CN116642500A - Lane-level navigation method and system for autonomous driving software-in-the-loop simulation test - Google Patents

Abstract

The invention discloses a lane-level navigation method and system for automatic driving software-in-the-loop simulation testing, relates to the technical field of automatic driving simulation testing, including creating a static map for simulation testing, and obtaining static attributes of the static map after parsing; Set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point; obtain 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, and convert the navigation path Output in reverse order to obtain the recommended navigation path. The present invention can efficiently obtain the best navigation path in a highly realistic simulation test scene, and improves the efficiency and accuracy of the automatic driving simulation test.

Description

Lane-level navigation method and system for autonomous driving software-in-the-loop simulation test

technical field

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

Background technique

In real life, high-precision navigation systems must be used based on high-precision maps and high-precision positioning. If the accuracy of vehicle positioning itself is not high, the effectiveness and reliability of the recommended navigation cannot be guaranteed. In the simulation test environment, if the high-precision navigation used in the real environment is used, the time and cost of the research are often very high, and the implementation method is also very complicated. In the simulation environment, there is no need for a high-precision positioning system as required by the real environment, so it is very necessary to invent a navigation system that is simple, effective, easy to use, and suitable for simulation test accuracy.

The prior art discloses a method and device for generating a recommended navigation route, including: obtaining the current location information of the vehicle and the destination information of the vehicle; Select a navigation path; obtain the electronic map data and vehicle parameters of each alternative navigation path, and judge in turn whether there is a navigation path that can pass through the vehicle according to the electronic map data and vehicle parameters of each alternative navigation path; if the judgment result is existence The navigation path that can pass through the vehicle is provided to the navigation client as the recommended navigation path, so that the navigation client can display the corresponding recommended navigation path. This application is a vehicle navigation method aimed at the real environment, and accurately obtains the best navigation path according to the actual situation of the vehicle and the road; although the best navigation path can be obtained to a certain extent, it needs to rely on high-precision maps and high-precision positioning. The calculation takes a lot of time and cost, and it is not suitable for the simulation environment, and cannot efficiently obtain the best navigation path during the simulation test.

Contents of the invention

In order to overcome the defect that the existing lane-level navigation method used in simulation testing cannot take into account both efficiency and accuracy, the present invention 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 to improve the efficiency and accuracy of autonomous driving simulation tests.

In order to solve the problems of the technologies described above, the technical solution of the present invention is as follows:

The invention provides a lane-level navigation method for automatic driving software-in-the-loop simulation test, comprising:

S1: Create a static map for simulation testing;

S2: Analyzing the static map to obtain static attributes of the static map;

S3: Set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point;

S4: According to the current position of the vehicle and the static attribute of the navigation end point, obtain a navigation path from the navigation end point to the current position of the vehicle;

S5: Outputting the navigation path in reverse order to obtain a recommended navigation path.

Preferably, the static map includes lanes and their connections, roads and their connections, and objects; the connections of the lanes include the preceding lane, the rear driving lane, and the side lane of the current lane; the connections of the roads A road ahead and a road ahead of the current road are included; each said road includes at least one lane.

Preferably, the static attributes of the static map include road number, road number, lane number and lane number.

Preferably, the static attribute of the vehicle's current position is the road number and lane number of the vehicle's current position in the static map, and the static attribute of the navigation end point is the road number and lane number of the navigation end point in the static map.

Preferably, the specific method for obtaining the navigation path from the navigation end point to the current position of the vehicle according to the current position of the vehicle and the static attributes of the navigation end point is as follows:

S4.1: Set the lane number of the navigation end point as the recommended lane number;

S4.2: Based on the connection relationship of the lanes, search whether there is a preceding lane in the lane corresponding to the recommended lane number; if it does not exist, execute step S4.3; if it exists, execute step S4.4;

S4.3: Search whether there is a preceding lane in the side lane of the lane corresponding to the recommended lane number; if not, perform step S4.3 on the remaining side lanes of the lane corresponding to the recommended lane number until the preceding lane is found; otherwise, Execute step S4.4;

S4.4: Determine whether the road number of the preceding lane is the same as the road number of the vehicle's current position; if not, execute step S4.5; otherwise, execute step S4.6;

S4.5: Set the lane number of the preceding lane as the new recommended lane number, and repeat steps S4.2-S4.4 until the road number of the preceding lane is the same as the road number of the vehicle's current position;

S4.6: Save the recommended lane numbers in the order of searching, as the navigation path from the navigation end point to the current position of the vehicle.

The present invention also provides a lane-level navigation system for automatic driving software-in-the-loop simulation test, which is used to realize the above-mentioned navigation method, including:

Map file module for creating static maps for simulation testing;

A map parsing module, configured to parse the static map to obtain static attributes of the static map;

A position acquisition module, configured to set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point;

A pathfinding module, configured to obtain a navigation path from the navigation end point to the current position of the vehicle according to the current position of the vehicle and the static attributes of the navigation end point;

The navigation module is configured to output the navigation path in reverse order to obtain the recommended navigation path.

Preferably, in the map file module, the static map includes lanes and their connections, roads and their connections, and targets; the lanes' connections include the preceding lane, the rear driving lane, and the side lane of the current lane; The connection relationship of the roads includes the previous road and the subsequent road of the current road; each of the roads includes at least one lane.

Preferably, in the map analysis module, the static attributes of the static map include road number, road number, lane number and lane number.

Preferably, in the position acquisition module, the static attribute of the vehicle's current position is the road number and lane number of the vehicle's current position in the static map, and the static attribute of the navigation end point is the road number and lane number of the navigation end point in the static map serial number.

Preferably, in the pathfinding module, according to the current location of the vehicle and the static attributes of the navigation destination, obtaining the navigation path from the navigation destination to the current location of the vehicle specifically includes:

The recommended lane setting unit is used to set the lane number of the navigation end point as the recommended lane number;

The first search unit is used to search whether there is a preceding lane in the lane corresponding to the recommended lane number based on the connection relationship of the lanes; if it does not exist, go to the second search unit; if it exists, go to the discrimination unit;

The second search unit is used to search whether there is a preceding lane in the side lane of the lane corresponding to the recommended lane number; if not, search the preceding lane for the remaining side lanes of the lane corresponding to the recommended lane number until the preceding lane is searched; Otherwise, go to the discrimination unit;

The judging unit is used to judge whether the road number of the preceding lane is the same as the road number of the vehicle's current position; if not, go to the recommended lane updating unit; otherwise, go to the storage unit;

The recommended lane update unit is used to set the lane number of the preceding lane as a new recommended lane number, and return to the first search unit until the road number of the preceding lane is the same as the road number of the vehicle's current position;

The storage unit is used to save 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.

Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

The present invention firstly creates a static map for simulation testing, analyzes 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 current location of the vehicle from the navigation end point to the current location of the vehicle according to the current position of the vehicle and the static attributes of the navigation end point. The navigation path of the position; the navigation path is output in reverse order, that is, the navigation path from the current position of the vehicle to the navigation end point is obtained as the recommended navigation path. The present invention can efficiently obtain the best navigation path in a highly realistic simulation test scene, and improves the efficiency and accuracy of the automatic driving simulation test.

Description of drawings

FIG. 1 is a flow chart of a lane-level navigation method for automatic driving software-in-the-loop simulation test described in Embodiment 1.

Fig. 2 is a flow chart of obtaining the navigation route from the navigation end point to the current position of the vehicle described in Embodiment 2.

FIG. 3 is a schematic simulation diagram of the lane-level navigation method used for the software-in-the-loop simulation test of automatic driving described in Embodiment 2.

FIG. 4 is a schematic structural diagram of a lane-level navigation system used for software-in-the-loop simulation testing of automatic driving described in Embodiment 3.

Detailed ways

The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

In order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

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

The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

Example 1

This embodiment provides a lane-level navigation method for software-in-the-loop simulation testing of automatic driving, as shown in FIG. 1 , including:

S1: Create a static map for simulation testing;

S2: Analyzing the static map to obtain static attributes of the static map;

S3: Set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point;

S4: According to the current position of the vehicle and the static attribute of the navigation end point, obtain a navigation path from the navigation end point to the current position of the vehicle;

S5: Outputting the navigation path in reverse order to obtain a recommended navigation path.

In the specific implementation process, this embodiment first creates a static map for simulation testing, analyzes and obtains the static attributes of the static map; sets the current position of the vehicle and the navigation destination in the static map, and according to the static attributes of the current location of the vehicle and the navigation destination, Obtain the navigation path from the navigation end point to the vehicle's current position; output the navigation path in reverse order, that is, obtain the navigation path from the vehicle's current position to the navigation end point, as the recommended navigation path. This embodiment can efficiently obtain the best navigation path in a highly realistic simulation test scene, improving the efficiency and accuracy of the automatic driving simulation test.

Example 2

This embodiment provides a lane-level navigation method for software-in-the-loop simulation testing of automatic driving, including:

S1: Create a static map for simulation testing; the static map includes lanes and their connections, roads and their connections, and objects; the connections of the lanes include the preceding lane, the rear driving lane, and the side of the current lane Lane; the connection relationship of the road includes the preceding road and the driving road of the current road; each of the roads includes at least one lane; the target is set in the lane;

S2: Analyze the static map to obtain static attributes of the static map; the static attributes of the static map include road numbers, road numbers, lane numbers, and lane numbers;

S3: Set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point; specifically:

In the static map, the two objects are respectively set as the vehicle current position and the navigation end point, and the static attributes of the two objects are respectively used as the static attributes of the vehicle current position and the navigation end point;

The static attribute of the current position of the vehicle is the road number and the lane number of the vehicle's current position in the static map, and the static attribute of the navigation end point is the road number and the lane number of the navigation end point in the static map;

S4: According to the static attribute of the current position of the vehicle and the navigation end point, obtain the navigation path from the navigation end point to the current position of the vehicle; as shown in Figure 2, the specific method is:

S4.1: Set the lane number of the navigation end point as the recommended lane number;

S4.2: Based on the connection relationship of the lanes, search whether there is a preceding lane in the lane corresponding to the recommended lane number; if it does not exist, execute step S4.3; if it exists, execute step S4.4;

S4.3: Search whether there is a preceding lane in the side lane of the lane corresponding to the recommended lane number; if not, perform step S4.3 on the remaining side lanes of the lane corresponding to the recommended lane number until the preceding lane is found; otherwise, Execute step S4.4;

S4.4: Determine whether the road number of the preceding lane is the same as the road number of the vehicle's current position; if not, execute step S4.5; otherwise, execute step S4.6;

S4.5: Set the lane number of the preceding lane as the new recommended lane number, and repeat steps S4.2-S4.4 until the road number of the preceding lane is the same as the road number of the vehicle's current position;

S4.6: Save the recommended lane numbers in the order of search as the navigation path from the navigation end point to the current position of the vehicle;

S5: Outputting the navigation path in reverse order to obtain a recommended navigation path.

In the specific implementation process, this embodiment is based on the standard format of the open format of automatic driving simulation, and uses the simulation scene software VTD (VirtualTestDrive, a complete tool chain for driving simulation applications) to create a static map. The suffix extension of the static map is .xodr, namely A file describing the static scene; by analyzing the static map, extract the lanes, lane connections, roads, road connections and objects; the connections of each lane include the preceding lane, the rear driving lane and the side lane of the current lane, The connection relationship of each road includes the previous road and the subsequent road of the current road. Each road includes at least one lane. The static attributes of the static map include the road number, the number of roads, the number of lanes, and the number of lanes. All the static maps that will be parsed The attributes are stored in the defined first container in order; different targets are created as the vehicle's current position and navigation end point, and the road number and lane number of the vehicle's current position, the road number and lane number of the navigation end point are obtained from the first container;

Use the lane number of the navigation end point as the recommended lane number, and search whether there is a preceding lane in the lane corresponding to the recommended lane number; if it exists, store the recommended lane number in the defined second container; if not, search for the recommended lane number Whether there is a preceding lane in the side lane of the corresponding lane; if it exists, store the lane number of the side lane in the defined second container, otherwise, continue to search whether there is a preceding lane in the remaining side lanes until the preceding lane is found Up to the lane, store the lane number of the side lane with the preceding lane in the second container; judge whether the road number of the preceding lane is the road number of the vehicle’s current position, if not, set the lane number of the preceding lane as New recommended lane numbers, repeat the above steps until the road number of the new preceding lane is the road number of the vehicle's current position, and save each recommended lane in order as a navigation path from the navigation end point to the vehicle's current position; The path is output in reverse order, that is, the navigation path from the current position of the vehicle to the navigation end point is obtained as the recommended navigation path.

As shown in Figure 3, the road number at the navigation end point is 4, the lane number is -1, the road number at the vehicle's current location is 1, and the lane number is -2; set the lane number at the navigation end point as the recommended lane number, and determine whether there is The preceding lane, as can be seen from the figure, there is a preceding lane, the lane number of the preceding lane is -5, and the road number is 3, then the recommended lane number {-1} is saved, because the road number of the preceding lane is different from that of the vehicle The road numbers at the current location are not equal, and the search needs to be continued; set the preceding lane as the new recommended lane number, and judge whether there is a preceding lane. It can be seen from the figure that if there is no preceding lane, then search whether the next lane exists The previous lane; the lane number of the next lane is -4, if there is a previous lane, the lane number of the next lane will be saved as the recommended lane number, which is {-1, -4} at this time; at this time, the new front lane The road number is 2, which is still not equal to the road number of the vehicle’s current position, and the search needs to be continued; use the same method to continue searching until the road number of the previous lane is the same as the road number of the vehicle’s current position, and the final saved recommended lane number is {-1, -4, -3, -3}, that is, the navigation path from the navigation end point to the current position of the vehicle; output the navigation path in reverse order, that is, {-3, -3, -4, -1}, to obtain from The navigation path from the current position of the vehicle to the navigation end point is used as the recommended navigation path.

Example 3

This embodiment provides a lane-level navigation system for software-in-the-loop simulation testing of automatic driving, which is used to implement the navigation method described in Embodiment 1 or 2, as shown in FIG. 4 , including:

Map file module for creating static maps for simulation testing;

A map parsing module, configured to parse the static map to obtain static attributes of the static map;

A position acquisition module, configured to set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point;

A pathfinding module, configured to obtain a navigation path from the navigation end point to the current position of the vehicle according to the current position of the vehicle and the static attributes of the navigation end point;

The navigation module is configured to output the navigation path in reverse order to obtain the recommended navigation path.

In the map analysis module, the static attributes of the static map include road number, road quantity, lane number and lane number.

In the position acquiring module, the static attribute of the vehicle's current position is the road number and the lane number of the vehicle's current position in the static map, and the static attribute of the navigation end point is the road number and the lane number of the navigation end point in the static map.

In the pathfinding module, according to the current position of the vehicle and the static attributes of the navigation end point, obtaining the navigation path from the navigation end point to the current position of the vehicle specifically includes:

The recommended lane setting unit is used to set the lane number of the navigation end point as the recommended lane number;

The first search unit is used to search whether there is a preceding lane in the lane corresponding to the recommended lane number based on the connection relationship of the lanes; if it does not exist, go to the second search unit; if it exists, go to the discrimination unit;

The second search unit is used to search whether there is a preceding lane in the side lane of the lane corresponding to the recommended lane number; if not, search the preceding lane for the remaining side lanes of the lane corresponding to the recommended lane number until the preceding lane is searched; Otherwise, go to the discrimination unit;

The judging unit is used to judge whether the road number of the preceding lane is the same as the road number of the vehicle's current position; if not, go to the recommended lane updating unit; otherwise, go to the storage unit;

The recommended lane update unit is used to set the lane number of the preceding lane as a new recommended lane number, and return to the first search unit until the road number of the preceding lane is the same as the road number of the vehicle's current position;

The storage unit is used to save 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.

The same or similar reference numerals correspond to the same or similar components;

The terms describing the positional relationship in the drawings are only for illustrative purposes and cannot be interpreted as limitations on this patent;

Apparently, the above-mentioned embodiments of the present invention are only examples for clearly illustrating the present invention, rather than limiting the implementation of the present invention. For those of ordinary skill in the art, other changes or changes in different forms can be made on the basis of the above description. It is not necessary and impossible to exhaustively list all the implementation manners here. All modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the claims of the present invention.

Claims (10)

1. A lane-level navigation method for automatic driving software-in-the-loop simulation test, characterized in that, comprising: S1: Create a static map for simulation testing; S2: Analyzing the static map to obtain static attributes of the static map; S3: Set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point; S4: According to the current position of the vehicle and the static attribute of the navigation end point, obtain a navigation path from the navigation end point to the current position of the vehicle; S5: Outputting the navigation path in reverse order to obtain a recommended navigation path. 2. the lane-level navigation method for automatic driving software-in-the-loop simulation test according to claim 1, is characterized in that, described static map comprises lane and connection relation thereof, road and connection relation thereof, object; The connection relationship of the lanes includes the preceding lane, the rear driving lane and the side lane of the current lane; The connection relationship of the road includes the previous road and the subsequent road of the current road; Each of said roads includes at least one lane. 3. The lane-level navigation method for automatic driving software-in-the-loop simulation test according to claim 2, wherein the static attributes of the static map include road number, road quantity, lane number and lane number. 4. The lane-level navigation method for automatic driving software-in-the-loop simulation test according to claim 3, wherein the static attribute of the current position of the vehicle is the road number and the lane number of the current position of the vehicle in the static map , the static attribute of the navigation end point is the road number and lane number of the navigation end point in the static map. 5. The lane-level navigation method for automatic driving software-in-the-loop simulation test according to claim 4, characterized in that, according to the static attribute of the current position of the vehicle and the navigation end point, the vehicle current position from the navigation end point is obtained. The specific method of the navigation path of the location is: S4.1: Set the lane number of the navigation end point as the recommended lane number; S4.2: Based on the connection relationship of the lanes, search whether there is a preceding lane in the lane corresponding to the recommended lane number; if it does not exist, execute step S4.3; if it exists, execute step S4.4; S4.3: Search whether there is a preceding lane in the side lane of the lane corresponding to the recommended lane number; if not, perform step S4.3 on the remaining side lanes of the lane corresponding to the recommended lane number until the preceding lane is found; otherwise, Execute step S4.4; S4.4: Determine whether the road number of the preceding lane is the same as the road number of the vehicle's current position; if not, execute step S4.5; otherwise, execute step S4.6; S4.5: Set the lane number of the preceding lane as the new recommended lane number, and repeat steps S4.2-S4.4 until the road number of the preceding lane is the same as the road number of the vehicle's current position; S4.6: Save the recommended lane numbers in the order of searching, as the navigation path from the navigation end point to the current position of the vehicle. 6. A lane-level navigation system for automatic driving software-in-the-loop simulation testing, for realizing the navigation method described in any one of claims 1-5, characterized in that, comprising: Map file module for creating static maps for simulation testing; A map parsing module, configured to parse the static map to obtain static attributes of the static map; A position acquisition module, configured to set the current position of the vehicle and the navigation end point in the static map, and obtain the static attributes of the current position of the vehicle and the navigation end point; A pathfinding module, configured to obtain a navigation path from the navigation end point to the current position of the vehicle according to the current position of the vehicle and the static attributes of the navigation end point; The navigation module is configured to output the navigation path in reverse order to obtain the recommended navigation path. 7. The lane-level navigation system for automatic driving software-in-the-loop simulation test according to claim 6, characterized in that, in the map file module, the static map includes lanes and their connections, roads and their connections relationship, object The connection relationship of the lanes includes the preceding lane, the rear driving lane and the side lane of the current lane; The connection relationship of the road includes the previous road and the subsequent road of the current road; Each of said roads includes at least one lane. 8. The lane-level navigation system for automatic driving software-in-the-loop simulation test according to claim 7, characterized in that, in the map analysis module, the static attributes of the static map include road number, road quantity, lane number and number of lanes. 9. The lane-level navigation method for automatic driving software-in-the-loop simulation test according to claim 8, characterized in that, in the position acquisition module, the static attribute of the current position of the vehicle is the current position of the vehicle in the static map The road number and the lane number, 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. 10. The lane-level navigation system for automatic driving software-in-the-loop simulation test according to claim 9, characterized in that, in the pathfinding module, according to the static attribute of the current position of the vehicle and the navigation end point, the following information is obtained from The navigation path from the navigation terminal to the current position of the vehicle specifically includes: The recommended lane setting unit is used to set the lane number of the navigation end point as the recommended lane number; The first search unit is used to search whether there is a preceding lane in the lane corresponding to the recommended lane number based on the connection relationship of the lanes; if it does not exist, go to the second search unit; if it exists, go to the discrimination unit; The second search unit is used to search whether there is a preceding lane in the side lane of the lane corresponding to the recommended lane number; if not, search the preceding lane for the remaining side lanes of the lane corresponding to the recommended lane number until the preceding lane is searched; Otherwise, go to the discrimination unit; The judging unit is used to judge whether the road number of the preceding lane is the same as the road number of the vehicle's current position; if not, go to the recommended lane updating unit; otherwise, go to the storage unit; The recommended lane update unit is used to set the lane number of the preceding lane as a new recommended lane number, and return to the first search unit until the road number of the preceding lane is the same as the road number of the vehicle's current position; The storage unit is used to save 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.