Lane-level navigation method and system for automated driving software-in-the-loop simulation testing

Abstract

The application discloses a lane-level navigation method and system for automatic driving software-in-loop simulation test, relates to the technical field of automatic driving simulation test, and comprises the following steps: creating a static map for simulation test, and obtaining static attributes of the static map after analysis; setting a current vehicle position and a navigation terminal point in the static map, and obtaining static attributes of the current vehicle position and the navigation terminal point; obtaining a navigation path from the navigation terminal point to the current vehicle position according to the static attributes of the current vehicle position and the navigation terminal point; and outputting the navigation path in reverse order to obtain a recommended navigation path. The application can efficiently obtain the best navigation path in a high-fidelity simulation test scene, and improves the efficiency and accuracy of automatic driving simulation test.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving simulation testing, and more particularly to a lane-level navigation method and system for automatic driving software-in-the-loop simulation testing. BACKGROUND

[0002] In real life, a high-precision navigation system must be used according to high-precision map matching high-precision positioning, and if the vehicle positioning itself is not high in precision, the effectiveness and reliability of the recommended navigation cannot be guaranteed. In a simulation test environment, if the high-precision navigation used in the real environment is applied, the time and cost spent by the research are often very high, and the method implemented is very complex. In a simulation environment, a high-precision positioning system is not required as in the real environment, and therefore it is necessary to invent a simple and effective, convenient to use, and suitable for simulation test precision navigation system.

[0003] The prior art discloses a method and device for generating a recommended navigation path, comprising: obtaining vehicle current position information and vehicle destination information, obtaining a plurality of candidate navigation paths of the vehicle from the current position to the destination according to the vehicle current position information and the destination information; obtaining electronic map data and vehicle parameters of each candidate navigation path, and sequentially judging whether there is a navigation path that can pass through the vehicle according to the electronic map data and the vehicle parameters of each candidate navigation path; if the judgment result is that there is a navigation path that can pass through the vehicle, the navigation path that can pass through the vehicle is provided as a recommended navigation path to a navigation client, so that the navigation client displays the corresponding recommended navigation path. The application is a vehicle navigation method for a real environment, and the best navigation path is accurately obtained according to the actual situation of the vehicle and the road; although the best navigation path can be obtained to some extent, high-precision maps and high-precision positioning are required, the time and cost of calculation are high, it is not suitable for a simulation environment, and the best navigation path cannot be efficiently obtained in simulation testing. SUMMARY

[0004] The present application provides a lane-level navigation method and system for automatic driving software-in-the-loop simulation testing, which can efficiently obtain the best navigation path in a simulation scene and improve the efficiency and accuracy of automatic driving simulation testing, to overcome the defects of the prior art that the lane-level navigation method used in simulation testing cannot balance efficiency and accuracy.

[0005] To solve the above technical problems, the technical solutions of the present application are as follows:

[0006] The present application provides a lane-level navigation method for automatic driving software-in-the-loop simulation testing, comprising:

[0007] S1: creating a static map for simulation testing;

[0008] S2: parsing the static map to obtain static attributes of the static map;

[0009] S3: setting a current vehicle position and a navigation end point in the static map to obtain static attributes of the current vehicle position and the navigation end point;

[0010] S4: obtaining a navigation path from the navigation end point to the current vehicle position according to the static attributes of the current vehicle position and the navigation end point;

[0011] S5: outputting the navigation path in reverse order to obtain a recommended navigation path.

[0012] Preferably, the static map comprises lanes and connection relationships thereof, roads and connection relationships thereof, and objects; the connection relationships of the lanes comprise a preceding lane, a following lane and a side lane of a current lane; the connection relationships of the roads comprise a preceding road and a following road of a current road; each of the roads comprises at least one lane.

[0013] Preferably, the static attributes of the static map comprise road numbers, road quantities, lane numbers and lane quantities.

[0014] Preferably, the static attributes of the current vehicle position are road numbers and lane numbers of the current vehicle position in the static map, and the static attributes of the navigation end point are road numbers and lane numbers of the navigation end point in the static map.

[0015] Preferably, the specific method of obtaining the navigation path from the navigation end point to the current vehicle position according to the static attributes of the current vehicle position and the navigation end point comprises:

[0016] S4.1: setting a lane number of the navigation end point as a recommended lane number;

[0017] S4.2: searching, based on the connection relationships of the lanes, whether a preceding lane exists for the lane corresponding to the recommended lane number; if not, performing step S4.3; if yes, performing step S4.4;

[0018] S4.3: searching whether a preceding lane exists for a side lane of the lane corresponding to the recommended lane number; if not, performing step S4.3 for the remaining side lanes of the lane corresponding to the recommended lane number until a preceding lane is searched; otherwise, performing step S4.4;

[0019] S4.4: judging whether a road number of the preceding lane is the same as a road number of the current vehicle position; if not, performing step S4.5; otherwise, performing step S4.6;

[0020] S4.5: setting the lane number of the previous lane as the new recommended lane number, repeating steps S4.2-S4.4 until the road number of the previous lane is the same as the road number of the current position of the vehicle;

[0021] S4.6: saving the recommended lane number in the order of the search as a navigation path from the navigation end point to the current position of the vehicle.

[0022] The application also provides a lane-level navigation system for automatic driving software in-loop simulation testing, which is used to implement the above navigation method, comprising:

[0023] a map file module for creating a static map for simulation testing;

[0024] a map parsing module for parsing the static map to obtain the static attributes of the static map;

[0025] a position acquisition module for setting the current position of the vehicle and the navigation end point in the static map, and obtaining the static attributes of the current position of the vehicle and the navigation end point;

[0026] a pathfinding module for obtaining a navigation path from the navigation end point to the current position of the vehicle according to the static attributes of the current position of the vehicle and the navigation end point;

[0027] a navigation module for outputting the navigation path in reverse order to obtain a recommended navigation path.

[0028] Preferably, in the map file module, the static map includes lanes and their connection relationships, roads and their connection relationships, and objects; the connection relationships of the lanes include the previous lane, the next lane, and the side lane of the current lane; the connection relationships of the roads include the previous road and the next road of the current road; each road includes at least one lane.

[0029] Preferably, in the map parsing module, the static attributes of the static map include road numbers, road quantities, lane numbers, and lane quantities.

[0030] Preferably, in the position acquisition module, the static attributes of the current position of the vehicle are the road number and the lane number of the current position of the vehicle in the static map, and the static attributes of the navigation end point are the road number and the lane number of the navigation end point in the static map.

[0031] Preferably, in the pathfinding module, obtaining a navigation path from the navigation end point to the current position of the vehicle according to the static attributes of the current position of the vehicle and the navigation end point specifically comprises:

[0032] a recommended lane setting unit for setting the lane number of the navigation end point as the recommended lane number;

[0033] The first searching unit is configured to search whether a previous lane exists for a lane corresponding to the recommended lane number based on a connection relationship of the lane, and if the previous lane does not exist, the process is transferred to the second searching unit, and if the previous lane exists, the process is transferred to the judging unit.

[0034] The second searching unit is configured to search whether a previous lane exists for a lane corresponding to the recommended lane number based on a connection relationship of the lane, and if the previous lane does not exist, the process is transferred to the second searching unit, and if the previous lane exists, the process is transferred to the judging unit.

[0035] The judging unit is configured to judge whether a road number of the previous lane is the same as a road number of a current position of the vehicle, and if the road number of the previous lane is not the same as the road number of the current position of the vehicle, the process is transferred to the recommended lane updating unit, and if the road number of the previous lane is the same as the road number of the current position of the vehicle, the process is transferred to the storage unit.

[0036] The recommended lane updating unit is configured to set the road number of the previous lane as a new recommended lane number, and return to the first searching unit until the road number of the previous lane is the same as the road number of the current position of the vehicle.

[0037] The storage unit is configured to save the recommended lane number in a searching order as a navigation path from a navigation end point to the current position of the vehicle.

[0038] Compared with the prior art, the technical scheme of the present application has the following beneficial effects:

[0039] The present application firstly creates a static map for simulation test, and obtains static attributes of the static map; the current position of the vehicle and the navigation end point are set in the static map, and a navigation path from the navigation end point to the current position of the vehicle is obtained according to the static attributes of the current position of the vehicle and the navigation end point; the navigation path is output in reverse order, that is, a navigation path from the current position of the vehicle to the navigation end point is obtained as a recommended navigation path. The present application can efficiently obtain the best navigation path in a high-fidelity simulation test scene, and improves the efficiency and accuracy of automatic driving simulation test. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A flowchart of a lane-level navigation method for automatic driving software-in-the-loop simulation test described in embodiment 1.

[0041] Figure 2 A flowchart of obtaining a navigation path from a navigation end point to a current position of a vehicle described in embodiment 2.

[0042] Figure 3 A simulation schematic diagram of a lane-level navigation method for automatic driving software-in-the-loop simulation test described in embodiment 2.

[0043] Figure 4A schematic structural diagram of a lane-level navigation system for automatic driving software-in-the-loop simulation test. DETAILED DESCRIPTION

[0044] The drawings are only used for illustrative description and cannot be understood as a limitation of the patent;

[0045] In order to better illustrate the embodiment, some components in the drawings may be omitted, enlarged or reduced, and do not represent the actual size of the product;

[0046] For those skilled in the art, it is understandable that some well-known structures in the drawings and their descriptions may be omitted.

[0047] The technical solutions of the present application will be further described below in combination with the drawings and embodiments.

[0048] Embodiment 1

[0049] The embodiment provides a lane-level navigation method for automatic driving software-in-the-loop simulation test, which comprises: Figure 1 As shown in the figure, comprising:

[0050] S1: creating a static map for simulation test;

[0051] S2: parsing the static map to obtain the static attributes of the static map;

[0052] S3: setting the current position of the vehicle and the navigation end point in the static map, and obtaining the static attributes of the current position of the vehicle and the navigation end point;

[0053] S4: obtaining the navigation path from the navigation end point to the current position of the vehicle according to the static attributes of the current position of the vehicle and the navigation end point;

[0054] S5: outputting the navigation path in reverse order to obtain the recommended navigation path.

[0055] In the specific implementation process, the embodiment first creates a static map for simulation test, parses and obtains the static attributes of the static map; sets the current position of the vehicle and the navigation end point in the static map, and obtains the navigation path from the navigation end point to the current position of the vehicle according to the static attributes of the current position of the vehicle and the navigation end point; output the navigation path in reverse order, that is, obtain the navigation path from the current position of the vehicle to the navigation end point as the recommended navigation path. The embodiment can efficiently obtain the best navigation path in a high-fidelity simulation test scene, and improve the efficiency and accuracy of automatic driving simulation test.

[0056] Embodiment 2

[0057] The embodiment provides a lane-level navigation method for automatic driving software-in-the-loop simulation test, which comprises:

[0058] S1: create a static map for simulation test; the static map comprises lanes and connection relationship thereof, roads and connection relationship thereof, and objects; the connection relationship of the lanes comprises a preceding lane, a following lane and a side lane of a current lane; the connection relationship of the roads comprises a preceding road and a following road of a current road; each of the roads comprises at least one lane; the objects are arranged in the lanes;

[0059] S2: analyze the static map to obtain static attributes of the static map; the static attributes of the static map comprise road numbers, road quantities, lane numbers and lane quantities;

[0060] S3: set a current vehicle position and a navigation terminal point in the static map, and obtain static attributes of the current vehicle position and the navigation terminal point; in particular:

[0061] In the static map, two objects are set as the current vehicle position and the navigation terminal point respectively, and static attributes of the two objects are set as the static attributes of the current vehicle position and the navigation terminal point respectively;

[0062] The static attributes of the current vehicle position are road numbers and lane numbers of the current vehicle position in the static map, and the static attributes of the navigation terminal point are road numbers and lane numbers of the navigation terminal point in the static map;

[0063] S4: obtain a navigation path from the navigation terminal point to the current vehicle position according to the static attributes of the current vehicle position and the navigation terminal point; as shown, the specific method is: Figure 2

[0064] S4.1: set a lane number of the navigation terminal point as a recommended lane number;

[0065] S4.2: search whether a preceding lane exists for a lane corresponding to the recommended lane number based on the connection relationship of the lanes; if not, execute step S4.3; if yes, execute step S4.4;

[0066] S4.3: search whether a preceding lane exists for a side lane of a lane corresponding to the recommended lane number; if not, execute step S4.3 for the remaining side lanes of the lane corresponding to the recommended lane number until a preceding lane is searched; otherwise, execute step S4.4;

[0067] S4.4: judge whether a road number of the preceding lane is same as a road number of the current vehicle position; if not, execute step S4.5; otherwise, execute step S4.6;

[0068] ​S4.5: setting the lane number of the previous lane as the new recommended lane number, repeating steps S4.2-S4.4 until the road number of the previous lane is the same as the road number of the current position of the vehicle;

[0069] S4.6: saving the recommended lane numbers in the order of searching as a navigation path from the navigation end point to the current position of the vehicle;

[0070] S5: outputting the navigation path in reverse order to obtain a recommended navigation path.

[0071] In the specific implementation process, the embodiment is based on the standard format of the autonomous driving simulation open format, and a static map is created by using a simulation scene software VTD (Virtual Test Drive, complete tool chain for driving simulation application). The suffix extension of the static map is.xodr, that is, a file describing a static scene. By parsing the static map, lanes, lane connection relationships, roads, road connection relationships and target objects are extracted. The connection relationship of each lane includes the previous lane, the next lane and the side lane of the current lane. The connection relationship of each road includes the previous road and the next road of the current road. Each road includes at least one lane. The static attributes of the static map include road numbers, road quantities, lane numbers and lane quantities. All the parsed static attributes are stored in a defined first container in order. Different target objects are created as the current position of the vehicle and the navigation end point. The road numbers and lane numbers of the current position of the vehicle and the road numbers and lane numbers of the navigation end point are obtained from the first container.

[0072] The lane number of the navigation end point is taken as a recommended lane number, and it is searched whether the lane corresponding to the recommended lane number has a previous lane. If yes, the recommended lane number is stored in a defined second container. If no, it is searched whether the side lane of the lane corresponding to the recommended lane number has a previous lane. If yes, the lane number of the side lane is stored in the second container. Otherwise, it is continuously searched whether the remaining side lanes have a previous lane until a previous lane is found. The lane number of the side lane having the previous lane is stored in the second container. It is judged whether the road number of the previous lane is the road number of the current position of the vehicle. If no, the lane number of the previous lane is set as a new recommended lane number, and the above steps are repeated until the road number of the new previous lane is the road number of the current position of the vehicle. The recommended lanes are saved in order as a navigation path from the navigation end point to the current position of the vehicle. The navigation path is output in reverse order, that is, a navigation path from the current position of the vehicle to the navigation end point is obtained as a recommended navigation path.

[0073] As Figure 3As shown in the figure, the road number of the navigation end point is 4, the lane number is -1, the road number of the current position of the vehicle is 1, and the lane number is -2; the lane number of the navigation end point is set as the recommended lane number, and it is judged whether there is a predecessor lane, and it can be seen from the figure that there is a predecessor lane, the lane number of the predecessor lane is -5, and the road number is 3, so the recommended lane number {-1} is saved, and since the road number of the predecessor lane is not equal to the road number of the current position of the vehicle, it needs to continue searching; the predecessor lane is set as the new recommended lane number, and it is judged whether there is a predecessor lane, and it can be seen from the figure that there is no predecessor lane, so it is judged whether there is a predecessor lane in the side lane; the lane number of the side lane is -4, and there is a predecessor lane, so the lane number of the side lane is saved as the recommended lane number, which is {-1, -4} at this time; the road number of the new predecessor lane is 2, which is still not equal to the road number of the current position of the vehicle, and it needs to continue searching; the same method is used to continue searching until the road number of the predecessor lane is equal to the road number of the current position of the vehicle, and finally the recommended lane number saved is {-1, -4, -3, -3}, that is, the navigation path from the navigation end point to the current position of the vehicle; the navigation path is output in reverse order, that is, {-3, -3, -4, -1}, and the navigation path from the current position of the vehicle to the navigation end point is obtained as the recommended navigation path.

[0074] Embodiment 3

[0075] The embodiment provides a lane-level navigation system for automatic driving software in-loop simulation test, which is used for implementing the navigation method in the embodiments 1 or 2, and as shown in the figure, comprises: Figure 4 As shown in the figure, it comprises:

[0076] A map file module is configured to create a static map for simulation test.

[0077] A map analysis module is configured to analyze the static map to obtain static attributes of the static map.

[0078] A position acquisition module is configured to set a current position of a vehicle and a navigation end point in the static map, and obtain static attributes of the current position of the vehicle and the navigation end point.

[0079] A path searching module is configured to obtain a navigation path from the navigation end point to the current position of the vehicle according to the static attributes of the current position of the vehicle and the navigation end point.

[0080] A navigation module is configured to output the navigation path in reverse order to obtain a recommended navigation path.

[0081] In the map analysis module, the static attributes of the static map include road numbers, road quantities, lane numbers and lane quantities.

[0082] The static attribute of the current position of the vehicle is a road number and a lane number of the current position of the vehicle in a static map, and the static attribute of the navigation end point is a road number and a lane number of the navigation end point in the static map.

[0083] The navigation path from the navigation end point to the current position of the vehicle is obtained according to the static attributes of the current position of the vehicle and the navigation end point, and specifically includes:

[0084] The lane number of the navigation end point is set as a recommended lane number by a recommended lane setting unit.

[0085] A first searching unit is used to search whether a preceding lane exists for the lane corresponding to the recommended lane number based on the connection relationship of the lanes, and if not, the process goes to a second searching unit, and if yes, the process goes to a judging unit.

[0086] The second searching unit is used to search whether a preceding lane exists for the lane adjacent to the lane corresponding to the recommended lane number, and if not, the remaining adjacent lanes of the lane corresponding to the recommended lane number are searched for the preceding lane until the preceding lane is found, and if yes, the process goes to the judging unit.

[0087] The judging unit is used to judge whether the road number of the preceding lane is the same as the road number of the current position of the vehicle, and if not, the process goes to a recommended lane updating unit, and if yes, the process goes to a storage unit.

[0088] The recommended lane updating unit is used to set the lane number of the preceding lane as a new recommended lane number, and the process returns to the first searching unit until the road number of the preceding lane is the same as the road number of the current position of the vehicle.

[0089] The storage unit is used to save the recommended lane number as the navigation path from the navigation end point to the current position of the vehicle in the searching order.

[0090] The same or similar reference signs correspond to the same or similar components;

[0091] The terms used for describing the position relationship in the drawings are only used for illustrative description, and should not be understood as a limitation on the patent;

[0092] Obviously, the above embodiments of the present application are only examples for clearly illustrating the present application, and are not intended to limit the implementation modes of the present application. Based on the above description, other different forms of changes or variations can be made by those skilled in the art. Here, all the implementation modes are not required or can not be exhausted. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the claims of the present application.

Claims

1. A lane-level navigation method for automated driving software-in-the-loop simulation testing, characterized in that, The method comprises the following steps: S1: creating a static map for simulation test; S2: parsing the static map to obtain static attributes of the static map; S3: setting a current vehicle position and a navigation end point in the static map, and obtaining static attributes of the current vehicle position and the navigation end point; The static attribute of the current vehicle position is a road number and a lane number of the current vehicle position in the static map, and the static attribute of the navigation end point is a road number and a lane number of the navigation end point in the static map; S4: obtaining a navigation path from the navigation end point to the current vehicle position according to the static attributes of the current vehicle position and the navigation end point, and the specific method is as follows: S4.1: setting the lane number of the navigation end point as a recommended lane number; S4.2: searching whether a preceding lane exists for the lane corresponding to the recommended lane number based on a connection relationship of the lane; If not, step S4.3 is executed; If yes, step S4.4 is executed; S4.3: searching whether a preceding lane exists for the lane corresponding to the recommended lane number; if not, step S4.3 is executed for the remaining lanes beside the lane corresponding to the recommended lane number until the preceding lane is searched; otherwise, step S4.4 is executed; S4.4: judging whether the road number of the preceding lane is the same as the road number of the current vehicle position; if not, step S4.5 is executed; otherwise, step S4.6 is executed; S4.5: setting the lane number of the preceding lane as a new recommended lane number, and repeating steps S4.2-S4.4 until the road number of the preceding lane is the same as the road number of the current vehicle position; S4.6: saving the recommended lane numbers in a searched order as the navigation path from the navigation end point to the current vehicle position; S5: outputting the navigation path in a reverse order to obtain a recommended navigation path.

2. The lane-level navigation method for automated driving software-in-the-loop simulation testing of claim 1, wherein, The static map comprises lanes, connection relationships of the lanes, roads, connection relationships of the roads and objects; The connection relationship of the lane comprises a preceding lane, a following lane and a lane beside the current lane; The connection relationship of the road comprises a preceding road and a following road of the current road; Each road comprises at least one lane.

3. The lane-level navigation method for automated driving software-in-the-loop simulation testing of claim 2, wherein, The static attributes of the static map comprise a road number, a road quantity, a lane number and a lane quantity.

4. A lane-level navigation system for automated driving software-in-the-loop simulation testing for implementing the navigation method of any one of claims 1-3, characterized in that, The method comprises the following steps: A map file module is used to create a static map for simulation test; A map parsing module is used to parse the static map to obtain static attributes of the static map; A position obtaining module is used to set a current vehicle position and a navigation end point in the static map, and obtain static attributes of the current vehicle position and the navigation end point; The static attribute of the current vehicle position is a road number and a lane number of the current vehicle position in the static map, and the static attribute of the navigation end point is a road number and a lane number of the navigation end point in the static map; A path searching module is used to obtain a navigation path from the navigation end point to the current vehicle position according to the static attributes of the current vehicle position and the navigation end point, and the specific method comprises the following steps: A recommended lane setting unit is used to set the lane number of the navigation end point as a recommended lane number; The first searching unit is configured to search whether a preceding lane exists for a lane corresponding to the recommended lane number based on a connection relationship of the lane; if not, go to the second searching unit; if yes, go to the judging unit; The second searching unit is configured to search whether a preceding lane exists for a lane beside the lane corresponding to the recommended lane number; if not, search for the preceding lane for the remaining lanes beside the lane corresponding to the recommended lane number until the preceding lane is found; otherwise, go to the judging unit; The judging unit is configured to judge whether a road number of the preceding lane is the same as a road number of a current position of the vehicle; if not, go to the recommended lane updating unit; otherwise, go to the storing unit; The recommended lane updating unit is configured to set the road number of the preceding lane as a new recommended lane number, and return to the first searching unit until the road number of the preceding lane is the same as the road number of the current position of the vehicle; The storing unit is configured to save the recommended lane number in a searching order as a navigation path from a navigation end point to the current position of the vehicle; The navigation module is configured to output the navigation path in a reverse order to obtain a recommended navigation path.

5. The lane-level navigation system for automated driving software-in-the-loop simulation testing of claim 4, wherein, In the map file module, the static map includes lanes and connection relationships thereof, roads and connection relationships thereof, and objects; The connection relationship of the lane includes a preceding lane, a following lane and a lane beside a current lane; The connection relationship of the road includes a preceding road and a following road of a current road; Each of the roads includes at least one lane.

6. The lane-level navigation system for automated driving software-in-the-loop simulation testing of claim 5, wherein, In the map analysis module, the static attribute of the static map includes road numbers, road quantities, lane numbers and lane quantities.

Images