Navigation route generation method and device, electronic equipment and storage medium

Abstract

The application relates to a navigation route generation method and device, electronic equipment and a storage medium. When a vehicle for automatic driving generates a navigation route, a trigger instruction is obtained. The trigger instruction is used to represent that, in the process of generating the navigation route, one-time route calculation is successful and second-time route calculation fails. According to the trigger instruction, a target road is searched in a road navigation route after the one-time route calculation is successful. Then, a lane-changing mark is generated for a target lane in a lane of the target road. Then, a lane navigation route is generated based on at least a starting point and an ending point of the road navigation route and the lane-changing mark, so that a lane where the starting point is located is connected to a lane where the ending point is located. Finally, the current navigation route of the vehicle is generated based on the road navigation route and the lane navigation route. The application can improve the success rate of second-time route calculation, thereby improving the success rate of navigation route generation while ensuring the efficiency of navigation route generation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a method and device for generating a navigation route, an electronic device, and a storage medium. BACKGROUND

[0002] A navigation route of a vehicle is the basis for realizing automatic driving.

[0003] In related technologies, in the process of generating a navigation route, one-time route calculation and two-time route calculation can be used to generate a navigation route. The one-time route calculation can obtain a road with multiple lanes, and a road navigation route can be formed by connecting the multiple roads. The two-time route calculation can calculate a lane navigation route between lanes in the road based on a start point and an end point of the road navigation route. Thus, the navigation route is generated based on the one-time route calculation and the two-time route calculation.

[0004] The two-time route calculation needs to connect the lanes involved from the start point to the end point. Due to the switching of virtual and real roads, the change of the number of lanes, and other limitations, the lanes of a certain road can not be successfully connected, which causes the two-time route calculation to fail, and thus the navigation route needs to be regenerated from the one-time route calculation, which is costly and inefficient. SUMMARY

[0005] To solve or partially solve the problems in related technologies, the present application provides a method and device for generating a navigation route, an electronic device, and a storage medium, which can improve the success rate of two-time route calculation, and thus improve the success rate of generating a navigation route while ensuring the efficiency of generating a navigation route.

[0006] The first aspect of the present application provides a method for generating a navigation route, which comprises:

[0007] In the process of generating a navigation route for a vehicle for automatic driving, a trigger instruction is obtained. The trigger instruction is used to indicate that the one-time route calculation is successful and the two-time route calculation fails in the process of generating a navigation route.

[0008] According to the trigger instruction, a target road is searched in a road navigation route after the one-time route calculation is successful. The target road includes a lane that allows lane changing.

[0009] A lane-changing mark is generated for a target lane in the lane of the target road. The target lane allows lane changing.

[0010] A lane navigation route is generated based on at least a start point and an end point of the road navigation route and the lane-changing mark, so that the lane where the start point is located is connected to the lane where the end point is located.

[0011] generate a current navigation route of the vehicle based on the road navigation route and the lane navigation route.

[0012] Optionally, the process of generating the trigger instruction comprises:

[0013] when the secondary route calculation is performed after the success of the primary route calculation, determining a starting point and an ending point in the road navigation route after the success of the primary route calculation;

[0014] loading lanes corresponding to each road in the road navigation route;

[0015] if the lane where the starting point is located fails to be connected to the lane where the ending point is located through other lanes, generating a trigger instruction.

[0016] Optionally, the process of searching for a target road in the road navigation route after the success of the primary route calculation comprises:

[0017] determining each road in the road navigation route;

[0018] searching for a first road where a lane that fails to connect the starting point and the ending point in the secondary route calculation is located;

[0019] taking the first road as a target road.

[0020] Optionally, the process of searching for a target road in the road navigation route after the success of the primary route calculation comprises:

[0021] determining each road in the road navigation route;

[0022] searching for a first road where a lane that fails to connect the starting point and the ending point in the secondary route calculation is located;

[0023] taking a road having a blood relationship with the first road as a second road; the blood relationship is used to represent that each road has a parent-child node relationship and / or an inheritance node relationship;

[0024] taking the first road and the second road as target roads.

[0025] Optionally, the process of generating a lane-changing mark for a target lane in the lane of the target road comprises:

[0026] taking a lane in the target road that is not traversed in the secondary route calculation as a target lane;

[0027] generating a lane-changing mark corresponding to the target lane based on lane data corresponding to the target lane; wherein the lane data at least includes first data used to represent whether the target lane can change lanes, second data used to represent a lane-changing direction, and third data used to represent a lane-changing termination position.

[0028] Optionally, the lane navigation route is generated based on at least the starting point and the ending point of the road navigation route and the lane-changeable mark, comprising:

[0029] determining a corresponding starting point in the target road for the starting point and a corresponding ending point in the target road for the ending point;

[0030] determining a position point based on the lane-changeable mark, which enables the lane where the starting point is located to be connected with the lane where the ending point is located;

[0031] calculating a candidate lane navigation route connecting the starting point and the ending point according to the position point;

[0032] selecting one of the candidate lane navigation routes as the lane navigation route, which meets the minimum cost condition.

[0033] Optionally, the lane navigation route is selected from the candidate lane navigation routes based on the minimum cost condition, comprising:

[0034] calling a cost function to calculate the cost value of each candidate lane navigation route; wherein the cost function is used to calculate the cost value based on the number of lane changes and the length of lane changes in the lane navigation route;

[0035] selecting the candidate lane navigation route corresponding to the minimum cost value as the lane navigation route.

[0036] The second aspect of the present application provides a device for generating a navigation route, comprising:

[0037] a triggering unit configured to obtain a triggering instruction when a navigation route is generated for an autonomous vehicle; the triggering instruction is used to indicate that the first route calculation is successful and the second route calculation fails in the process of generating the navigation route;

[0038] a searching unit configured to search for a target road in the road navigation route after the first route calculation is successful according to the triggering instruction; wherein the target road has a lane that allows lane change;

[0039] a marking unit configured to generate a lane-changeable mark for a target lane in the lane of the target road; wherein the target lane allows lane change;

[0040] a calculating unit configured to generate a lane navigation route based on at least the starting point and the ending point of the road navigation route and the lane-changeable mark, so that the lane where the starting point is located is connected with the lane where the ending point is located;

[0041] a generating unit configured to generate the current navigation route of the vehicle based on the road navigation route and the lane navigation route.

[0042] The third aspect of the present application provides an electronic device, comprising:

[0043] a processor; and

[0044] a memory having stored thereon executable code that, when executed by the processor, causes the processor to perform the method described above.

[0045] The fourth aspect of the present application provides a computer-readable storage medium having stored thereon executable code that, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0046] The technical solution provided by the present application first obtains a trigger instruction when generating a navigation route for an autonomous vehicle; the trigger instruction is used to represent that, in the process of generating the navigation route, a first route calculation is successful and a second route calculation fails; then, according to the trigger instruction, a target road is searched for in a road navigation route after the first route calculation is successful; the target road has a lane that allows lane changing; then, a lane-changing mark is generated for a target lane in the lane of the target road; the target lane allows lane changing; then, a lane navigation route is generated based at least on a starting point and an ending point of the road navigation route and the lane-changing mark, so that the lane where the starting point is located is connected to the lane where the ending point is located; finally, a current navigation route of the vehicle is generated based on the road navigation route and the lane navigation route. It can be seen that, in the present application, the lane-changing mark is generated for the target lane based on the road navigation route after the first route calculation is successful when the first route calculation is successful and the second route calculation fails, which can improve the success rate of the second route calculation, and thus improve the success rate of the navigation route generation while ensuring the efficiency of the navigation route generation.

[0047] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present application. BRIEF DESCRIPTION OF DRAWINGS

[0048] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings, in which like reference characters refer to like parts throughout the several views, and in which:

[0049] Figure 1 is a flow diagram of a navigation route generation method according to an embodiment of the present application.

[0050] Figure 2 is a schematic diagram of a scenario in which a lane-changing mark is generated according to an embodiment of the present application.

[0051] Figure 3FIG. 1 is a flowchart illustrating a process of searching for a target road in a method for generating a navigation route according to an embodiment of the present application.

[0052] Figure 4 FIG. 2 is a diagram illustrating a data structure between roads according to an embodiment of the present application.

[0053] Figure 5 FIG. 3 is a diagram illustrating a scenario of a lane navigation route according to an embodiment of the present application.

[0054] Figure 6 FIG. 4 is a block diagram of a navigation route generation apparatus according to an embodiment of the present application.

[0055] Figure 7 FIG. 5 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] Embodiments of the present application will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the application are shown. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0057] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0058] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It is to be further understood that the terms "comprise", "comprising", "comprises", "including", "includes" or "contain" or "containing" when used in this specification, specify the presence of stated features, integers, steps, operations, elements, or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof.

[0059] The embodiment of the application can be applied in the scene of automatic driving, and in particular, can be applied in the scene of once successful route calculation and twice failed route calculation when generating a navigation route of automatic driving. When once successful route calculation and twice failed route calculation, the navigation route is usually recalculated from the once successful route calculation, which results in high calculation cost and long generation time of the navigation route, and may also cause safety hazards to automatic driving.

[0060] To solve the above problems, the embodiment of the application provides a method for generating a navigation route, which can determine a target road that is not successfully connected by using a road navigation route after once successful route calculation and twice failed route calculation, connect the lanes in the target road, and generate a navigation route. Compared with the calculation cost of regenerating the navigation route, the method only needs to pay a little calculation cost to obtain an accurate navigation route, and improves the generation efficiency.

[0061] The technical solutions of the embodiment of the application are described in detail below with reference to the drawings.

[0062] Figure 1 FIG. 1 is a flowchart of a method for generating a navigation route according to an embodiment of the application.

[0063] Referring to Figure 1 The method for generating a navigation route according to the embodiment of the application includes the following steps.

[0064] In S101, a trigger instruction is obtained when a navigation route of an automatic driving vehicle is generated. The trigger instruction is used to represent that once successful route calculation and twice failed route calculation occur in the process of generating the navigation route.

[0065] In the embodiment of the application, the route calculation method can be one-way search or two-way search, and any route calculation method that can be applied in the embodiment of the application can be used, which is not limited herein.

[0066] In the embodiment of the application, the navigation route of the automatic driving vehicle can be obtained by using once route calculation and twice route calculation when the navigation route is generated. The embodiment of the application is mainly aimed at the scene of once successful route calculation and twice failed route calculation, and can improve the generation efficiency of the navigation route.

[0067] In the embodiment of the application, the trigger instruction is generated when once successful route calculation and twice failed route calculation occur. The embodiment of the application can obtain the trigger instruction to execute the subsequent process.

[0068] The generation process of the trigger instruction includes the following steps.

[0069] When the twice route calculation is performed after the once successful route calculation, the starting point and the ending point in the road navigation route after the once successful route calculation are determined.

[0070] Load the lanes corresponding to each road in the road navigation route;

[0071] If the starting lane fails to connect with the ending lane through other lanes, a trigger instruction is generated.

[0072] In the embodiments of the present application, after a successful first route calculation, a road navigation route is generated, which includes a plurality of roads road, and each road can include a plurality of lanes lane. After generating the road navigation route, the lanes in the generated road navigation route are further connected based on the starting point and the ending point, as the basic data for generating the navigation route.

[0073] In actual use, when the first route calculation is successful, a position point representing the connection relationship can be set in each road, and a starting point and an ending point are set in each road to realize the connection from the starting point to the ending point of the navigation route and to prepare data for the second route calculation.

[0074] In the embodiments of the present application, when the second route calculation is performed, each lane in each road in the road navigation route can be loaded. When the starting lane cannot be successfully connected with the ending lane, the second route calculation fails, and a trigger instruction can be generated at this time. The trigger instruction can be, for example, error information generated when the second route calculation fails, or a lane navigation route that can be connected is not included in the result detected when the second route calculation process ends.

[0075] It can be understood that the map data used in the embodiments of the present application can be pre-set, and the map data can include a plurality of information, such as position information, coordinate information, lane change markers corresponding to lanes, lane change termination position markers, and the like. After the first route calculation is successful, a starting point and an ending point of each road segment can be generated, and if the starting point and the ending point of any road segment cannot be connected based on the lane, a trigger instruction of the second route calculation failure can be generated.

[0076] S102, according to the trigger instruction, find a target road in the road navigation route after the first route calculation is successful; wherein the target road has a lane that allows lane changing.

[0077] In the embodiments of the present application, the target road can be found according to the result of the first route calculation. The target road at least has a lane that allows lane changing, that is, the target road at least has the possibility of successfully connecting the starting point and the ending point.

[0078] In the embodiments of the present application, the target road can be a road whose starting point and ending point fail to successfully connect, or a road having a blood relationship with the target road, such as a parent node of the target road.

[0079] It can be understood that the target road can be multiple, if it is multiple target roads, since at least having blood relationship, can be combined, can be multiple target roads as a target road to perform the embodiment of the application. That is, if the target road is combined with multiple roads having blood relationship, the first point and the tail point of the target road still have and only one.

[0080] S103, generating a lane-changing mark for the target lane in the lane of the target road; wherein the target lane allows lane changing.

[0081] In the embodiment of the application, after obtaining the target road, a lane-changing mark can be generated for the target lane in the lane of the target road.

[0082] In actual use, the lane-changing mark can represent the direction from which the lane can change, the length of the lane change termination, etc. The shape, color and style of the lane-changing mark can be pre-set according to actual needs to represent a variety of information, which will not be described here.

[0083] In actual use, referring to Figure 2 , Figure 2 is a scene diagram generated by the lane-changing mark according to the embodiment of the application.

[0084] Figure 2 In the embodiment of the application, the road 10 and the road 20 are connected, wherein the road 10 and the road 20 each have three lanes, the first lane, the second lane and the third lane. Wherein, the lane-changing mark can be lane-changing mark 101, lane-changing mark 102, lane-changing mark 103, lane-changing mark 201, lane-changing mark 202, lane-changing mark 203. In actual use, the lane-changing mark 101 and the lane-changing mark 102 can represent that the lane can change from the first lane to the second lane, the lane-changing mark 102 and the lane-changing mark 103 can represent that the lane can change from the third lane to the second lane. The lane-changing mark 201 and the lane-changing mark 202 can represent that the lane can change from the first lane to the second lane and from the second lane to the first lane, and the lane-changing mark 202 can represent the position and direction of the lane change.

[0085] It can be understood that in actual use, the corresponding relationship between the lane-changing marks can be set according to actual needs, and when there is no lane-changing mark, it can be determined that the lane does not allow lane changing or does not need to be taken as a lane for re-executing the secondary route calculation.

[0086] S104, generating a lane navigation route based on at least the starting point and the ending point of the road navigation route and the lane-changing mark, so that the lane where the starting point is located is connected to the lane where the ending point is located.

[0087] In the embodiment of the present application, when the target road has a lane-changing mark, a lane navigation route can be generated based on the lane-changing mark, wherein the lane navigation route can at least connect the lane where the starting point is located and the lane where the ending point is located in the target road section, and finally can connect the lane where the starting point is located and the lane where the ending point is located.

[0088] S105, generating a current navigation route of the vehicle based on the road navigation route and the lane navigation route.

[0089] In the embodiment of the present application, the current drivable navigation route of the vehicle can be generated based on the lane navigation route generated in the foregoing and the road navigation route generated after the first route calculation succeeds, and the vehicle controller of the autonomous vehicle is provided to realize autonomous driving.

[0090] As can be seen from the embodiment of the present application, when the first route calculation succeeds and the second route calculation fails, the target road is found by triggering the instruction, and the lane-changing mark is generated for the target road in the road, and then the route that fails to be successfully connected after the second route calculation fails can be regenerated, and the current navigation route that can be used by the vehicle is generated. The success rate of the second route calculation can be improved, and the success rate of the navigation route generation is improved while ensuring the efficiency of the navigation route generation.

[0091] It should be noted that in the field of autonomous driving, the basis for route calculation is usually the lane center line, not the boundary line of the road.

[0092] In the foregoing embodiment, the process of finding the target road is introduced, and the target road can be found in various ways in the embodiment of the present application, so as to improve the success rate of the second route calculation.

[0093] Referring to Figure 3 , Figure 3 is a flowchart of finding a target road in a navigation route generation method according to an embodiment of the present application.

[0094] In the embodiment of the present application, the target road is found in the road navigation route after the first route calculation succeeds, comprising:

[0095] S301, determining each road in the road navigation route.

[0096] In the embodiment of the present application, each road in the road navigation route can be loaded based on map data. Generally, the road navigation route can be composed of multiple roads, and the basic information of the road can be obtained based on the map data. The map data in the embodiment of the present application can be data obtained from a high-precision map database, or can be locally saved map data, which is not limited herein.

[0097] S302, find the first road where the lane that fails to connect the start point and the end point is located.

[0098] S303, take the first road as the target road.

[0099] In the embodiments of the present application, the navigation route can correspond to a structure tree on the data structure, each road can be as a node in the structure tree, when the secondary route calculation fails, the node corresponding to the road where the failure occurs can be marked, and the first road where the lane that fails to connect the start point and the end point is located can be confirmed by searching the mark, and the road is taken as the target road.

[0100] Of course, when the secondary route calculation fails, when the lane navigation route that successfully connects the beginning and the end in the road fails to appear, the road can be determined as the first road.

[0101] In actual use, when the lane navigation route that successfully connects the beginning and the end in the road fails to appear, the mark corresponding to the failed road can be output, and the target road can be quickly determined by using the mark.

[0102] It can be understood that the embodiments of the present application can be used to plan the local road, so that the beginning point and the end point in the road segment can be successfully connected.

[0103] In actual use, the situation that the beginning point and the end point cannot be connected can be that in the road segment, the map data corresponding to the road segment is marked with the number of times that the road segment can change lanes, for example, once, at this time, if the beginning point is located in the first lane in the road segment, and the secondary route calculation needs to change lanes twice to the third lane where the end point is located, at this time, due to the limitation of the number of times of changing lanes, the beginning point and the end point cannot be connected, and the road can be taken as the unconnected road.

[0104] However, since the data marked in the map data is usually the overall data of the entire road segment, at this time, the number of times of changing lanes cannot completely reflect the actual driving situation in the actual driving process, the unconnected road can be re-planned, and the lane change can be completed before the lane change prohibited position of the road, therefore, the embodiments of the present application can not need to perform the primary route calculation, and can directly optimize the unconnected road based on the result of the primary route calculation and the lane searched by the secondary route calculation, and the lane driving route of the road segment can be re-planned through calculation, thereby improving the success rate of the secondary route calculation.

[0105] Of course, in order to further improve the success rate of the secondary route calculation, the road having a blood relationship with the unconnected road can also be re-planned.

[0106] On the basis of the foregoing embodiments, in the embodiments of the present application, the target road is searched in the road navigation route after the primary route calculation succeeds, comprising:

[0107] determining each road in the road navigation route;

[0108] finding a first road in which a lane from the start point to the end point is not connected when the secondary algorithm fails;

[0109] taking a road having a blood relationship with the first road as a second road; the blood relationship is used to represent that each road has a parent-child node relationship and / or an inheritance node relationship;

[0110] taking the first road and the second road as target roads.

[0111] Referring to Figure 4 , Figure 4 is a schematic diagram of the data structure between the roads shown in the embodiments of the present application. In the data structure, A, B, C, and D can represent four roads, respectively, and road A is connected to road B, road B is connected to road C and road D, respectively. In actual use, after the first algorithm succeeds, the road navigation route has the connection order of D-C-B-A, then road D is the parent node of road C, and by analogy, road B is the parent node of road A, and road A has the inheritance node relationship of road C and road D.

[0112] In the embodiments of the present application, the blood relationship can refer to the road having a parent node relationship or an inheritance node relationship with the node of the first road.

[0113] When the lane from the start point to the end point of the first road fails to be connected, it can be re-planned, but it cannot be connected, for example, due to the change in the number of lanes, from two lanes of the previous road to three lanes, when it is necessary to change lanes from the third lane to the first lane, since the third lane cannot change lanes in the road, the start point and the end point of the road segment do not exist. Based on this, in the embodiments of the present application, the second road having a parent node relationship with the first road can be taken as a target road. The start point of the target road can be the start point of the second road, and the end point can be the end point of the first road.

[0114] In the embodiments of the present application, the blood relationship is used to generate the road navigation route, and multiple target roads can be taken as a whole, even if the road changes from three lanes to two lanes, it can be calculated as a target road, and the lane navigation route in the road is re-planned, so that the lane from the start point to the end point in the target road can be connected, so that the lane from the start point to the end point in the road navigation route can be connected.

[0115] When the target road is determined, the embodiment of the application generates lane-changing marks as basic data for improving the success rate of the secondary route calculation in the manner. This manner only needs very little computing power, which can be ignored compared with the computing power needed for the primary route calculation. The process is explained in detail below.

[0116] In the embodiment of the application, the lane-changing marks are generated for the target lane in the target road, including:

[0117] The lane in the target road which is not traversed in the secondary route calculation is taken as the target lane.

[0118] The lane-changing marks corresponding to the target lane are generated based on the lane data corresponding to the target lane, wherein the lane data at least includes the first data for representing whether the target lane can change lanes, the second data for representing the lane-changing direction, and the third data for representing the lane-changing termination position.

[0119] In the embodiment of the application, for the lane in the target road, the target road can be determined to re-plan the lane navigation route.

[0120] It can be understood that in the secondary route calculation, the lane identifiers corresponding to the searched lanes are added to the search node, which can be embodied in the form of a list or an array. When the embodiment of the application is executed, the lane identifiers corresponding to the unsearched lanes can be added to the search node.

[0121] Of course, the search node can only include the lane identifiers corresponding to the untraversed lanes, or can include the lane identifiers corresponding to the traversed lanes in the secondary route calculation.

[0122] In the embodiment of the application, based on the search node, the information in the map data in the foregoing embodiment, such as the position information, the coordinate information, the lane-changing marks corresponding to the lanes, the lane-changing termination position marks, and the like, can be called to calculate whether the start point and the end point in the target road can be connected. Each time a lane identifier corresponding to a lane is added, whether the start point and the end point in the target road can be connected can be calculated once, and the route in which the start point and the end point can be connected. When a preset number of routes in which the start point and the end point in the target road can be connected are calculated, the lane identifiers of the lanes in the search node can be stopped. The preset number can be one or more, and is preferably at least two. Of course, all the lane identifiers corresponding to the lanes can be added, and then the lane navigation route in which the start point and the end point can be connected is calculated.

[0123] In the embodiments of the present application, the lane-changing mark corresponding to the target lane can be generated based on the lane data corresponding to the target lane. The lane data can be information in the aforementioned map data. It can be understood that the specific form of the lane-changing mark can be set according to actual needs. The information represented by the mark can be set according to actual needs. For example, a circular mark can represent that the lane marked can change lanes, an arrow mark can represent the direction in which the lane can change lanes, a cross mark can represent the position at which the lane can change lanes, and the like, and the lane-changing mark can be generated based on the lane data in the map data.

[0124] In the embodiments of the present application, based on the road navigation route after the first successful calculation, the lane-changing mark can be generated for the target lane in the target road that cannot successfully connect the start point and the end point, so that a preset number of lane navigation routes can be calculated according to the lane-changing mark.

[0125] When the lane-changing mark is generated, the lane navigation route can be generated based on the lane-changing mark.

[0126] In the embodiments of the present application, the lane navigation route is generated based on at least the start point and the end point of the road navigation route and the lane-changing mark, comprising:

[0127] determining the start point corresponding to the start point in the target road and the end point corresponding to the end point in the target road;

[0128] determining the position point that can connect the lane where the start point is located and the lane where the end point is located based on the lane-changing mark;

[0129] calculating the candidate lane navigation route connecting the start point and the end point according to the position point;

[0130] taking one of the candidate lane navigation routes meeting the minimum cost condition as the lane navigation route.

[0131] According to the foregoing embodiments, the start point and the end point in the road navigation route correspond to the start point and the end point of each road, and based on this, in the embodiments of the present application, the lane navigation route can be generated based on the lane-changing mark generated in the foregoing.

[0132] It can be understood that in the target road, the start point and the end point of the target road can be connected by calculating a Bezier curve. Of course, other connection methods, such as point-by-point connection, can also be used. The embodiments of the present application preferably use a Bezier curve.

[0133] In actual use, referring to Figure 5 , Figure 5is a scene schematic diagram of a lane navigation route shown by an embodiment of the present application. Among them, the lane AA, the lane BB and the lane CC are lanes in the same road, for example, a target road. X1 is the starting point of the target road, and X2 is the ending point of the target road. When the second route calculation is performed, the starting point and the ending point cannot be connected. By applying the embodiment of the present application, a road navigation route composed of a plurality of Y points in 500 is automatically generated, and then the Y point and the X2 point can be connected to make the starting point and the ending point of the road connected. The curve in 500 can be a calculated Bezier curve.

[0134] In the embodiment of the present application, the lane changeable mark can be used to obtain the information of the corresponding lane, that is, the specific lane which needs to generate the road navigation route can be obtained, and then based on the turning and position information represented by the lane changeable mark, the starting point and the ending point of the corresponding curve of the road navigation route to be generated can be determined, and then the Bezier curve in, for example, Figure 5 can be calculated.

[0135] In the embodiment of the present application, the lane navigation route can have multiple lanes in the target road. In order to ensure that the generated is the optimal route, in the embodiment of the present application, the lane navigation route with the minimum cost in the selected lane navigation route can be selected as the final selected lane navigation route.

[0136] Among them, the lane navigation route that meets the minimum cost condition in the selected lane navigation route is selected as the lane navigation route, including:

[0137] The cost function is called to calculate the cost value of each selected lane navigation route. The cost function is used to calculate the cost value based on the number of lane changes and the length of lane changes in the lane navigation route.

[0138] The selected lane navigation route corresponding to the minimum value of the cost value is selected as the lane navigation route.

[0139] In the embodiment of the present application, the minimum cost condition is used to represent the route with the minimum cost value in each route.

[0140] In the embodiment of the present application, the cost function can be, for example, a cost function. The cost value can have a correlation with the distance, length and number of lane changes. In the embodiment of the present application, the cost function can include: cost=a*time-b*min(len,10*time). Wherein, cost is the cost value, time is the number of lane changes, len is the length of lane change, and len can be set to have a maximum value, and a and b represent weights respectively. It can be understood that in the present application, the cost function can represent that when the number of switching is consistent, the route with longer switching distance is selected, and if the number of switching is inconsistent, the route with smaller number of switching is selected.

[0141] Based on this, the application embodiment can calculate a route with the minimum value as a lane navigation route.

[0142] In the application embodiment, when planning a navigation route, when the first time calculation is successful and the second time calculation fails, the lane navigation route can be found and added without repeated calculation, which can greatly improve the success rate of the second time calculation at a small calculation cost.

[0143] Corresponding to the foregoing application function implementation method embodiment, the application further provides a navigation route generation device, an electronic device, and corresponding embodiments.

[0144] Figure 6 The application embodiment shows a structural schematic diagram of a navigation route generation device.

[0145] Referring to Figure 6 A navigation route generation device, the device 600 comprises:

[0146] A triggering unit 1 is configured to obtain a triggering instruction when a navigation route is generated for an autonomous vehicle; the triggering instruction is used to indicate that the first time calculation is successful and the second time calculation fails in the process of generating the navigation route;

[0147] A finding unit 2 is configured to find a target road in a road navigation route after the first time calculation according to the triggering instruction; wherein the target road has a lane that allows lane changing;

[0148] A marking unit 3 is configured to generate a lane changing mark for a target lane in the lane of the target road; wherein the target lane allows lane changing;

[0149] A calculation unit 4 is configured to generate a lane navigation route based on at least the starting point and the ending point of the road navigation route and the lane changing mark, so that the lane where the starting point is located is connected to the lane where the ending point is located;

[0150] A generation unit 5 is configured to generate the current navigation route of the vehicle based on the road navigation route and the lane navigation route.

[0151] Optionally, in the finding unit, the generation process of the triggering instruction comprises:

[0152] When the first time calculation is successful, the starting point and the ending point in the road navigation route after the first time calculation are determined when the second time calculation is performed;

[0153] The lanes corresponding to each road in the road navigation route are loaded;

[0154] If the lane where the starting point is located fails to be connected to the lane where the ending point is located through other lanes, a triggering instruction is generated.

[0155] Optionally, the searching unit is specifically configured to:

[0156] determine each road in the road navigation route;

[0157] search for a first road in which a lane that fails to connect the start point and the end point is located when the secondary road calculation fails;

[0158] take the first road as a target road.

[0159] Optionally, the searching unit is specifically configured to:

[0160] determine each road in the road navigation route;

[0161] search for a first road in which a lane that fails to connect the start point and the end point is located when the secondary road calculation fails;

[0162] take a road having a blood relationship with the first road as a second road; the blood relationship is used to represent that each road has a parent-child node relationship and / or an inheritance node relationship;

[0163] take the first road and the second road as target roads.

[0164] Optionally, the marking unit is specifically configured to:

[0165] take a lane in the target road that is not traversed in the secondary road calculation as a target lane;

[0166] generate a lane-changing mark corresponding to the target lane based on lane data corresponding to the target lane; wherein the lane data at least includes first data used to represent whether the target lane can change lanes, second data used to represent a lane-changing direction, and third data used to represent a lane-changing termination position.

[0167] Optionally, the generating unit is specifically configured to:

[0168] determine a start point corresponding to the start point in the target road and an end point corresponding to the end point in the target road;

[0169] determine a position point that can connect a lane in which the start point is located and a lane in which the end point is located based on the lane-changing mark;

[0170] calculate a candidate lane navigation route connecting the start point and the end point according to the position point;

[0171] take one of the candidate lane navigation routes that meets a minimum cost condition as a lane navigation route.

[0172] Optionally, the step of selecting the route meeting the minimum cost condition from the candidate lane navigation routes as the lane navigation route comprises:

[0173] calling a cost function to calculate a cost value of each of the candidate lane navigation routes, wherein the cost function is used to calculate the cost value based on the number of lane changes and the length of lane changes in the lane navigation route;

[0174] selecting the candidate lane navigation route corresponding to the minimum cost value as the lane navigation route.

[0175] The device in the embodiments of the present application can generate the lane changeable mark for the target lane based on the road navigation route after the first time of successful route calculation and before the second time of failed route calculation, which can improve the success rate of the second time of route calculation, and further improve the success rate of the navigation route generation while ensuring the efficiency of the navigation route generation.

[0176] As to the device in the above embodiments, the specific manners in which the modules perform operations have been described in detail in the embodiments of the method, and will not be described in detail here.

[0177] Figure 7 FIG. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application.

[0178] Referring to FIG. 1, Figure 7 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0179] The processor 1020 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0180] The memory 1010 can include various types of storage units such as a system memory, a read-only memory (ROM), and a permanent storage device. Among them, the ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device can be a rewritable storage device. The permanent storage device can be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device employs a mass storage device (e.g., a magnetic or optical disk, a flash memory) as a permanent storage device. In some other embodiments, the permanent storage device can be a removable storage device (e.g., a floppy disk, an optical drive). The system memory can be a readable and writable storage device or a volatile readable and writable storage device such as a dynamic random access memory. The system memory can store some or all of the instructions and data required by the processor during runtime. In addition, the memory 1010 can include a combination of any computer readable storage media, including various types of semiconductor storage chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks and / or optical disks. In some embodiments, the memory 1010 can include a readable and / or writable removable storage device such as a compact disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., an SD card, a min SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer readable storage medium does not include a carrier wave and an instantaneous electronic signal transmitted by wireless or wired transmission.

[0181] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to perform part or all of the above-mentioned methods.

[0182] In addition, the method according to the present application can also be implemented as a computer program or a computer program product, which includes computer program code instructions for performing part or all of the steps of the above-mentioned methods of the present application.

[0183] Alternatively, the present application can also be implemented as a computer readable storage medium (or non-transitory machine readable storage medium or machine readable storage medium) having executable code (or computer program or computer instruction code) stored thereon, which, when executed by a processor of an electronic device (or a server, etc.), causes the processor to perform part or all of the steps of the above-mentioned methods according to the present application.

[0184] Having described various embodiments of the application, it is to be understood that the above description is meant to be illustrative only, and that many modifications and variations of the embodiments described herein are possible. It is therefore to be understood that within the scope of the appended claims, and their equivalents, many alternatives to the embodiments described herein are possible. The selection of terms to be used in the description is not intended to limit the scope of the embodiments described herein, but rather to best explain the principles of the embodiments, practical application, or improvement over the technology in the art, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating navigation routes, characterized in that, include: A trigger command is received when generating navigation routes for autonomous vehicles; The trigger command is used to indicate that during the process of generating a navigation route, one route calculation is successful and the second route calculation fails. According to the triggering command, the target road is searched in the road navigation route after the first successful route calculation; wherein, the target road contains lanes that allow lane changes, and the target road includes the road where the lane that failed to connect the starting point and the ending point when the second route calculation failed; A lane-change marker is generated for the target lanes in the target road; wherein, the target lanes are allowed to change lanes, and the target lanes include lanes in the target road that were not traversed in the secondary road calculation; A lane navigation route is generated based at least on the start and end points of the road navigation route and the lane-change markers, such that the lane where the start point is located is connected to the lane where the end point is located; The vehicle's current navigation route is generated based on the road navigation route and the lane navigation route.

2. The method according to claim 1, characterized in that, The process of generating the trigger command includes: When a route calculation is successful in the first iteration, the starting point and ending point of the road navigation route after the first successful route calculation are determined during the second iteration. Load the lanes corresponding to each road in the road navigation route; If the lane where the starting point is located cannot be connected to the lane where the ending point is located via other lanes, a trigger command is generated.

3. The method according to claim 1, characterized in that, The process of finding the target road in the road navigation route after a successful route calculation includes: Determine each road in the road navigation route; Find the first road containing the lane that failed to connect the start and end points when the secondary route calculation failed; The first road is selected as the target road.

4. The method according to claim 1, characterized in that, The process of finding the target road in the road navigation route after a successful route calculation includes: Determine each road in the road navigation route; Find the first road containing the lane that failed to connect the start and end points when the secondary route calculation failed; Roads that are related to the first road are designated as second roads; the relatedness is used to characterize the parent-child node relationship and / or inheritance node relationship between the roads. The first road and the second road are designated as target roads.

5. The method according to claim 1, characterized in that, The process of generating lane-change markers for the target lanes in the target road includes: The lanes in the target road that were not traversed in the secondary road calculation are taken as the target lanes; Based on the lane data corresponding to the target lane, a lane-change marker corresponding to the target lane is generated; wherein, the lane data includes at least first data for indicating whether the target lane can be changed, second data for indicating the direction of lane change, and third data for indicating the termination position of lane change.

6. The method according to claim 1, characterized in that, The generation of lane navigation routes based at least on the start and end points of the road navigation route and the lane-change markers includes: Determine the first point corresponding to the starting point in the target road and the last point corresponding to the ending point in the target road; Based on the lane-change marker, a position point is determined that allows the lane containing the first point to connect with the lane containing the last point. Calculate the candidate lane navigation route connecting the first and last points based on the location points; The route that meets the minimum cost condition among the candidate lane navigation routes will be selected as the lane navigation route.

7. The method according to claim 6, characterized in that, The step of selecting the route that meets the minimum cost condition from the candidate lane navigation routes as the lane navigation route includes: The cost function is invoked to calculate the cost value of each of the candidate lane navigation routes; wherein, the cost function is used to calculate the cost value based on the number of lane changes and the length of lane changes in the lane navigation route; The lane navigation route corresponding to the minimum cost value is taken as the lane navigation route.

8. A navigation route generation device, characterized in that, include: The triggering unit is used to obtain triggering instructions when generating navigation routes for autonomous vehicles; The trigger command is used to indicate that during the process of generating a navigation route, one route calculation is successful and the second route calculation fails. The search unit is used to search for a target road in the road navigation route after the first successful route calculation, according to the triggering instruction; wherein the target road contains lanes that allow lane changes, and the target road includes the road where the lane that failed to connect the starting point and the ending point when the second route calculation failed; A marking unit is used to generate lane-change markings for target lanes in the lanes of the target road; wherein, the target lanes allow lane changes, and the target lanes include lanes in the target road that were not traversed in the secondary road calculation; A calculation unit is configured to generate a lane navigation route based at least on the start and end points of the road navigation route and the lane-change markers, such that the lane where the start point is located is connected to the lane where the end point is located. The generation unit is used to generate the current navigation route of the vehicle based on the road navigation route and the lane navigation route.

9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-7.

Images