navigation route throughout the journey on the highway by means of the intelligent driving assistance system installed. However, during the process of the vehicle using the intelligent driving assistance system to achieve automatic driving, the vehicle may encounter situations where the lane lines are not obvious or even there are no lane lines on the actual road, and there may also be situations where the camera recognition is poor in some sections. In such situations, the vehicle can usually use the lane lines in the high-precision map to achieve autonomous driving. However, the lane lines in the high-precision map are not perfect, resulting in a poor intelligent driving experience. Summary of the Invention

[0003] The present application provides a method, device, electronic device, and storage medium for outputting lane line points, and this method can improve the stability of the intelligent driving process.

[0004] In a first aspect, a method for outputting lane line points is provided. The method includes: obtaining map data of a high-precision map; based on the map data, restoring the lanes within a preset distance in front of the vehicle; and outputting lane line point information according to the restored lanes. Among them, the restored lanes are continuous lanes, and the lane line point information is used to form continuous lane lines.

[0005] In the above technical solution, first obtain the map data in the high-precision map, and then based on the map data, restore the lanes within a preset distance in front of the vehicle. Restoring the road within a preset distance in front based on the map data in the high-precision map can be used by the vehicle during the intelligent driving process, which can better ensure the stability of the intelligent driving process. Output lane line point information according to the restored lanes. Among them, the restored lanes are continuous and complete lanes, and the lane line point information is used to form continuous lane lines. By outputting the lane line point information for forming the lane lines, the lane lines of the road ahead can be restored in terms of data form, so that in the case of unclear or no lane lines during the vehicle's autonomous driving process, it can still smoothly perform intelligent driving based on the continuous lane lines output based on the high-precision map, improving the stability of the intelligent driving process.

[0006] In combination with the first aspect, in some implementations of the first aspect, the map data includes a plurality of road blocks and the connection relationships between lanes. Based on the map data, restoring the lanes within a preset distance in front of the vehicle includes: determining the target road block where the vehicle is currently located among the plurality of road blocks; determining the first target lane where the vehicle is located in the target road block; determining the target connection relationship between the first target lane and the lanes within a preset distance in front of the vehicle according to the connection relationships between the lanes; and restoring the lanes within a preset distance in front of the vehicle according to the target connection relationship.

[0007] In combination with the first aspect and the above implementation, in some implementations of the first aspect, determining the target connection relationship between the first target lane and the lanes within a preset distance in front of the vehicle according to the connection relationships between the lanes includes: when there are multiple lanes within the preset distance in front of the vehicle that have connection relationships with the first target lane, determining the lanes that meet the preset conditions among the multiple lanes as the second target lanes connected to the first target lane; when there is a single lane within the preset distance in front of the vehicle that has a connection relationship with the first target lane, determining the single lane as the second target lane connected to the first target lane; and determining the connection relationship between the first target lane and the second target lane as the target connection relationship.

[0008] In combination with the first aspect and the above implementation, in some implementations of the first aspect, determining the lanes that meet the preset conditions among the multiple lanes as the second target lanes connected to the first target lane includes: if the total lane width of the multiple lanes is greater than the lane width of the first target lane, determining the lane that is connected to both the left and right lane lines of the first target lane among the multiple lanes as the second target lane; or if the total lane width of the multiple lanes is equal to the lane width of the first target lane, determining the lane that is in the same direction as the navigation path of the vehicle among the multiple lanes as the second target lane.

[0009] In the above technical solution, when there are multiple lanes that have connection relationships with the first target lane, determining the lanes that meet the preset conditions as the second target lanes can restore the road to the original road form as much as possible based on the high-precision map, and ensure that the determined second target lane is the lane that is in the same direction as the vehicle driving direction, without the user taking over the vehicle to change lanes, which can further improve the stability of intelligent driving and enhance the user experience.

[0010] In combination with the first aspect and the above implementation, in some implementations of the first aspect, restoring the lanes within a preset distance in front of the vehicle according to the target connection relationship includes: connecting the first target lane and the second target lane according to the connection relationship between the first target lane and the second target lane to restore the lanes within a preset distance in front of the vehicle.

[0011] Combined with the first aspect and the above implementation manners, in some implementation manners of the first aspect, according to the restored lane, lane alignment point information is output, including: obtaining the lane lines of the restored lane; wherein, the restored lane includes the lane after the connection of the first target lane and the second target lane, and the lane lines include the left line, the right line and the center line; determining a second target lane line in the lane lines of the second target lane according to the lane lines of the restored lane; wherein, the second target lane line is connected to the first target lane line in the first target lane, and the first target lane line and the second target lane line are lane lines in the same direction; outputting the lane alignment point information corresponding to the second target lane line and the lane alignment point information corresponding to all the lane lines of the first target lane.

[0012] Combined with the first aspect and the above implementation manners, in some implementation manners of the first aspect, after outputting the lane alignment point information according to the restored lane, the method further includes: based on the lane alignment point information corresponding to the continuous lane lines in the output lane, fitting the continuous lane alignment points to construct continuous lane lines.

[0013] In the above technical solution, only the lane alignment point information corresponding to the continuous lane lines is output, and continuous lane lines are constructed based on the lane alignment point information corresponding to the continuous lane lines, so that the vehicle end can generate a driving reference line based on the continuous lane lines and successfully complete the intelligent driving task based on the driving reference line, improving the reliability of intelligent driving.

[0014] In a second aspect, an apparatus for outputting lane alignment points is provided, the apparatus including: an obtaining module, configured to obtain map data of a high-precision map; a restoring module, configured to restore the lanes within a preset distance in front of the vehicle based on the map data; an output module, configured to output lane alignment point information according to the restored lane; wherein, the restored lane is a continuous lane, and the lane alignment point information is used to form continuous lane lines.

[0015] Combined with the second aspect, in some implementation manners of the second aspect, the map data includes a plurality of road blocks and the connection relationships between lanes, and the restoring module is specifically configured to: determine the target road block where the vehicle is currently located among the plurality of road blocks; determine the first target lane where the vehicle is located in the target road block; determine the target connection relationship between the first target lane and the lanes within a preset distance in front of the vehicle according to the connection relationships between the lanes; and restore the lanes within a preset distance in front of the vehicle according to the target connection relationship.

[0016] Combined with the second aspect and the above implementation manners, in some implementation manners of the second aspect, the restoration module further includes a first determination unit, and the first determination unit is specifically configured to: when there are multiple lanes having a connection relationship with the first target lane within the preset distance ahead, determine the lane that meets the preset conditions among the multiple lanes as the second target lane connected to the first target lane; when there is a single lane having a connection relationship with the first target lane within the preset distance ahead, determine the single lane as the second target lane connected to the first target lane; and determine the connection relationship between the first target lane and the second target lane as the target connection relationship.

[0017] Combined with the second aspect and the above implementation manners, in some implementation manners of the second aspect, the first determination unit is further specifically configured to: if the total lane width of the multiple lanes is greater than the lane width of the first target lane, determine the lane that is connected to both the left and right lane lines of the first target lane among the multiple lanes as the second target lane; or; if the total lane width of the multiple lanes is equal to the lane width of the first target lane, determine the lane that is in the same direction as the navigation path of the vehicle among the multiple lanes as the second target lane.

[0018] Combined with the second aspect and the above implementation manners, in some implementation manners of the second aspect, the restoration module is specifically configured to: connect the first target lane and the second target lane according to the connection relationship between the first target lane and the second target lane, so as to restore the lanes within the preset distance ahead of the vehicle.

[0019] Combined with the second aspect and the above implementation manners, in some implementation manners of the second aspect, the output module is specifically configured to: obtain the lane lines of the restored lane; wherein, the restored lane includes the lane after the connection of the first target lane and the second target lane, and the lane lines include a left line, a right line, and a center line; determine a second target lane line among the lane lines of the second target lane according to the lane lines of the restored lane; wherein, the second target lane line is connected to the first target lane line in the first target lane, and the first target lane line and the second target lane line are lane lines in the same direction; and output the lane line shape point information corresponding to the second target lane line and the lane line shape point information corresponding to all the lane lines of the first target lane.

[0020] Combined with the second aspect and the above implementation manners, in some implementation manners of the second aspect, the device further includes a fitting module, and the fitting module is specifically configured to: based on the lane line shape point information corresponding to the continuous lane lines in the output lane, fit the continuous lane line shape points to construct continuous lane lines.

[0021] In a third aspect, an electronic device is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the electronic device executes the lane linear point output method in the first aspect and any possible implementation of the first aspect above.

[0022] In a fourth aspect, a computer program product is provided, including: computer program code, when the computer program code runs on a computer, enabling the computer to execute the lane linear point output method in the first aspect and any possible implementation of the first aspect above.

[0023] In a fifth aspect, a computer-readable storage medium is provided, storing computer program code, when the computer program code runs on a computer, enabling the computer to execute the lane linear point output method in the first aspect and any possible implementation of the first aspect above. Description of the Drawings

[0024] Figure 1 is a schematic flowchart of a lane linear point output method provided by an embodiment of the present application;

[0025] Figure 2 is a schematic diagram of the form of an original road form and a high-precision map data storage format provided by an embodiment of the present application;

[0026] Figure 3 is a schematic diagram of a method for determining a road block and a first target lane in a high-precision map provided by an embodiment of the present application;

[0027] Figure 4(a) is a schematic diagram of the form of a special lane provided by an embodiment of the present application;

[0028] Figure 4(b) is a schematic diagram of another special lane provided by an embodiment of the present application;

[0029] Figure 4(c) is a schematic diagram of yet another special lane provided by an embodiment of the present application;

[0030] Figure 5(a) is a schematic diagram of the form of a lane connection provided by an embodiment of the present application;

[0031] Figure 5(b) is a schematic diagram of another lane connection provided by an embodiment of the present application;

[0032] Figure 5(c) is a schematic diagram of yet another lane connection provided by an embodiment of the present application;

[0033] Figure 6 is a schematic flowchart of another lane linear point output method provided by an embodiment of the present application;

[0034] Figure 7 FIG. 2 is a schematic structural diagram of an output device for lane line points provided by an embodiment of the present application;

[0035] Figure 8 FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0036] Hereinafter, the technical solutions in the present application will be clearly and elaborately described with reference to the accompanying drawings. Among them, in the description of the embodiments of the present application, unless otherwise specified, " / " means "or". For example, A / B may mean A or B. The "and / or" in the text is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B may mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality" means two or more than two.

[0037] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0038] Currently, a vehicle can automatically drive along the navigation route throughout the journey on a highway by means of an intelligent driving assistance system carried thereon. However, during the process of the vehicle using the intelligent driving assistance system to achieve automatic driving, the vehicle may encounter situations where the lane lines are not obvious or even there are no lane lines on the actual road, and there may also be situations where the camera recognition is poor in some sections. When the above situations occur, the vehicle can usually use the lane lines in the high-precision map to achieve autonomous driving. However, the lane lines in the high-precision map are not perfect, which may result in a poor intelligent driving experience.

[0039] Specifically, the existing high-precision map usually stores multiple road blocks obtained by breaking a complete road, and also stores the connection relationships between the lanes in each of the multiple road blocks. That is to say, the high-precision map contains multiple divided road blocks, rather than continuous lanes. And the intelligent driving system of the vehicle requires continuous lanes and continuous lane line information during the process of achieving automatic driving. If continuous lanes and continuous lane line information cannot be provided for the vehicle, it will cause the vehicle to be unable to achieve autonomous driving in some special road environments, resulting in poor intelligent driving stability.

[0040] To solve the above technical problems, an embodiment of the present application provides a method for outputting lane line points. The execution subject of this method can be an electronic device, specifically an electronic device in a vehicle, such as a controller.

[0041] Figure 1 It is a schematic flowchart of a method for outputting lane alignment points provided by an embodiment of the present application.

[0042] Exemplarily, as Figure 1 shown, the method 100 includes:

[0043] S101, obtaining map data of a high-precision map.

[0044] S102, based on the map data, restoring the lanes within a preset distance in front of the vehicle.

[0045] S103, outputting lane alignment point information according to the restored lanes.

[0046] Wherein, the restored lanes are continuous lanes, and the lane alignment point information is used to form continuous lane lines.

[0047] In the above method, first obtain the map data in the high-precision map, and then based on the map data, restore the lanes within a preset distance in front of the vehicle. Restoring the road within a preset distance in front based on the map data in the high-precision map can be used by the vehicle during the intelligent driving process, and can better ensure the stability of the intelligent driving process. According to the restored lanes, output lane alignment point information; wherein, the restored lanes are continuous and complete lanes, and the lane alignment point information is used to form continuous lane lines. By outputting the lane alignment point information for forming lane lines, the lane lines of the road ahead can be restored in data form, so that in the case of unclear or no lane lines during the vehicle's automatic driving process, the vehicle can still smoothly perform intelligent driving based on the continuous lane lines output based on the high-precision map, improving the stability of the intelligent driving process.

[0048] Next, a specific description will be given of the implementation manners of each step in the Figure 1 shown embodiment:

[0049] For the above S101, it can be understood that when the vehicle uses the intelligent driving assistance system to achieve automatic driving, if it encounters the situation of unclear or even no lane lines or the vehicle has poor camera recognition in some sections, in order to ensure the stability of intelligent driving, the vehicle can obtain the high-precision map and continue to use the intelligent driving assistance system to achieve automatic driving based on the high-precision map.

[0050] Specifically, a high-precision map is a high-precision map for autonomous driving. The high-precision map usually includes map elements such as road shapes, road markings, traffic signs, and obstacles, and the accuracy of the high-precision map can reach the centimeter level.

[0051] Furthermore, the map data of the above high-precision map can also be referred to as the original data of the high-precision map. This original data usually contains multiple road blocks divided based on a preset processing rule. The preset rule can usually be to divide the road into road blocks every 200 meters, and it can also be divided according to the current road structure. For example, when there are changes in the number of lanes on the current road, road grade (such as changing from a national road to a provincial road), and road lines (such as a solid line changing to a dashed line) on the current road, the current road is interrupted to form multiple road blocks. As Figure 2 shown, by dividing the original road form in the above figure according to the preset rule, the data storage format of the high-precision map in the following figure can be obtained.

[0052] It can be understood that the high-precision map not only stores multiple road blocks, but also stores the connection relationships between the individual lanes in these multiple road blocks. In addition, it also includes lane information and road information. Among them, lane information usually includes the number of lanes, lane types (such as ordinary lanes, acceleration lanes, emergency lanes, etc.), lane line patterns (such as white dashed lines, deceleration lines, double yellow lines, etc.), etc. Road information usually includes road grades such as highways, urban roads, branch roads, etc.

[0053] As can be seen from the above content, the high-precision map contains multiple divided road blocks, rather than continuous lanes. However, the intelligent driving system of the vehicle requires complete and continuous lane line information during the process of realizing automatic driving. Therefore, in the embodiments of the present application, it is necessary to restore the discontinuous lanes in the high-precision map to the complete and continuous lanes in the original road.

[0054] Regarding the above S102, it can be understood that the above map data can include multiple road blocks and the connection relationships between lanes. The above preset distance ahead can be set according to the actual situation and is usually set to 200 meters ahead.

[0055] Furthermore, after obtaining multiple road blocks and the connection relationships between lanes in the high-precision map, it is possible to restore the lanes within 200 meters ahead of the current position of the vehicle based on these multiple road blocks and the connection relationships between lanes.

[0056] In one possible implementation, the map data includes multiple road blocks and the connection relationships between lanes. Based on this map data, restoring the lanes within a preset distance ahead of the vehicle includes: determining the target road block where the vehicle is currently located among the multiple road blocks; determining the first target lane where the vehicle is located in the target road block; determining the target connection relationship between the first target lane and the lanes within the preset distance ahead of the vehicle according to the connection relationships between the lanes; and restoring the lanes within the preset distance ahead of the vehicle according to the target connection relationship.

[0057] Exemplarily, as Figure 3 shown, the current position of the vehicle is determined by the positioning module of the vehicle. Among multiple road blocks of the obtained high-precision map, the target road block X where the current position of the vehicle is located is determined. Then, the first target lane A where the vehicle is located is determined in the target road block X. Based on the obtained connection relationships between lanes, the target connection relationship A-B between the first target lane A and the lane B within a preset distance in front of the vehicle is determined (the first target lane A and the lane B have the connection relationship A-B). Finally, according to the target connection relationship A-B, the lanes within a preset distance in front of the current position are restored.

[0058] It can be understood that, as described above, when dividing multiple road blocks in the high-precision map, changes in the road structure of the current road will cause the current road to be interrupted, such as situations where the number of lanes decreases or increases, or there are no lane lines. When the number of lanes increases or decreases, there may be a situation where one lane has connection relationships with two lanes in front.

[0059] Based on this, it is necessary to select a set of connection relationships from the two sets of connection relationships between this lane and the two lanes in front, so that the front and rear lanes form a continuous lane.

[0060] In a possible implementation manner, determining the target connection relationship between the first target lane and the lanes within a preset distance in front of the current position according to the connection relationships between lanes includes: when there are multiple lanes within the preset distance that have connection relationships with the first target lane, determining the lanes that meet the preset conditions among the multiple lanes as the second target lanes connected to the first target lane; when there is a single lane within the preset distance that has a connection relationship with the first target lane, determining the single lane as the second target lane connected to the first target lane; and determining the connection relationship between the first target lane and the second target lane as the target connection relationship.

[0061] It can be understood that since the lane line information will greatly affect the automatic driving of the vehicle, the vehicle needs to drive along the lane lines as smooth as possible. When there is an increase in the number of lanes in front on the road, it is necessary to select the lanes that meet the preset conditions among the multiple lanes in front as the second target lanes connected to the first target lane. It should be understood that the lanes that meet the preset conditions can be the lanes that make the connected lanes smooth, or the lanes that conform to the navigation driving path.

[0062] When there is a decrease in the number of lanes in front on the road or the number of lanes remains unchanged, there will only be a set of connection relationships between the current first target lane and any one of the multiple lanes in front. Then, directly determine the lane with the connection relationship as the second target lane connected to the first target lane.

[0063] It should be understood that there are also different situations when the number of lanes ahead increases on the above-mentioned road. For example, in some cases, the total width of the lanes remains unchanged while the number of lanes increases, and in other cases, both the total width of the lanes and the number of lanes increase.

[0064] In one possible situation, as shown in Fig. 4(a), the multiple lanes A1 and A2 in front of the above-mentioned first target lane A are lanes whose total width increases compared with the first target lane and the number of lanes also increases.

[0065] It can be understood that in order to make the lane shape smoother after connecting the first target lane and the second target lane, it is preferable to select a lane that can be directly connected to the first target lane A as the second target lane.

[0066] In one possible implementation, determining the lane that meets the preset conditions among the multiple lanes as the second target lane connected to the first target lane includes: if the total width of the multiple lanes is greater than the lane width of the first target lane, then determining the lane that is connected to both the left and right lane lines of the first target lane among the multiple lanes as the second target lane.

[0067] It can be understood that, as described above, in order to make the lane shape smoother after connecting the first target lane and the second target lane, it is preferable to select a lane that can be directly connected to the first target lane as the second target lane, and the directly connected lane can be a lane where both the left and right lane lines can be directly connected.

[0068] Exemplarily, as shown in Fig. 4(a), the left and right lane lines of lane A1 can be connected to the left and right lane lines of the first target lane A, so lane A1 is selected as the second target lane.

[0069] In one possible situation, as shown in Fig. 4(b), the multiple lanes A1 and A2 in front of the above-mentioned first target lane A are lanes whose total width remains unchanged compared with the first target lane, but the number of lanes increases. In this case, the first target lane A can be called an extra-wide lane.

[0070] It can be understood that since the first target lane A is an extra-wide lane, there is no direct connection relationship between the multiple lanes A1 and A2 in front of the first target lane A and the first target lane A, that is, the right lane line of the first target lane A cannot be connected to the right lane line of lane A1, resulting in lane A1 not being directly connected to the first target lane A; the left lane line of the first target lane A cannot be connected to the left lane line of lane A2, resulting in lane A2 not being directly connected to the first target lane A. Based on this, the lane that is more in line with the navigation driving direction can be selected as the second target lane according to the navigation path information of the current vehicle.

[0071] In a possible implementation, determining the lanes that meet the preset conditions in the multiple lanes as the second target lanes connected to the first target lane includes: if the total lane width of the multiple lanes is equal to the lane width of the first target lane and the number of lanes increases, determining the lanes in the multiple lanes that are consistent with the navigation path direction of the vehicle as the second target lanes.

[0072] It can be understood that, as described above, according to the navigation path information of the current vehicle, the lanes that are more in line with the navigation driving direction are determined as the second target lanes. The navigation path information of the current vehicle is usually the direction of the path planned by the intelligent driving system when the vehicle is automatically driving currently.

[0073] Exemplarily, as shown in Figure 4(b), when the vehicle is automatically driving currently, the planned path is to drive through Lane A2, then Lane A2 is determined as the second target lane.

[0074] In another possible situation, as shown in Figure 4(c), on the current road, there is a situation where the number of lanes decreases, from two lanes to one lane, and the lane that was originally directly connected to Lane A disappears. Therefore, Lane A can be called the disappearing lane.

[0075] It can be understood that if there is only Lane B that has a connection relationship with Lane A, then Lane B can be directly determined as the second target lane.

[0076] In the above method, when there are multiple lanes that have a connection relationship with the first target lane, determining the lanes that meet the preset conditions as the second target lanes can restore the road to the original road form as much as possible based on the high-precision map, and ensure that the determined second target lanes are the lanes that are consistent with the vehicle driving direction, without the user taking over the vehicle for lane change, which can further improve the stability of intelligent driving and enhance the user experience.

[0077] It should be understood that after determining the above second target lanes, the connection relationship between the first target lane and the second target lane can be determined as the target connection relationship, and based on this target connection relationship, the lanes within a preset distance in front of the current position of the vehicle can be restored.

[0078] In a possible implementation, restoring the lanes within a preset distance in front of the current position according to the target connection relationship includes: connecting the first lane and the second lane according to the connection relationship between the first target lane and the second target lane to restore the lanes within a preset distance in front of the vehicle.

[0079] It can be understood that since the first target lane and the second target lane have a connection relationship, connecting the first target lane and the second target lane end to end can form a complete and continuous lane.

[0080] In a possible situation, as shown in Fig. 4(c), if the lane length after connecting lane A and lane B end to end is less than the above preset distance, lane B can be used as the first target lane, and the method for determining the second target lane described above can be continued to determine the second target lane connected to lane B and continue to form a complete lane until the total length after connecting these lanes can reach the above preset distance.

[0081] It should be understood that after obtaining the above restored lane, the lane lines actually become continuous and smooth lines. However, due to the appearance of special lanes such as those shown in Figs. 4(a), (b), and (c), the lane lines of some lanes may be interrupted, and the left and right lane lines may intersect, resulting in discontinuous situations. For the convenience of vehicle use, when obtaining lane line point information, the lane line point information corresponding to the interrupted lane line points may not be obtained, and only the lane line point information corresponding to the complete and continuous lane lines is retained.

[0082] In a possible implementation manner, outputting lane line point information according to the restored lane includes: obtaining the lane lines of the restored lane; where the restored lane includes the lane after connecting the first target lane and the second target lane, and the lane lines include the left line, the right line, and the center line; determining the second target lane line in the lane lines of the second target lane according to the lane lines of the restored lane; where the second target lane line is connected to the first target lane line in the first target lane, and the first target lane line and the second target lane line are lane lines in the same direction; outputting the lane line point information corresponding to the second target lane line and the lane line point information corresponding to all the lane lines of the first target lane.

[0083] It can be understood that the first target lane line and the second target lane line being lane lines in the same direction means that both the first target lane line and the second target lane line are the left line, or both are the right line, or both are the center line. That is to say, if the first target lane line is the left line on the first target lane, then the second target lane line is the left line on the second target lane. If the first target lane line is the right line on the first target lane, then the second target lane line is the right line on the second target lane. If the first target lane line is the center line on the first target lane, then the second target lane line is the center line on the second target lane.

[0084] It can be understood that after obtaining the above-restored lanes, the lane lines of the restored lanes can be traversed, mainly including the left and right boundary lines and the center line of the restored lanes. As mentioned above, due to the appearance of special lanes, the lane lines of some lanes may be interrupted or the left and right lane lines may intersect. Discontinuous lane lines may be inconvenient for vehicle use. Therefore, when traversing the lane lines of the restored lanes in the embodiments of the present application, generally, the lane line shape point information corresponding to the interrupted lane lines is not obtained, only the lane line shape point information corresponding to the continuous lane lines is obtained, and the lane line shape point information corresponding to the continuous lane lines is output.

[0085] In some embodiments, after obtaining the lane lines of the restored lanes, the lane lines are traversed in sequence, for example, in the order of the left boundary line - the center line - the right boundary line. When traversing the left boundary line of the first target lane and the left boundary line of the second target lane, if it is determined that the left boundary line of the second target lane cannot be connected to the left boundary line of the first target lane, the traversal is stopped, and the lane line shape point information corresponding to the left boundary line of the second target lane is no longer obtained; if the right boundary line of the second target lane is connected to the right boundary line of the first target lane, and the center line of the second target lane is connected to the center line of the first target lane, the lane line shape point information corresponding to the right boundary line and the center line of the second lane and the lane line shape point information of all lane lines of the first target lane are output.

[0086] When traversing the center line of the first target lane and the center line of the second target lane, if it is determined that the center line of the second target lane cannot be connected to the center line of the first target lane, the traversal is stopped, and the lane line shape point information corresponding to the center line of the second target lane is no longer obtained; if the right boundary line of the second target lane is connected to the right boundary line of the first target lane, and the left boundary line of the second target lane is connected to the left boundary line of the first target lane, the lane line shape point information corresponding to the right boundary line and the left boundary line of the second lane and the lane line shape point information of all lane lines of the first target lane are output.

[0087] When traversing the right boundary line of the first target lane and the right boundary line of the second target lane, if it is determined that the right boundary line of the second target lane cannot be connected to the right boundary line of the first target lane, the traversal is stopped, and the lane line shape point information corresponding to the right boundary line of the second target lane is no longer obtained; if the left boundary line of the second target lane is connected to the left boundary line of the first target lane, and the center line of the second target lane is connected to the center line of the first target lane, the lane line shape point information corresponding to the left boundary line and the center line of the second lane and the lane line shape point information of all lane lines of the first target lane are output.

[0088] Exemplarily, as shown in Fig. 5(a), the left and right side lines and the center line of lanes A, B, and C in the figure can all be connected. Therefore, the lane lines formed after connecting the left and right side lines and the center line of lanes A, B, and C are all continuous, and then the linear point information of the left and right side lines and the center line of lanes A, B, and C can be obtained.

[0089] As shown in Fig. 5(b), assume that the vehicle is driving in lane A. Lane A in the figure is the disappearing lane mentioned above. The left side line a1 and the right side line a3 of lane A coincide when connecting with the right side line b3 of lane B, resulting in the disconnection between the left side line a1 of lane A and the left side line b1 of lane B, that is, the line that should originally be connected to a1 is interrupted. Therefore, the linear point information corresponding to the left side line b1 of lane B is no longer obtained. However, the center line a2 and the right side line a3 of lane A can both be connected to the center line b2 and the right side line b3 of lane B, so the linear point information corresponding to the center line b2 and the right side line b3 of lane B can be obtained.

[0090] It can be understood that after the vehicle changes lanes from lane A to lane C, since the left side line, the right side line, and the center line of lane C can be connected to the left side line, the right side line, and the center line of lane B, at this time, the lane linear point information corresponding to the left side line, the right side line, and the center line of lanes B and C can be obtained.

[0091] As shown in Fig. 5(c), assume that the vehicle is driving in the center of lane A. Lane A in the figure is the extra-wide lane mentioned above. The left and right side lines of lane A are respectively connected to two different lanes, that is, the left side line a1 of lane A is connected to the left side line b1 of lane B, and the right side line a3 of lane A is connected to the right side line c3 of lane C. In order for the vehicle to successfully drive along the navigation path, the vehicle needs to drive into lane B. Therefore, the lane linear point information corresponding to the non-navigation path lane, that is, lane C, is no longer obtained. And the right side line a3 of lane A cannot be connected to the right side line b3 of lane B, and the lane linear point information corresponding to the right side line b3 of lane b is no longer obtained either. Only the lane linear point information corresponding to the left side line b1 and the center line b2 of lane B is obtained.

[0092] It can be understood that when the vehicle drives from lane A to lane B, the lane linear point information corresponding to the right side line b3 of lane B can be obtained.

[0093] Further, after obtaining the continuous lane linear point information in the above-restored lanes, the continuous lane linear point information is output for use by the vehicle terminal.

[0094] In a possible implementation, after outputting the lane alignment point information according to the restored lane, the method further includes: based on the lane alignment point information corresponding to the continuous lane lines in the output lane, fitting the continuous lane alignment points to construct continuous lane lines.

[0095] It can be understood that the vehicle end cannot directly use the lane alignment point information corresponding to the above-mentioned continuous lane lines output. It is also necessary to fit these continuous lane alignment points to obtain continuous lane lines before they can be used by the vehicle end.

[0096] Exemplarily, the above-mentioned fitting of continuous lane alignment points can be performed by fitting methods such as the least squares method, kernel method, spline method, and maximum likelihood estimation method.

[0097] In some embodiments, a driving reference line for the vehicle can be generated based on the continuous lane lines for the intelligent driving system of the vehicle to achieve autonomous driving based on the driving reference line.

[0098] The above method only outputs the lane alignment point information corresponding to the continuous lane lines, and constructs continuous lane lines based on the lane alignment point information corresponding to the continuous lane lines, so that the vehicle end can generate a driving reference line based on the continuous lane lines and successfully complete the intelligent driving task based on the driving reference line, improving the reliability of intelligent driving.

[0099] Figure 6 It is a schematic flowchart of another method for outputting lane alignment points provided by an embodiment of the present application.

[0100] Exemplarily, as Figure 6 shown, the method 600 includes:

[0101] S601, obtaining the original data of the high-precision map.

[0102] It can be understood that the above-mentioned original data can be understood as the map data in the previous text.

[0103] S602, determining the road block and the lane where the current position is located according to the positioning information of the vehicle.

[0104] It can be understood that based on the above-mentioned original data, the road block where the current position is located in the high-precision map, that is, the target road block in the previous text, and the lane where the vehicle is located, that is, the first target lane in the previous text, are determined according to the positioning information of the vehicle.

[0105] S603, restoring the complete lane form in front of the current position according to the connection relationship between lanes.

[0106] It can be understood that the above-mentioned connection relationship between lanes is stored in the original data, and the restored lane form is complete and continuous.

[0107] S604. Traverse the lane alignment point information of all lanes in the restored complete lane strip.

[0108] It can be understood that, as described above, first obtain the lane lines of the restored lanes, and then traverse the lane alignment point information corresponding to the lane lines.

[0109] S605. During the traversal, if the condition for stopping the traversal is detected, the traversal stops.

[0110] It can be understood that, as described above, traverse in the order of left lane line - center line - right lane line. For example, when traversing the left lane lines of the first target lane and the second target lane, if it is determined that the left lane line of the second target lane cannot be connected to the left lane line of the first target lane, it is determined that the condition for stopping the traversal is detected, and thus the traversal stops. After completing the traversal of the left lane line - center line - right lane line, it can also be determined that the condition for stopping the traversal is detected, and thus the traversal stops.

[0111] S606. Determine whether the traversal is over.

[0112] It can be understood that if the reason for stopping the traversal is to complete the traversal of the left lane line - center line - right lane line, that is, the traversal has been completed in the above traversal order, it is determined that the traversal is over.

[0113] Exemplarily, if the traversal is not over, execute S606; if the traversal is over, execute S608.

[0114] S607. Determine whether the currently traversed lane is an extra-wide lane or a disappearing lane.

[0115] It can be understood that there are interrupted lane alignment points in the above-mentioned extra-wide lanes and disappearing lanes. When traversing to the interrupted lane alignment points, the traversal cannot be completed, that is, the traversal stops.

[0116] Exemplarily, if the lane is an extra-wide lane or a disappearing lane, execute S608; if the lane is not an extra-wide lane or a disappearing lane, continue the traversal, that is, execute S604.

[0117] S608. Stop obtaining the lane alignment point information corresponding to the interrupted lane line.

[0118] It can be understood that if the lane is a disappearing lane or an extra-wide lane, it means that there is an interrupted lane line, that is, the left lane line, the right lane line, and the center line mentioned above. When encountering the interrupted lane line, stop obtaining the lane alignment point information corresponding to the lane line, and then continue to traverse the lane alignment point information corresponding to other continuous lane lines.

[0119] S609 outputs complete and continuous lane line point information.

[0120] It can be understood that after determining that all the lane lines of the restored lanes have been traversed, the lane line point information corresponding to the continuous lane lines in the lane is output. For example, the lane line point information corresponding to the second target lane line and the lane line point information corresponding to all the lane lines of the first target lane are output.

[0121] Figure 7 It is a schematic structural diagram of a lane line point output device provided by an embodiment of the present application.

[0122] Exemplarily, as Figure 7 shown, the device 700 includes:

[0123] An acquisition module 701, configured to acquire map data of a high-precision map.

[0124] A restoration module 702, configured to restore the lanes within a preset distance in front of the vehicle based on the map data.

[0125] An output module 703, configured to output lane line point information according to the restored lane; wherein, the restored lane is a continuous lane, and the lane line point information is used to form continuous lane lines.

[0126] In a possible implementation manner, the map data includes a plurality of road blocks and the connection relationships between lanes. The restoration module is specifically configured to: in the plurality of road blocks, determine the target road block where the vehicle is currently located; determine the first target lane where the vehicle is located in the target road block; according to the connection relationships between lanes, determine the target connection relationship between the first target lane and the lanes within a preset distance in front of the vehicle; and restore the lanes within a preset distance in front of the vehicle according to the target connection relationship.

[0127] In a possible implementation manner, the restoration module further includes a first determination unit, and the first determination unit is specifically configured to: when there are multiple lanes within the preset distance in front that have a connection relationship with the first target lane, determine the lanes that meet the preset conditions among the multiple lanes as the second target lanes connected to the first target lane; when there is a single lane within the preset distance in front that has a connection relationship with the first target lane, determine the single lane as the second target lane connected to the first target lane; and determine the connection relationship between the first target lane and the second target lane as the target connection relationship.

[0128] In a possible implementation, the first determination unit is further specifically configured to: if the total lane width of the multiple lanes is greater than the lane width of the first target lane, determine the lane that is connected to both the left and right lane lines of the first target lane among the multiple lanes as the second target lane; or; if the total lane width of the multiple lanes is equal to the lane width of the first target lane, determine the lane that is consistent with the navigation path direction of the vehicle among the multiple lanes as the second target lane.

[0129] In a possible implementation, the restoration module is specifically configured to: connect the first target lane and the second target lane according to the connection relationship between the first target lane and the second target lane, so as to restore the lanes within a preset distance in front of the vehicle.

[0130] In a possible implementation, the output module is specifically configured to: obtain the lane lines of the restored lane; wherein, the restored lane includes the lane after the connection of the first target lane and the second target lane, and the lane lines include the left line, the right line, and the center line; determine the second target lane line in the lane lines of the second target lane according to the lane lines of the restored lane; wherein, the second target lane line is connected to the first target lane line in the first target lane, and the first target lane line and the second target lane line are lane lines in the same direction; output the lane line form point information corresponding to the second target lane line and the lane line form point information corresponding to all the lane lines of the first target lane.

[0131] Optionally, the device further includes a fitting module, and the fitting module is specifically configured to: based on the lane line form point information corresponding to the continuous lane lines in the output lane, fit the continuous lane line form points to construct continuous lane lines.

[0132] Figure 8 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0133] Exemplarily, as Figure 8 shown, the electronic device 800 includes: a memory 801 and a processor 802. Among them, an executable program code 8011 is stored in the memory 801, and the processor 802 is used to call and execute the executable program code 8011 to execute a method for outputting lane line form points.

[0134] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor. Among them, an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to execute a method for outputting lane line form points provided by an embodiment of the present application.

[0135] In this embodiment, the device can be divided into functional modules according to the above method examples. For example, each functional module can be corresponding, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0136] In the case of dividing each functional module corresponding to each function, the device can also include an acquisition module, a reduction module, an output module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be cited in the function description of the corresponding functional module, and will not be repeated here.

[0137] It should be understood that the device provided in this embodiment is used to execute the above method for outputting lane alignment points, so the same effect as the above implementation method can be achieved.

[0138] In the case of using an integrated unit, the device can include a processing module and a storage module. Among them, when the device is applied to a vehicle, the processing module can be used to control and manage the actions of the vehicle. The storage module can be used to support the vehicle to execute mutual program codes, etc.

[0139] Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the disclosure of this application. The processor can also be a combination that realizes computing functions, such as including a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0140] In addition, the device provided in the embodiment of this application can specifically be a chip, a component, or a module. The chip can include a connected processor and a memory; among them, the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the method for outputting lane alignment points provided in the above embodiment.

[0141] This embodiment also provides a computer-readable storage medium, in which computer program code is stored. When the computer program code runs on a computer, the computer is caused to execute the above relevant method steps to implement the method for outputting lane alignment points provided in the above embodiment.

[0142] This embodiment also provides a computer program product. When the computer program product runs on a computer, the computer is caused to execute the above relevant steps to implement the method for outputting lane alignment points provided in the above embodiment.

[0143] Among them, the device, computer-readable storage medium, computer program product, or chip provided in this embodiment are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be elaborated here.

[0144] From the description of the above embodiments, those skilled in the art can understand that for the convenience and brevity of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0145] In the embodiments provided in this application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0146] The above content is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A method for outputting lane alignment points, characterized in that, The method includes: Obtaining map data of a high-precision map; Restoring the lanes within a preset distance in front of the vehicle based on the map data; Outputting lane linear point information according to the restored lanes; wherein, the restored lanes are continuous lanes, and the lane linear point information is used to form continuous lane lines.

2. The method according to claim 1, characterized in that, The map data includes multiple road blocks and the connection relationships between lanes. The restoring of the lanes within a preset distance in front of the vehicle based on the map data includes: Determining the target road block where the vehicle is currently located among the multiple road blocks; Determining the first target lane where the vehicle is located in the target road block; Determining the target connection relationship between the first target lane and the lanes within a preset distance in front of the vehicle according to the connection relationships between the lanes; Restoring the lanes within a preset distance in front of the vehicle according to the target connection relationship.

3. The method according to claim 2, characterized in that, The determining of the target connection relationship between the first target lane and the lanes within a preset distance in front of the vehicle according to the connection relationships between the lanes includes: When there are multiple lanes within the preset distance in front that have connection relationships with the first target lane, determining the lanes that meet the preset conditions among the multiple lanes as the second target lanes connected to the first target lane; When there is a single lane within the preset distance in front that has a connection relationship with the first target lane, determining the single lane as the second target lane connected to the first target lane; Determining the connection relationship between the first target lane and the second target lane as the target connection relationship.

4. The method according to claim 3, characterized in that, The determining of the lanes that meet the preset conditions among the multiple lanes as the second target lanes connected to the first target lane includes: If the total lane width of the multiple lanes is greater than the lane width of the first target lane, determining the lane that is connected to both the left and right lane lines of the first target lane among the multiple lanes as the second target lane; Or; If the total lane width of the multiple lanes is equal to the lane width of the first target lane, determining the lane that is in the same direction as the navigation path of the vehicle among the multiple lanes as the second target lane.

5. The method according to claim 3, wherein The restoring of the lanes within a preset distance in front of the vehicle according to the target connection relationship includes: Connecting the first target lane and the second target lane according to the connection relationship between the first target lane and the second target lane to restore the lanes within a preset distance in front of the vehicle.

6. The method according to claim 5, characterized in that, The outputting of lane linear point information according to the restored lanes includes: Obtaining the lane lines of the restored lanes; wherein, the restored lanes include the lanes after the connection of the first target lane and the second target lane, and the lane lines include the left lane line, the right lane line, and the center line; Determining a second target lane line in the lane lines of the second target lane according to the lane lines of the restored lanes; wherein, the second target lane line is connected to the first target lane line in the first target lane, and the first target lane line and the second target lane line are lane lines in the same direction; Output the lane line shape point information corresponding to the second target lane line and the lane line shape point information corresponding to all lane lines of the first target lane.

7. The method according to claim 1, characterized in that, After outputting the lane line shape point information according to the restored lane, the method further includes: Based on the lane line shape point information corresponding to the continuous lane lines in the output lane, fitting the continuous lane line shape points to construct continuous lane lines.

8. An output device for lane alignment points, characterized in that, The device includes: An acquisition module, configured to acquire map data of a high-precision map; A restoration module, configured to restore the lane within a preset distance in front of the vehicle based on the map data; An output module, configured to output lane line shape point information according to the restored lane; wherein, the restored lane is a continuous lane, and the lane line shape point information is used to form continuous lane lines.

9. An electronic device, characterized in that, The electronic device includes: A memory, configured to store executable program code; A processor, configured to call and run the executable program code from the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed, implements the method according to any one of claims 1 to 7.