Method, apparatus, and electronic map for generating virtual guiding lines

By obtaining the vehicle driving route when there are no obstacles in the road surface area covered by the intersection, determining the evacuation route with reference lines and generating virtual guide lines, the problem of low reliability of virtual guide lines is solved, and high accuracy intelligent and automated virtual guide lines are achieved.

CN114880419BActive Publication Date: 2025-06-13AUTONAVI SOFTWARE CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202210689474.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-16
Publication Date
2025-06-13
Estimated Expiration
2042-06-16

AI Technical Summary

Technical Problem

In the prior art, the reliability of virtual guide lines is relatively low, especially when there is no lane line in the road surface area, it is difficult to accurately generate virtual guide lines to guide the driving of intelligent driving vehicles.

Method used

By obtaining the vehicle driving route (reference line) assuming there are no obstacles in the road surface area covered by the intersection, the evacuation route to avoid obstacles is determined in combination with the reference line, and a virtual guide line is generated based on the evacuation route.

Benefits of technology

The accuracy and effectiveness of virtual guide lines are improved, and the intelligence and automation of virtual guide lines are realized, avoiding the disadvantage of low accuracy caused by manual determination of virtual guide lines.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114880419B_ABST
    Figure CN114880419B_ABST
Patent Text Reader

Abstract

The present disclosure provides a method, an apparatus and an electronic map for generating a virtual guiding line, including: obtaining a reference line of an intersection pre-generated, wherein the reference line is generated based on a set driving direction in a road surface area covered by the intersection and does not avoid obstacles located in the road surface area; determining an avoidance route for avoiding the obstacles according to the reference line, wherein the distance from the avoidance route to the reference line is less than a set distance threshold; and generating a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route and the obstacles, which avoids the disadvantage of low accuracy caused by determining the virtual guiding line in an artificial manner, realizes the intelligence and automation of determining the virtual guiding line, and improves the accuracy and effectiveness of the determined virtual guiding line.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of high-precision maps, and in particular, to a method and apparatus for generating virtual guiding lines and an electronic map. Background Art

[0002] An electronic map is a digital representation of the real world. Most roads in the real world have lane lines drawn on the road surface for vehicles to drive along the lanes in a standardized manner. Therefore, when making a high-precision electronic map, the lane lines on the road surface can be made based on the collected road data.

[0003] However, the inventor of the present disclosure has found that there are usually no lane lines in the road surface area of roads in the real world. Since the high-precision electronic map mainly serves for intelligent driving vehicles to make driving decisions, in order for the decision-making system of intelligent driving vehicles to make corresponding driving decision instructions based on the high-precision electronic map, it is necessary to generate virtual guiding lines for the road surface area of the road. The virtual guiding line is also called an intersection virtual line.

[0004] In some embodiments, the virtual guiding line can be determined based on an artificial method. Summary of the Invention

[0005] The present disclosure provides a method and apparatus for generating virtual guiding lines and an electronic map to solve the problem of relatively low reliability of virtual guiding lines.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for generating a virtual guiding line, including:

[0007] Obtain a reference line of a pre-generated intersection, where the reference line is generated based on a set driving direction in a road surface area covered by the intersection and does not avoid obstacles located in the road surface area;

[0008] Determine an avoidance route that avoids the obstacle according to the reference line, where the distance from the avoidance route to the reference line is less than a set distance threshold;

[0009] Generate a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route, and the obstacle.

[0010] In an embodiment of the present disclosure, the generating a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route, and the obstacle includes:

[0011] Determine an intersection point between the avoidance route and the obstacle;

[0012] Taking the reference line as a reference and the intersection point as an avoidance point, generate an offset line with a smooth curvature;

[0013] Determine the virtual guiding line according to the offset line.

[0014] In an embodiment of the present disclosure, the reference line for generating the offset line is the road center line of the pre-generated road surface area;

[0015] The determining the virtual guiding line according to the offset line includes:

[0016] Generate virtual lane lines with the offset line as the virtual center line;

[0017] Determine the virtual lane lines as the virtual guiding line.

[0018] In an embodiment of the present disclosure, the generating virtual lane lines with the offset line as the virtual center line includes:

[0019] Obtain the entry width of the entry road surface of the road surface area;

[0020] Obtain the exit width of the exit road surface of the road surface area;

[0021] Perform sampling processing on the virtual center line according to the entry width and the exit width to obtain the virtual lane lines.

[0022] In an embodiment of the present disclosure, the performing sampling processing on the virtual center line according to the entry width and the exit width to obtain the virtual lane lines includes:

[0023] Sample the sampling points on the virtual center line according to a preset fixed interval;

[0024] Obtain the perpendicular lines passing through the sampling points and perpendicular to the virtual center line;

[0025] Generate the virtual lane lines according to the entry width, the exit width, the sampling points, and the perpendicular lines.

[0026] In an embodiment of the present disclosure, the generating the virtual lane lines according to the entry width, the exit width, the sampling points, and the perpendicular lines includes:

[0027] Calculate the width difference between the entry width and the exit width;

[0028] According to the number of sampling points and the width difference, respectively determine a side line point on the perpendicular lines on both sides of the virtual center line where the sampling points are located;

[0029] Generate the virtual lane line on one side according to the side line points on the same side of the virtual center line.

[0030] In one embodiment of the present disclosure, determining an avoidance route to avoid the obstacle according to the reference line includes:

[0031] Taking half of the preset vehicle driving width as the expansion benchmark, performing an expansion process on the obstacle to obtain an expanded obstacle;

[0032] Determining the avoidance route according to the expanded obstacle and the reference line.

[0033] In one embodiment of the present disclosure, the method further includes:

[0034] Constructing a grid topology map of the intersection, where the grid topology map includes obstacle grids and non-obstacle grids;

[0035] Generating the reference line according to the grid topology map;

[0036] And, determining an avoidance route to avoid the obstacle according to the reference line, including:

[0037] Determining an avoidance route to avoid the obstacle according to the reference line and the grid topology map.

[0038] In a second aspect, an embodiment of the present disclosure provides a virtual guiding line generation device, including:

[0039] An acquisition unit, configured to acquire a reference line of a pre-generated intersection, where the reference line is generated based on a set driving direction in a road surface area covered by the intersection and does not avoid obstacles located in the road surface area;

[0040] A determination unit, configured to determine an avoidance route to avoid the obstacle according to the reference line, where the distance from the avoidance route to the reference line is less than a set distance threshold;

[0041] A first generation unit, configured to generate a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route, and the obstacle.

[0042] In one embodiment of the present disclosure, the first generation unit includes:

[0043] A first determination subunit, configured to determine an intersection point between the avoidance route and the obstacle;

[0044] A generation subunit, configured to generate an offset line with smooth curvature with the reference line as the benchmark and the intersection point as the avoidance point;

[0045] A second determination subunit, configured to determine the virtual guiding line according to the offset line.

[0046] In one embodiment of the present disclosure, the reference line for generating the offset line is the center line of the road surface of the pre-generated road surface area;

[0047] The second determination sub-unit includes:

[0048] A generation module, configured to generate a virtual lane line with the offset line as the virtual center line;

[0049] A determination module, configured to determine the virtual lane line as the virtual guiding line.

[0050] In one embodiment of the present disclosure, the generation module includes:

[0051] A first acquisition sub-module, configured to acquire the entry width of the entry road surface of the road surface area;

[0052] A second acquisition sub-module, configured to acquire the exit width of the exit road surface of the road surface area;

[0053] A sampling sub-module, configured to perform sampling processing on the virtual center line according to the entry width and the exit width to obtain the virtual lane line.

[0054] In one embodiment of the present disclosure, the sampling sub-module is configured to sample the sampling points on the virtual center line according to a preset fixed interval, obtain the perpendicular lines passing through the sampling points and perpendicular to the virtual center line, and generate the virtual lane line according to the entry width, the exit width, the sampling points, and the perpendicular lines.

[0055] In one embodiment of the present disclosure, the sampling sub-module is configured to calculate the width difference between the entry width and the exit width, determine a side line point on each of the perpendicular lines on both sides of the virtual center line according to the number of sampling points and the width difference, and generate the virtual lane line on that side according to the side line points on the same side of the virtual center line.

[0056] In one embodiment of the present disclosure, the determination unit includes:

[0057] An expansion sub-unit, configured to perform expansion processing on the obstacle with half of the preset vehicle driving width as the expansion reference to obtain an expanded obstacle;

[0058] A third determination sub-unit, configured to determine the avoidance route according to the expanded obstacle and the reference line.

[0059] In one embodiment of the present disclosure, the device further includes:

[0060] A building unit for building a grid topology map of the intersection, where the grid topology map includes obstacle grids and non-obstacle grids;

[0061] A second generation unit for generating the reference line according to the grid topology map;

[0062] And, the determination unit is configured to determine an avoidance route that avoids the obstacle according to the reference line and the grid topology map.

[0063] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0064] At least one processor; and

[0065] A memory communicatively connected to at least one processor; wherein,

[0066] The memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor so that the electronic device can execute the method described in any one of the first aspects of the present disclosure.

[0067] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the first aspects of the present disclosure is implemented.

[0068] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects of the present disclosure is implemented.

[0069] In a sixth aspect, an embodiment of the present disclosure provides an electronic map, the electronic map records intersection elements, the intersection elements include obstacles and virtual guiding lines, the virtual guiding lines are used to guide vehicles through the intersection area, and the virtual guiding lines are generated based on the method described in any one of the first aspects of the present disclosure.

[0070] The method, device and electronic map for generating a virtual guiding line provided by the embodiments of the present disclosure obtain a reference line for a vehicle to travel on the road surface area covered by assuming that there are no obstacles in the road surface area in the set driving direction at the intersection, so as to determine an avoidance route that avoids obstacles in combination with the reference line, and generate a virtual guiding line for guiding the vehicle to avoid obstacles based on the avoidance route. The technical features avoid the disadvantages of low accuracy caused by determining the virtual guiding line based on manual methods, realize the intelligence and automation of determining the virtual guiding line, and improve the accuracy and effectiveness of the determined virtual guiding line. Description of the Drawings

[0071] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0072] Figure 1 Flowchart of the method for generating a virtual guiding line according to an embodiment of the present disclosure;

[0073] Figure 2 Flowchart of the method for generating a virtual guiding line according to another embodiment of the present disclosure;

[0074] Figure 3 Schematic diagram of the principle for determining the offset line according to an embodiment of the present disclosure;

[0075] Figure 4 Schematic diagram of the principle for generating a virtual guiding line according to an embodiment of the present disclosure;

[0076] Figure 5 Schematic diagram of the device for generating a virtual guiding line according to an embodiment of the present disclosure;

[0077] Figure 6 Schematic diagram of the device for generating a virtual guiding line according to another embodiment of the present disclosure;

[0078] Figure 7 Schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present disclosure.

[0079] Through the above accompanying drawings, the clear embodiments of the present disclosure have been shown, and there will be more detailed descriptions hereinafter. These accompanying drawings and the textual descriptions are not intended to limit the scope of the concept of the present disclosure in any way, but to illustrate the concept of the present disclosure to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0080] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts fall within the scope of protection of the present disclosure.

[0081] The terms "first", "second", "third", etc. in the description, claims and the above-mentioned drawings of the present disclosure are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein.

[0082] In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0083] For the convenience of understanding the embodiments of the present disclosure, at least some of the terms related to the present disclosure are explained as follows:

[0084] An electronic map refers to a map with a computer screen and a projection large screen as the display medium.

[0085] An electronic map includes a general map and a high-precision map. A high-precision map, also known as a high-accuracy map or a high-standard map, refers to an electronic map serving an autonomous driving system as opposed to a general map serving navigation. Therefore, a high-precision map can also be called an autonomous driving map and a high-resolution map, which is a new map data paradigm for autonomous driving vehicles.

[0086] A lane is a road area for vehicles to travel in a specific driving direction, and a lane can be defined by left and right boundaries.

[0087] A lane line is an element in a high-precision map used to represent a lane and is vector data made through established operation rules. Among them, the lane lines in a high-precision map can be the center line of the lane (which refers to the center line of the lane) or the edge line of the lane (which refers to the boundary line of the lane).

[0088] An intersection refers to an area where roads converge, such as an intersection or a T-junction, etc.

[0089] A virtual guiding line is also called a virtual driving line for the road area covered by an intersection (which can be simply called an intersection virtual line). Since most of the road areas covered by intersections in the real world do not currently draw lane lines to regulate the driving area of vehicles passing through the intersection, but the driver selects the driving area according to the intersection traffic conditions and traffic needs. However, for the autonomous driving scenario, the autonomous driving decision-making system needs to make driving decisions based on the elements provided by the high-precision map. In order to enable autonomous driving vehicles to know how to drive, therefore, it is necessary to generate virtual lane lines to guide vehicle passage. In some embodiments, the virtual guiding line can be determined based on an artificial method.

[0090] Exemplarily, a staff member may generate a virtual guiding line according to the driving habits of a human driver, so that when an autonomous vehicle and a human-driven vehicle turn simultaneously in the road surface area covered by an intersection, they will not conflict with each other, such as traffic events like collisions will not occur.

[0091] However, there may be many obstacles affecting driving safety in the road surface area covered by an intersection, such as green belts, pedestrian safety islands, traffic kiosks, signal lights, and diversion belts, etc. This requires the staff member to avoid these when generating the virtual guiding line.

[0092] However, when the staff member avoids the obstacles affecting driving safety, it is easily affected by human subjective factors, resulting in the problem of low reliability of the virtual guiding line.

[0093] In some other embodiments, it is also possible to obtain the historical driving trajectories of the road surface area covered by an intersection and generate a virtual guiding line that conforms to the kinematic characteristics of actual vehicle driving according to the historical driving trajectories. Among them, the historical driving trajectory refers to the driving trajectory of a vehicle traveling in the road surface area covered by an intersection during a past period.

[0094] However, when generating a virtual guiding line in this way, in order to make the virtual guiding line relatively accurately conform to the kinematic characteristics of actual vehicle driving, a large number of historical driving trajectories need to be collected, and the accuracy of the historical driving trajectories is relatively required to be high, then the corresponding cost will be relatively high, and when the amount of historical driving trajectories is relatively large, the analysis resources are also consumed relatively high.

[0095] To avoid at least one of the above problems, the inventors of the present disclosure have obtained the inventive concept of the present disclosure through creative labor: obtain the driving route (which can be called a reference line) of a vehicle traveling on the road surface area based on a set driving direction assuming there are no obstacles in the road surface area covered by an intersection, and determine a line relatively close to the reference line to avoid obstacles (which can be called an avoidance route), so as to generate a virtual guiding line according to the avoidance route.

[0096] Next, the technical solutions of the present disclosure will be described in detail through specific embodiments. It should be noted that the following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0097] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for generating a virtual guiding line according to an embodiment of the present disclosure. As Figure 1 shown, the method includes:

[0098] S101: Obtain a reference line of a pre-generated intersection. The reference line is generated based on the road surface area covered by the intersection in the set driving direction and does not avoid obstacles located in the road surface area.

[0099] Exemplarily, the execution subject of the embodiment of the present disclosure is a virtual guiding line generation device (hereinafter simply referred to as the generation device). The generation device can be a server (such as a cloud server, or a local server, or a server cluster), or a computer, or a terminal device, or a processor, or a chip, etc., which will not be listed one by one here.

[0100] There are obstacles in the road surface area covered by the set driving direction at the intersection. This step can be understood as: assuming there are no obstacles in this road surface area, the vehicle can form a driving route when driving in this road surface area based on the set driving direction, and this driving route is the reference line. In this embodiment, the set driving direction is not limited. For example, it can be turning left along the road surface area, or turning right along the road surface area.

[0101] There are two possibilities for the reference line. One possibility is that the reference line is a reference line of the road surface boundary line of the road surface area covered by the set driving direction at the intersection. For example, if this road surface area is defined based on two virtual boundary lines, the reference line can be determined based on these two virtual boundary lines. Exemplarily, this road surface area is the road area of a lane. Therefore, the road surface boundary line can be the lane boundary line, that is, the reference line can be the reference line of the lane boundary line, and this reference line can be understood as the line for reference as the lane boundary line.

[0102] Another possibility is that the reference line is a reference line of the road surface center line of the road surface area covered by the set driving direction at the intersection. Combining the above example, this road surface area can be defined based on two virtual boundary lines. The road surface center line can be understood as the virtual line at the center of the two virtual boundary lines, that is, the reference line can be the reference line of the center line of this road surface area. Exemplarily, this road surface area is the road area of a lane. Correspondingly, this road surface center line is the center line of this lane, that is, the reference line can be understood as the line for reference as the lane center line.

[0103] In this embodiment, the method for obtaining the reference line is not limited. For example, it can be obtained based on experiments, or based on algorithms, etc., which will not be listed one by one here.

[0104] Taking the method of obtaining the reference line based on an algorithm as an example, the Bezier curve (also known as the B-spline curve) algorithm can be used to calculate the reference line. Of course, other algorithms can also be used to calculate the reference line, which is not limited in this embodiment.

[0105] S102: Determine an avoidance route that avoids obstacles based on a reference line. Here, the distance from the avoidance route to the reference line is less than a set distance threshold.

[0106] Here, the distance threshold can be determined based on requirements, historical records, experiments, etc., and is not limited in this embodiment.

[0107] Exemplarily, the avoidance route can be understood as a line that can avoid obstacles and is relatively close to the reference line.

[0108] In some embodiments, the avoidance route is the line closest to the reference line. That is, the avoidance route can be a line that can both avoid obstacles and is the closest to the reference line.

[0109] S103: Generate a virtual guidance line corresponding to the set driving direction based on the reference line, the avoidance route, and the obstacles.

[0110] Exemplarily, if the set driving direction is to turn left along the road surface area covered by the intersection, a virtual guidance line can be generated based on the reference line, the avoidance route, and the obstacles, and this virtual guidance line can guide the vehicle to complete the driving operation of turning left in this road surface area, and the vehicle can avoid the obstacles in this road surface area during driving, so as to improve the safety and reliability of vehicle driving.

[0111] Based on the above analysis, it can be known that the embodiments of the present disclosure provide a method for generating a virtual guidance line, including: obtaining a pre-generated reference line of an intersection, where the reference line is generated based on the set driving direction in the road surface area covered by the intersection and does not avoid the obstacles located in this road surface area, determining an avoidance route that avoids obstacles based on the reference line, where the distance from the avoidance route to the reference line is less than a set distance threshold, and generating a virtual guidance line corresponding to the set driving direction based on the reference line, the avoidance route, and the obstacles. In this embodiment, by obtaining the reference line of the vehicle driving in the road surface area of the intersection assuming there are no obstacles, combining the reference line to determine an avoidance route that avoids obstacles, and generating a virtual guidance line for guiding the vehicle to avoid obstacles during driving, the drawback of low accuracy caused by determining the virtual guidance line based on manual methods is avoided, the intelligence and automation of determining the virtual guidance line are realized, and the accuracy and effectiveness of the determined virtual guidance line are improved.

[0112] To enable readers to more deeply understand the implementation principle of the present disclosure, the present disclosure will now be described in more detail in combination with Figure 2 the present disclosure. Among them, Figure 2 is a flowchart of a method for generating a virtual guidance line according to another embodiment of the present disclosure. As Figure 2 shown, this method includes:

[0113] S201: Use the B-spline curve algorithm to obtain the reference line of a pre-generated intersection. Among them, the reference line is generated based on the road surface area covered by the intersection in the set driving direction and does not avoid obstacles located in the road surface area.

[0114] It should be understood that, in order to avoid cumbersome statements, for the same technical features in this embodiment and the above embodiments, this embodiment will not be described in detail.

[0115] Exemplarily, the road surface where the vehicle enters the road surface area covered by the intersection based on the set driving direction can be called the entering road surface, and the lane where the vehicle enters the road surface area covered by the intersection based on the set driving direction can be called the entering lane. That is, the road surface connected to the intersection before the vehicle enters the intersection is called the entering road surface, and the lane connected to the intersection before the vehicle enters the intersection is called the entering lane.

[0116] The road surface where the vehicle exits the road surface area covered by the intersection based on the set driving direction is called the exiting road surface, and the lane where the vehicle exits the road surface area covered by the intersection based on the set driving direction is called the exiting lane. That is, the road surface connected to the intersection after the vehicle exits the intersection is called the exiting road surface, and the lane connected to the intersection after the vehicle exits the intersection is called the exiting lane.

[0117] If the number of entering lanes is the same as the number of exiting lanes, assuming they are both single lanes, and the lane lines of the entering lane include the first left lane boundary line and the first right lane boundary line, and the lane lines of the exiting lane include the second left lane boundary line and the second right lane boundary line, then the reference line can be two. One is the reference line corresponding to the first left lane boundary line and the second left lane boundary line (for easy distinction, this reference line is called the first reference line), and the other is the reference line corresponding to the first right lane boundary line and the second right lane boundary line (similarly, for easy distinction, this reference line is called the second reference line).

[0118] Among them, the first reference line can be the first reference line calculated by using the B-spline curve algorithm according to the end point of the vehicle on the first left lane boundary line when entering the road surface area and the starting point of the vehicle on the second left lane boundary line when exiting the road surface area. The second reference line can be the second reference line calculated by using the B-spline curve algorithm according to the end point of the vehicle on the first right lane boundary line when entering the road surface area and the starting point of the vehicle on the second right lane boundary line when exiting the road surface area.

[0119] In some other embodiments, the number of entering lanes is different from the number of exiting lanes. For example, the number of entering lanes is less than the number of exiting lanes. For example, the number of entering lanes is a single lane and the number of exiting lanes is a double lane. Then, the reference line of the new lane can be calculated by using the B-spline curve algorithm according to the outer lane boundary line of the new lane and the lane boundary line of the single lane closest to the outer lane boundary line.

[0120] In a scenario where the number of incoming lanes is different from the number of outgoing lanes, it is also possible that the number of incoming lanes is more than the number of outgoing lanes. For example, if the number of incoming lanes is two lanes and the number of outgoing lanes is one lane, there is no need to calculate the reference line for the reduced lane.

[0121] It should be understood that the implementation principle of the B-spline curve algorithm can refer to the related technology and will not be elaborated here. In this embodiment, by adopting the B-spline curve algorithm, the artificial determination of the virtual guiding line can be converted into the automatic determination of the virtual guiding line, and the reference line can be determined first by using the B-spline curve algorithm, so as to determine the virtual guiding line for avoiding obstacles in combination with the reference line, thereby improving the general applicability of determining the virtual guiding line.

[0122] The above embodiment takes the reference line as the reference line of the lane boundary as an example to demonstratively illustrate the implementation manner of obtaining the reference line. In some other embodiments, the reference line can also be the center line of the road surface area covered by the set driving direction at the intersection, and specifically, the center line of the road surface can be the reference line of the center line of the lane in this road surface area. If the reference line is the reference line of the center line of the lane, the reference line can be calculated by combining the center lines of the incoming lane and the outgoing lane. Its implementation principle can refer to the implementation principle of the reference line as the reference line of the lane boundary, and it can also be divided into the scenarios where the number of incoming lanes is the same as the number of outgoing lanes and the scenarios where the number of incoming lanes is different from the number of outgoing lanes, which will not be elaborated here.

[0123] In some embodiments, the reference line can also be calculated in combination with the grid topology map.

[0124] Exemplarily, a grid topology map of the intersection can be pre-constructed. Correspondingly, the pre-generated reference line of the intersection can be obtained in combination with the grid topology map. For example, S201 can be replaced with: using the B-spline curve algorithm to calculate the reference line in the grid topology map if there are no obstacles in this road surface area.

[0125] Among them, the grid topology map includes obstacle grids and non-obstacle grids.

[0126] Since the road surface area covered by the set driving direction at the intersection includes obstacles, in the grid topology map, if a certain grid is filled with obstacles (it may be partially filled or fully filled), then this grid is an obstacle grid. On the contrary, if a certain grid is not filled with obstacles, then this grid is a non-obstacle grid. The size of the grid can be determined based on requirements, historical records, and experiments, etc., and this embodiment does not make a limitation. For example, the size of the unit grid can be 1 meter * 1 meter.

[0127] The road surface area covered by the set driving direction at the intersection includes an obstacle flower bed. Correspondingly, as Figure 3As shown in the figure, the grid topology map includes an obstacle flower bed. The grid filled with at least part of the flower bed is an obstacle grid, and the grid not filled with the flower bed is a non-obstacle grid. By using the B-spline curve algorithm, the reference line in the grid topology map can be calculated.

[0128] In this embodiment, by combining the B-spline curve algorithm and the grid topology map to calculate the reference line, it is convenient to implement the B-spline curve algorithm, improve the efficiency and effectiveness of the B-spline curve algorithm, and thus improve the efficiency and reliability of obtaining the reference line.

[0129] In some embodiments, different marks can be used to identify the obstacle grid and the non-obstacle grid. For example, the identifier of the obstacle grid is 1, and the identifier of the non-obstacle grid is 0.

[0130] S202: Determine the avoidance route to avoid obstacles according to the reference line. Among them, the distance from the avoidance route to the reference line is less than the set distance threshold.

[0131] Combined with the above analysis, the reference line can be the reference line of the lane boundary line. Then the number of reference lines of the lane boundary line is two, and the number of avoidance routes is at least one. If the number of avoidance routes is two, the number of virtual guiding lines is two, and there is a one-to-one correspondence between the reference line of the lane boundary line, the avoidance route, and the virtual guiding line. If the number of avoidance routes is one, the number of reference lines of the lane boundary line is one, and the reference line of the lane boundary line intersects with the obstacle.

[0132] Exemplarily, if the two reference lines are the first reference line and the second reference line respectively, if the first reference line intersects with the obstacle, the number of avoidance routes is one, and this avoidance route is generated based on the first reference line. Correspondingly, the virtual guiding line includes the virtual guiding line generated based on the avoidance route, and the other virtual guiding line can be the second reference line.

[0133] If both the first reference line and the second reference line intersect with the obstacle, the number of avoidance routes is two. The avoidance route generated according to the first reference line can be called the first avoidance route, and the avoidance route generated according to the second reference line can be called the second avoidance route. The number of virtual guiding lines is two, one is generated based on the first avoidance route, and the other is generated based on the second avoidance route.

[0134] In the scenario where the reference line is the reference line of the lane boundary line, the number of reference lines is two. By combining whether each reference line intersects with the obstacle to determine the number of avoidance routes, the determined avoidance route can fit the actual scenario and improve the effectiveness of the determined avoidance route.

[0135] As can be seen from the above analysis, in some embodiments, a grid topology map can be pre-constructed. Accordingly, an avoidance route for avoiding obstacles can be determined based on the reference line and the grid topology map.

[0136] Similarly, in this embodiment, the grid topology map can relatively accurately represent the obstacle grids filled with obstacles and the non-obstacle grids not filled with obstacles. By combining the grid topology map, the obstacle grids can be relatively accurately avoided, so that the avoidance route can accurately avoid obstacles, that is, the accuracy and reliability of the avoidance route are improved.

[0137] In some embodiments, the reference line can be used as the weight guiding line, and the Dijskra algorithm can be used to calculate the avoidance route. That is, based on the reference line, the Dijskra algorithm is used for calculation to obtain an avoidance route for avoiding obstacles with a distance from the reference line less than the distance threshold.

[0138] Similarly, for the calculation principle of the Dijskra algorithm, reference can be made to the related technology, which will not be elaborated here. In this embodiment, by combining the Dijskra algorithm to calculate the avoidance route, an obstacle-avoiding route based on the reference line and relatively close to the reference line can be obtained, so as to improve the efficiency of the vehicle driving on the road surface area covered by the virtual guiding line at the intersection, and improve the effectiveness and reliability of the avoidance route.

[0139] As can be seen from the above analysis, the reference line can be the reference line of the road surface center line (specifically the lane center line). If the reference line is the reference line of the road surface center line, then the "surface avoidance" can be converted into "line avoidance", that is, the problem of avoiding obstacles on the road surface is converted into the problem of avoiding obstacles by the line.

[0140] Exemplarily, if the reference line is the reference line of the road surface center line, then determining the avoidance route for avoiding obstacles based on the reference line includes the following steps:

[0141] The first step: Taking half of the preset vehicle driving width as the expansion benchmark, the obstacle is expanded to obtain an expanded obstacle.

[0142] Wherein, the vehicle driving width is the drivable width of the vehicle on the road surface in the relevant vehicle driving scenario, such as 3 meters or 3.5 meters. Accordingly, this step can be understood as expanding the obstacle with half of the width of 3 meters or 3.5 meters to obtain an expanded obstacle.

[0143] Exemplarily, taking half of the width of 3 meters or 3.5 meters to expand the flower bed as shown in Figure 3 to obtain an expanded obstacle as shown in Figure 3

[0144] ​Second step: Determine the avoidance route based on the enlarged obstacle and the reference line.

[0145] Exemplarily, taking the reference line as shown in Figure 3 as the weight guiding line, the avoidance route in the grid topology graph as shown in Figure 3 is calculated by combining the Dijkstra algorithm.

[0146] In this embodiment, by enlarging the obstacle, the "surface avoidance" is converted into "line avoidance", which can reduce the complexity and improve the efficiency and reliability of determining the avoidance route.

[0147] S203: Determine the intersection points of the avoidance route and the obstacle.

[0148] Exemplarily, as shown in Figure 3 , if the avoidance route is generated based on the reference line of the road surface center line, the intersection point is the intersection point of the avoidance route and the enlarged obstacle.

[0149] S204: Taking the reference line as the benchmark and the intersection point as the avoidance point, generate an offset line with smooth curvature, and determine the virtual guiding line corresponding to the set driving direction according to the offset line.

[0150] Among them, the offset line includes the starting point and the ending point of the avoidance route.

[0151] Exemplarily, the offset line can include three points, one is the intersection point of the avoidance route and the obstacle, one is the starting point of the avoidance route, and one is the ending point of the avoidance route, and the curvature of the offset line including these three points is smooth, as shown in Figure 3 .

[0152] Exemplarily, the enlarged obstacle can be projected onto the reference line, and the reference line is divided into three segments, namely the A line, the B line and the C line as shown in Figure 3 . The B line is proportionally offset with the intersection point, and the A line and the C line are gradually offset with the intersection point to generate the offset line as shown in Figure 3 . Among them, the starting point of the offset line is the starting point of the A line, the ending point of the offset line is the ending point of the C line, and the offset line passes through the intersection point. So that the offset degree of the offset line is appropriate to meet the vehicle driving requirements in the actual scenario, that is, the technical effect of making the offset line have high accuracy and reliability.

[0153] In some embodiments, the reference line for generating the offset line is the road surface center line of the road surface area covered by the pre-generated set intersection, that is, the reference line is the reference line of the lane center line. Then, determining the virtual guiding line corresponding to the set driving direction according to the offset line includes: taking the offset line as the virtual center line, generating the virtual lane lines of the virtual center line, and determining the virtual lane lines as the virtual guiding line.

[0154] Exemplarily, since the lane center line is the center line of the lane, therefore, when the lane center line is determined, the lane lines can be determined in combination with the lane center line. Thus, this embodiment can be understood as that when the offset line is determined, it is equivalent that the virtual center line is determined, and thus the virtual lane boundary lines located on both sides of the virtual center line can be determined based on the virtual center line, that is, the virtual guiding line includes two virtual lane boundary lines.

[0155] In this embodiment, since the offset line has high accuracy and reliability, therefore, when generating the virtual guiding line with the offset line as the virtual center line, the technical effect that the virtual guiding line has high accuracy and reliability can be achieved.

[0156] In some embodiments, taking the offset line as the virtual center line to generate the virtual lane line may include the following steps:

[0157] The first step: Obtain the entry width of the entry road surface of the road surface area covered by the set driving direction at the intersection, and obtain the exit width of the exit road surface of the road surface area covered by the set driving direction at the intersection.

[0158] Exemplarily, in combination with the above analysis, the entry road surface may include the entry lane, and the entry road surface may include one entry lane or may include multiple entry lanes. The exit road surface may include the exit lane, and the exit road surface may include one exit lane or may include multiple exit lanes.

[0159] The number of entry lanes and the number of exit lanes may be the same or different. If the entry lane is a single lane, the entry width is the road surface width of the single lane. If the exit width is a double lane, the exit width is the road surface width of the double lane.

[0160] The second step: Perform sampling processing on the virtual center line according to the entry width and the exit width to obtain the virtual lane line.

[0161] In this embodiment, by generating the virtual lane line in combination with the entry width and the exit width, the number of virtual lane lines can meet the scenario where the numbers of each lane converge in the road surface area covered by the set driving direction at the intersection, improve the flexibility and diversity of generating the virtual lane line, and meet the pertinence of the vehicle driving scenario and the riding experience of the riding users.

[0162] In some embodiments, the second step includes the following sub-steps:

[0163] The first sub-step: Sample the virtual center line according to a preset fixed interval to obtain the sampling points on the virtual center line.

[0164] Similarly, the fixed interval can be determined based on requirements, historical records, experiments, etc., and this embodiment does not make any limitations.

[0165] For example, for scenarios with relatively high relative accuracy, the length of the fixed interval can be relatively short. Conversely, for scenarios with relatively low relative accuracy, the length of the fixed interval can be relatively long.

[0166] Exemplarily, as Figure 4 shown, the incoming lane is a single lane and the outgoing lane is three lanes. The width of the incoming lane in the grid topology is 1 meter, and the width of the outgoing lane in the grid topology is 3 meters. Then, sampling can be performed according to the fixed interval. For example, 10 sampling points are obtained from the virtual center line, and the starting point and the ending point of the virtual center line are included in the 10 sampling points.

[0167] Second sub-step: Obtain a perpendicular line passing through the sampling point and perpendicular to the virtual center line.

[0168] Exemplarily, for each sampling point, obtain a perpendicular line passing through the sampling point and perpendicular to the virtual center line. Correspondingly, as Figure 4 shown, multiple perpendicular lines can be obtained.

[0169] Third sub-step: Generate virtual lane lines according to the incoming width, the outgoing width, the sampling points, and the perpendicular lines.

[0170] In this embodiment, by determining the sampling points and determining the perpendicular lines, and combining the incoming width, the outgoing width, the sampling points, and the perpendicular lines to determine the virtual lane lines, the determined virtual lane lines can meet the vehicle driving requirements and improve the effectiveness and reliability of the virtual lane lines.

[0171] In some embodiments, the third sub-step may include the following refinement steps:

[0172] First refinement step: Calculate the width difference between the incoming width and the outgoing width.

[0173] Exemplarily, if the outgoing width is 3 meters and the incoming width is 1 meter, the width difference is 2 meters.

[0174] Second refinement step: According to the number of sampling points and the width difference, determine a boundary point on each of the perpendicular lines where the sampling points are on both sides of the virtual center line.

[0175] Third refinement step: Generate the virtual lane line on that side according to the boundary points on the same side of the virtual center line.

[0176] Exemplarily, the number of sampling points is multiple. For each sampling point, according to the number of sampling points and the width difference, boundary points on the vertical line of the sampling point are determined, that is, one boundary point is determined respectively on the vertical lines on both sides of the virtual center line where the sampling point is located. The boundary points on one side of the virtual center line are used to generate a virtual lane line, which can be understood as the virtual lane boundary on one side of the virtual center line. The boundary points on the other side of the virtual center line are used to generate a virtual lane line, which can be understood as the virtual lane boundary on the other side of the virtual center line.

[0177] Exemplarily, if the number of sampling points is 20, the boundary points of the Nth sampling point are ±N / 20*2, that is, one sampling point corresponds to two boundary points, and the distance of one boundary point is N / 20*2, and the other is -N / 20*2, where N is a positive integer greater than or equal to 1.

[0178] In this embodiment, by combining the width difference and the number of sampling points to determine the boundary points, and generating virtual lane lines based on the boundary points. Since the virtual center line has high accuracy and reliability, the sampling points on the virtual center line have high accuracy. Therefore, when determining the boundary points by combining the sampling points with high accuracy, the boundary points can have high reliability. Furthermore, when generating virtual lane lines by combining the boundary points, the virtual lane lines can have high accuracy.

[0179] Combined with the above analysis, the exit lane can be a single lane or multiple lanes. If the exit lane is a single lane, the boundary points are respectively located on both sides of the virtual center line. Then, generating virtual lane lines according to the boundary points may include: connecting the boundary points on one side of the virtual center line to obtain the virtual lane line on one side of the virtual center line (specifically, it can be understood as the virtual lane boundary), so as to obtain two virtual lane lines (specifically, it can be understood as the virtual lane boundary) located on both sides of the virtual center line, that is, the number of virtual lane lines (specifically, it can be understood as the virtual lane boundary) is two, and the two virtual lane lines (specifically, it can be understood as the virtual lane boundary) are located on both sides of the virtual center line.

[0180] Exemplarily, the exit lane can also be multiple lanes. After determining two virtual lane lines based on the above method, other virtual lane lines of the multiple lanes can be determined according to the vehicle driving width.

[0181] For example, the exit lane is Figure 4 the three-lane shown, then after determining the first virtual lane line and the second virtual lane line as shown in Figure 4 it can be based on the first virtual lane line to determine the third virtual lane line, and based on the second virtual lane line to determine the fourth virtual lane line.

[0182] Exemplarily, since the distance between two lane lines is the vehicle driving width, the third virtual lane line as shown in Figure 4 can be generated according to the first virtual lane line and the vehicle driving width, and the fourth virtual lane line as shown in Figure 4 can be generated according to the second virtual lane line and the vehicle driving width.

[0183] In some other embodiments, it is also possible to determine the side line points for generating the third virtual lane line and the line points for generating the fourth virtual lane line during sampling, and connect the side line points for generating the third virtual lane line to obtain the third virtual lane line, and connect the side line points for generating the fourth virtual lane line to obtain the fourth virtual lane line.

[0184] Please refer to Figure 5 , Figure 5 , which is a schematic diagram of a virtual guiding line generation device according to an embodiment of the present disclosure. As shown in Figure 5 , the device 500 includes:

[0185] An obtaining unit 501, configured to obtain a reference line of a pre-generated intersection, where the reference line is generated based on a set driving direction in a road surface area covered by the intersection and does not avoid obstacles located in the road surface area.

[0186] A determining unit 502, configured to determine an avoidance route for avoiding the obstacles according to the reference line, where a distance from the avoidance route to the reference line is less than a set distance threshold.

[0187] A first generating unit 503, configured to generate a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route, and the obstacles.

[0188] Please refer to Figure 6 , Figure 6 , which is a schematic diagram of a virtual guiding line generation device according to another embodiment of the present disclosure. As shown in Figure 6 , the device 600 includes:

[0189] A constructing unit 601, configured to construct a grid topology map of an intersection, where the grid topology map includes obstacle grids and non-obstacle grids.

[0190] A second generating unit 602, configured to generate the reference line according to the grid topology map.

[0191] An obtaining unit 603, configured to obtain a reference line of a pre-generated intersection, where the reference line is generated based on a set driving direction in a road surface area covered by the intersection and does not avoid obstacles located in the road surface area.

[0192] A determination unit 604, configured to determine an avoidance route that avoids the obstacle according to the reference line and the grid topology map.

[0193] Combined Figure 6 It can be known that in some embodiments, the determination unit 604 includes:

[0194] An expansion subunit 6041, configured to perform an expansion process on the obstacle with half of the preset vehicle driving width as the expansion reference to obtain an expanded obstacle.

[0195] A third determination subunit 6042, configured to determine the avoidance route according to the expanded obstacle and the reference line.

[0196] A first generation unit 605, configured to generate a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route, and the obstacle.

[0197] Combined Figure 6 It can be known that in some embodiments, the first generation unit 605 includes:

[0198] A first determination subunit 6051, configured to determine the intersection point of the avoidance route and the obstacle.

[0199] A generation subunit 6052, configured to generate an offset line with smooth curvature with the reference line as the reference and the intersection point as the avoidance point.

[0200] A second determination subunit 6053, configured to determine the virtual guiding line according to the offset line.

[0201] In some embodiments, the reference line for generating the offset line is the road center line of the pre-generated road surface area; the second determination subunit 6053 includes:

[0202] A generation module, configured to generate virtual lane lines with the offset line as the virtual center line;

[0203] A determination module, configured to determine the virtual lane lines as the virtual guiding line.

[0204] In some embodiments, the generation module includes:

[0205] A first acquisition sub-module, configured to acquire the driving width of the incoming road surface of the road surface area.

[0206] A second acquisition sub-module, configured to acquire the driving width of the outgoing road surface of the road surface area.

[0207] A sampling sub-module, configured to perform sampling processing on the virtual center line according to the incoming width and the outgoing width to obtain the virtual lane lines.

[0208] In some embodiments, the sampling sub-module is configured to sample the sampling points on the virtual center line at a preset fixed interval, obtain a perpendicular line passing through the sampling points and perpendicular to the virtual center line, and generate the virtual lane line according to the driving-in width, the driving-out width, the sampling points, and the perpendicular line.

[0209] In some embodiments, the sampling sub-module is configured to calculate the width difference between the driving-in width and the driving-out width, determine a side line point on each of the perpendicular lines on both sides of the virtual center line of the sampling points according to the number of sampling points and the width difference, and generate the virtual lane line on this side according to the side line points on the same side of the virtual center line.

[0210] According to another aspect of the embodiments of the present disclosure, the embodiments of the present disclosure further provide an electronic map, which records intersection elements, where the intersection elements include obstacles and virtual guiding lines, and the virtual guiding lines are used to guide vehicles to pass through the intersection area, and the virtual guiding lines are generated based on the method described in any one of the first aspects of the present disclosure.

[0211] Combined with the above embodiments of generating virtual guiding lines, it can be seen that the virtual guiding lines generated by sampling the above method have high accuracy and reliability. Therefore, the electronic map generated based on the virtual guiding lines has high accuracy and reliability, so that when a vehicle travels through the intersection area based on the electronic map, the driving safety of the vehicle can be improved, the vehicle can be prevented from colliding with obstacles, and the riding experience of the passengers can be satisfied.

[0212] Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided by the embodiments of the present disclosure. As Figure 7 shown, the electronic device 700 of the embodiments of the present disclosure may include: at least one processor 701 ( Figure 7 only one processor is shown in the figure); and a memory 702 communicatively connected to at least one processor. Among them, the memory 702 stores instructions executable by at least one processor 701, and the instructions are executed by at least one processor 701 so that the electronic device 700 can execute the technical solutions in any one of the foregoing method embodiments.

[0213] Optionally, the memory 702 may be either independent or integrated with the processor 701.

[0214] When the memory 702 is a device independent of the processor 701, the electronic device 700 further includes: a bus 703 for connecting the memory 702 and the processor 701.

[0215] The electronic device provided by the embodiments of the present disclosure may execute the technical solutions of any of the foregoing method embodiments. The implementation principles and technical effects are similar and will not be described herein again.

[0216] The embodiments of the present disclosure also provide a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, it is used to implement the technical solutions in any of the foregoing method embodiments.

[0217] The embodiments of the present disclosure provide a computer program product, including a computer program. When the computer program is executed by a processor, it implements the technical solutions in any of the foregoing method embodiments.

[0218] The embodiments of the present disclosure also provide a chip, including: a processing module and a communication interface. The processing module can execute the technical solutions in the foregoing method embodiments.

[0219] Further, the chip further includes a storage module (such as a memory). The storage module is used to store instructions. The processing module is used to execute the instructions stored in the storage module. And the execution of the instructions stored in the storage module enables the processing module to execute the technical solutions in the foregoing method embodiments.

[0220] It should be understood that the foregoing processor may be a central processing unit (English: Central Processing Unit, abbreviated as: CPU), or may also be other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated as: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated as: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly implemented by the execution of the hardware processor, or can be implemented by the combination of hardware and software modules in the processor.

[0221] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disc, etc.

[0222] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, the buses in the accompanying drawings of the present disclosure are not limited to only one bus or one type of bus.

[0223] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disc. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0224] An exemplary storage medium is coupled to the processor, enabling the processor to read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device.

[0225] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for generating a virtual guiding line, including: Obtaining a reference line of a pre-generated intersection, wherein the reference line is generated based on a set driving direction in a road surface area covered by the intersection and does not avoid obstacles located in the road surface area; Taking half of the preset vehicle driving width as an expansion benchmark, expanding the obstacle to obtain an expanded obstacle; Calculating an avoidance route that avoids the obstacle according to the expanded obstacle and using the reference line as a weight guiding line, wherein the distance from the avoidance route to the reference line is less than a set distance threshold; Generating a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route and the obstacle.

2. The method according to claim 1, wherein, The generating a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route and the obstacle includes: Determining an intersection point between the avoidance route and the obstacle; Taking the reference line as a benchmark and the intersection point as an avoidance point to generate an offset line with smooth curvature; Determining the virtual guiding line according to the offset line.

3. The method according to claim 2, wherein, The reference line used to generate the offset line is the road center line of the pre-generated road surface area; The determining the virtual guiding line according to the offset line includes: Generating virtual lane lines with the offset line as a virtual center line; Determining the virtual lane lines as the virtual guiding line.

4. The method according to claim 3, wherein, The generating virtual lane lines with the offset line as a virtual center line includes: Obtaining the driving-in width of the driving-in road surface of the road surface area; Obtaining the driving-out width of the driving-out road surface of the road surface area; Performing sampling processing on the virtual center line according to the driving-in width and the driving-out width to obtain the virtual lane lines.

5. The method according to claim 4, wherein, The performing sampling processing on the virtual center line according to the driving-in width and the driving-out width to obtain the virtual lane lines includes: Sampling at preset fixed intervals to obtain sampling points on the virtual center line; Obtaining perpendicular lines passing through the sampling points and perpendicular to the virtual center line; Generating the virtual lane lines according to the driving-in width, the driving-out width, the sampling points and the perpendicular lines.

6. The method according to claim 5, wherein, The generating the virtual lane lines according to the driving-in width, the driving-out width, the sampling points and the perpendicular lines includes: Calculating the width difference between the driving-in width and the driving-out width; According to the number of sampling points and the width difference, respectively determining a side line point on the perpendicular lines on both sides of the sampling points located on both sides of the virtual center line; Generating the virtual lane lines on one side according to the side line points located on the same side of the virtual center line.

7. The method according to claim 1, the method further includes: Constructing a grid topology of the intersection, wherein the grid topology includes obstacle grids and non-obstacle grids; Generating the reference line according to the grid topology; And, determining an avoidance route that avoids the obstacle according to the reference line, including: Determining an avoidance route that avoids the obstacle according to the reference line and the grid topology map.

8. A virtual guiding line generation device, including: An acquisition unit, configured to acquire a reference line of a pre-generated intersection, where the reference line is generated based on a set driving direction in a road surface area covered by the intersection and does not avoid obstacles located in the road surface area; A determination unit, configured to use half of the preset vehicle driving width as an expansion benchmark to perform an expansion process on the obstacle to obtain an expanded obstacle; calculate an avoidance route that avoids the obstacle according to the expanded obstacle and using the reference line as a weight guiding line, where the distance from the avoidance route to the reference line is less than a set distance threshold; A first generation unit, configured to generate a virtual guiding line corresponding to the set driving direction according to the reference line, the avoidance route, and the obstacle.

9. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1-7 is implemented.

10. A computer program product, including a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1-7 is implemented.

11. An electronic map, which records intersection elements, where the intersection elements include obstacles and virtual guiding lines, and the virtual guiding lines are used to guide a vehicle to pass through an intersection area, and the virtual guiding lines are generated based on the method according to any one of claims 1-7.

Citation Information

Patent Citations

  • Unmanned obstacle avoidance path planning method and system

    CN113916246A