TW202340677A - Adaptive navigation method and cloud navigation path and map publishing platform utilizing the same relating to an information processing platform capable of generating adaptive navigation paths and maps in the cloud to assist the accurate operation of the self-driving platform - Google Patents

Abstract

An adaptive navigation method is implemented by a cloud navigation path and map publishing platform, which includes: executing a path planning operation based on the starting point and end point specified by a self-driving platform, wherein the path planning operation includes calculating a global navigation path with the shortest distance, shortest time or lowest energy consumption based on a road network and weights in the stored map information of a high-precision electronic map storage unit, which factors of weights include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes a two-dimensional set consisting of longitude and latitude, a one-dimensional set consisting of altitude information corresponding to the global navigation path, a one-dimensional set consisting of the distance to the stop line ahead and a one-dimensional set consisting of the distance to the end point. The adaptive navigation method further includes reading a SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and performing a gridding process on the SLAM feature map to obtain a grid SLAM feature map; and transmitting the sets of global navigation paths and the grid SLAM feature map to the self-driving platform.

Description

Adaptive navigation method and cloud navigation path and map publishing platform utilizing it

The present invention relates to self-driving platforms or road smart vehicles, and in particular to an information processing platform that can generate adaptive navigation paths and maps in the cloud to assist the accurate operation of the self-driving platform.

Today's self-driving platforms (such as self-driving cars, robots, etc.) or road smart vehicles (such as smart cleaning vehicles and unmanned transportation vehicles) on the ground are mainly based on some sensing components (such as cameras, lidar, etc.). , radar) scans the surrounding environment of the path, uses a positioning element (such as GNSS/INS) to acquire the positioning information of the self-driving platform, and uses a computing platform (Computing Platform) to execute a global path calculation (Global planning) program and a region Path calculation (Local planning) program.

It is worth mentioning that after a traditional self-driving car enters an urban area, its GNSS/INS will reduce its positioning accuracy due to refraction or shielding of satellite signals, thus affecting the driving safety of the self-driving car; while after a robot vehicle enters a room, its GNSS/INS will The INS will also affect the driving safety of the robot because the lack of satellite signals will reduce its positioning accuracy.

In order to solve the above positioning uncertainty problem, the computing platform of a self-driving platform must use GNSS/INS fusion lidar and camera as the relative positioning basis to execute a Simultaneous Localization and Mapping (SLAM) program to improve Positioning reliability. That is, in order to achieve good perception ability, the computing platform must fuse the sensing data of these sensing elements so that the shortcomings of each sensing element can be complemented and the advantages can be multiplied. That is to say, when a self-driving platform is running, it must calculate a large amount of surrounding environment perception data at any time.

From the above, it can be seen that the computing platform of a self-driving platform not only needs to calculate positioning fusion results at any time, but the preprocessed high-precision electronic maps, feature maps and vector maps required by the SLAM technology also occupy a large amount of storage space of the computing platform.

In order to solve the above problems, a novel adaptive navigation method is urgently needed in this field.

The main purpose of the present invention is to disclose an adaptive navigation method, which can calculate a navigation path between two fixed points required by a self-driving platform in the cloud, construct a SLAM feature map corresponding to the navigation path, and convert the navigation path and the SLAM feature map is sent back to the self-driving platform, thereby eliminating the computing and storage burden of the self-driving platform. In other words, the method of the present invention can effectively reduce the computing power and data storage space requirements of a self-driving platform, thereby significantly reducing the Subsequent maintenance costs of the self-driving platform.

Another object of the present invention is to disclose a cloud navigation path and map publishing platform that can effectively reduce the computing power and data storage space requirements of multiple self-driving platforms wirelessly connected to it through the above-mentioned adaptive navigation method, thereby significantly reducing The subsequent maintenance costs of each self-driving platform.

In order to achieve the aforementioned purpose, an adaptive navigation method is proposed, which is implemented by a cloud navigation path and map publishing platform, and includes:

Execute a route planning operation based on the starting point and end point specified by a self-driving platform. The route planning operation includes calculating the shortest distance, shortest time or lowest energy consumption based on the road network and weight in the map information stored in a high-precision electronic map storage unit. A global navigation path, in which the weight factors include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes a two-dimensional set composed of longitude and latitude. The corresponding height information constitutes a one-dimensional set, a one-dimensional set constituted by the distance to the front stop line, and a one-dimensional set constituted by the distance to the end point;

Read the SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and perform a gridding process on the SLAM feature map to obtain a grid SLAM feature map; and

The sets of global navigation paths and the grid SLAM feature map are transmitted to the self-driving platform.

In one embodiment, the adaptive navigation method further includes executing a detour path planning operation to provide at least one regional detour path when an obstacle appears in front of the self-driving platform and requires a detour.

In one embodiment, the detour path planning operation includes:

Receive the current position, heading, and speed information of the self-driving platform and combine it with the lane width, number of lanes, road edge width, road slope, and road regulations in the current driving direction in the map information of the high-precision electronic map storage unit to perform at least Planning of a regional detour path, and then guiding it to converge with the previous path in the global navigation path, where each regional detour path includes a two-dimensional set consisting of longitude and latitude, and is composed of the global navigation path. The height information corresponding to the path constitutes a one-dimensional set, the distance to the front stop line constitutes a one-dimensional set, and the distance to the end point constitutes a one-dimensional set;

Read the SLAM feature maps within the scope of each detour route in the area from the high-precision electronic map storage unit;

Obtain a grid SLAM feature map based on the SLAM feature map; and

Each area detour path and the grid SLAM feature map are sent to the self-driving platform.

In order to achieve the aforementioned objectives, the present invention further proposes a cloud navigation path and map publishing platform that executes an adaptive navigation method, which method includes:

Execute a route planning operation based on the starting point and end point specified by a self-driving platform. The route planning operation includes calculating the shortest distance, shortest time or lowest energy consumption based on the road network and weight in the map information stored in a high-precision electronic map storage unit. A global navigation path, in which the weight factors include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes a two-dimensional set composed of longitude and latitude. The corresponding height information constitutes a one-dimensional set, a one-dimensional set constituted by the distance to the front stop line, and a one-dimensional set constituted by the distance to the end point;

Read the SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and perform a gridding process on the SLAM feature map to obtain a grid SLAM feature map; and

The sets of global navigation paths and the grid SLAM feature map are transmitted to the self-driving platform.

In one embodiment, the adaptive navigation method further includes executing a detour path planning operation to provide at least one regional detour path when an obstacle appears in front of the self-driving platform and requires a detour.

In one embodiment, the detour path planning operation includes:

Receive the current position, heading, and speed information of the self-driving platform and combine it with the lane width, number of lanes, road edge width, road slope, and road regulations in the current driving direction in the map information of the high-precision electronic map storage unit to perform at least Planning of a regional detour path, and then guiding it to converge with the previous path in the global navigation path, where each regional detour path includes a two-dimensional set consisting of longitude and latitude, and is composed of the global navigation path. The height information corresponding to the path constitutes a one-dimensional set, the distance to the front stop line constitutes a one-dimensional set, and the distance to the end point constitutes a one-dimensional set;

Read the SLAM feature maps within the scope of each detour route in the area from the high-precision electronic map storage unit;

Obtain a grid SLAM feature map based on the SLAM feature map; and

Each area detour path and the grid SLAM feature map are sent to the self-driving platform.

In order to enable the review committee to further understand the structure, characteristics and purpose of the present invention, drawings and detailed descriptions of preferred embodiments are attached as follows.

Please refer to FIG. 1 , which illustrates a block diagram of an embodiment of the cloud navigation path and map publishing platform of the present invention. As shown in Figure 1, a navigation route and map publishing platform 100 transmits navigation information to respective driving platforms 110 via a wireless network 10. The navigation route and map publishing platform 100 has a network interface 101 and a central processing unit. 102. A global path calculation module 103, a regional path calculation module 104, a high-precision electronic map storage unit 105 and a grid SLAM feature map storage unit 106.

The network interface 101 is used to communicate with the respective driving platform 110 via the wireless network 10 .

The central processing unit 102 is used to activate the global route calculation module 103 or the regional route calculation module 104 according to the navigation request information received by the network interface 101 to generate a grid based on the map information stored in the high-precision electronic map storage unit 105 The grid SLAM feature map is stored in the grid SLAM feature map storage unit 106, and the packaged data of the grid SLAM feature map is sent to a self-driving platform 110. That is, when a self-driving platform 110 needs navigation information from point A to point B, it only needs to transmit the locations of point A and point B to the navigation route and map publishing platform 100 through the wireless network 10, and the navigation route and map The publishing platform 100 will transmit the route information connecting point A and point B to the self-driving platform 110.

Specifically, the global path calculation module 103 executes a path planning algorithm based on the starting point, halfway point (option), and end point information specified by a self-driving platform 110, such as but not limited to A* or Dijkstra's common path planning algorithm. , to calculate a global navigation path of the shortest distance, the shortest time, the lowest energy consumption and the lane level of the recommended route based on the road network and weights in the map information stored in the high-precision electronic map storage unit 105, where, the global navigation path The navigation path includes: a two-dimensional set consisting of longitude and latitude, altitude information corresponding to the global navigation path (one-dimensional set), the distance to the stop line ahead (one-dimensional set), and the distance to the end point (one-dimensional set). Afterwards, the global path calculation module 103 will form these sets into a vector and send it back to the self-driving platform 110 . Please refer to Figure 2, which is a schematic diagram of the operation of the smart cloud navigation path and map publishing platform in Figure 1 to obtain the global navigation path and grid SLAM feature map of the present invention. As shown in Figure 2, during the process of executing the path planning algorithm, the global path calculation module 103 will determine the starting point, halfway point (option), and end point information specified by a self-driving platform 110 as fixed points; from the high-precision electronic map storage The unit 105 reads the road network information and height information and generates a global route accordingly; reads the SLAM feature map 106a within the scope of the global route from the high-precision electronic map storage unit 105; and obtains a grid based on the SLAM feature map 106a SLAM feature map; and transmit the global path and the grid SLAM feature map to the self-driving platform 110 .

In addition, the regional path calculation module 104 is used to execute a detour path planning algorithm when an obstacle appears in front of a self-driving platform 110 and requires a detour. The detour path planning algorithm includes: receiving information from the self-driving platform 110 The current position, heading, and speed information are combined with the lane width, number of lanes, road edge width, road slope, and road regulations in the current driving direction in the high-precision electronic map to plan multiple regional detours, ultimately leading to the entire area. In the navigation path, the path ahead must be met before driving to continue driving. The road edge is a path for overtaking, and each regional detour path includes: a two-dimensional set composed of longitude and latitude, and each corresponding The height information corresponding to the regional detour path (one-dimensional set), the distance to the stop line in front (one-dimensional set) and the distance to the end point (one-dimensional set). Afterwards, the regional path calculation module 104 will form a vector from these sets and send it back to the self-driving platform 110 . Please refer to Figure 3, which is a schematic diagram of the operation of the smart cloud navigation path and map publishing platform in Figure 1 to obtain the regional detour path and grid SLAM feature map of the present invention. As shown in Figure 3, during the execution of the detour path planning algorithm, the regional path calculation module 104 will determine the current location of a self-driving platform 110 as a fixed point; read road network information from the high-precision electronic map storage unit 105 and altitude information and generate multiple detour paths accordingly; read the SLAM feature maps within the range of these detour paths from the high-precision electronic map storage unit 105; obtain a grid SLAM feature map based on the SLAM feature map; and The detour paths and the grid SLAM feature map are sent to the self-driving platform 110 .

In addition, the grid SLAM feature map is based on the road SLAM features of the global navigation path or regional detour path of a self-driving platform 110, and the data is packaged in M meter x M meter grid units and returned accordingly. transmitted to the self-driving platform 110, where M is a positive real number.

In addition, the high-precision electronic map is mainly stored in the database of the navigation route and map publishing platform 100 in a structured form. The database stores and describes the geometric information of points, lines, and surfaces in different forms. The corresponding attribute relationships are provided for reference by the global path calculation module 103 or the regional path calculation module 104 . In addition, SLAM feature map data that is unstructured or cannot be stored in a form can be stored in the form of an additional identification code (ID).

According to the above description, the present invention discloses an adaptive navigation method. Please refer to FIG. 4 , which illustrates a flow chart of an embodiment of the adaptive navigation method of the present invention, in which the method is implemented by a cloud navigation path and map publishing platform. As shown in Figure 4, the adaptive navigation method includes: executing a path planning operation based on the starting point and end point specified by a self-driving platform. The path planning operation includes relying on a road network in map information stored in a high-precision electronic map storage unit. and weight to calculate a global navigation path with the shortest distance, shortest time or lowest energy consumption. The factors of the weight include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes longitude, A two-dimensional set consisting of latitude, a one-dimensional set consisting of the altitude information corresponding to the global navigation path, a one-dimensional set consisting of the distance to the stop line ahead, and a one-dimensional set consisting of the distance to the end point (step a) ; Read the SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and perform a gridding process on the SLAM feature map to obtain a grid SLAM feature map (step b); and convert the SLAM feature map The sets of global navigation paths and the grid SLAM feature map are sent to the self-driving platform (step c).

In addition, the adaptive navigation method may further include a detour path planning operation to provide at least one regional detour path when an obstacle appears in front of a self-driving platform and requires a detour. The detour path planning operation includes: receiving the The current position, heading, and speed information of the self-driving platform are combined with the lane width, number of lanes, road edge width, road slope, and road regulations in the current driving direction in the map information of the high-precision electronic map storage unit to conduct at least one area The planning of the detour path is then directed to rendezvous with the previous path in the global navigation path, where each regional detour path includes a two-dimensional set composed of longitude and latitude. A one-dimensional set composed of height information, a one-dimensional set composed of the distance to the stop line ahead, and a one-dimensional set composed of the distance to the end point; the detour paths of each area are read from the high-precision electronic map storage unit SLAM feature map within the range; obtain a grid SLAM feature map based on the SLAM feature map; and transmit each area detour route and the grid SLAM feature map to the self-driving platform.

In addition, in order to allow readers to better understand the technical solutions of the present invention, Figures 5 to 7 illustrate various schematic maps generated during the execution of the adaptive navigation method of the present invention, wherein Figure 5 shows the technical solution of the present invention. A schematic diagram of the grid map used; Figure 6a is a structured vector map in the high-precision electronic map used in the present invention; Figure 6b is an expansion and display of the attributes of points, lines, and surfaces in the vector map of Figure 6a Illustrations of lane width and signal lights; and Figure 7 is the global path returned to a self-driving platform by the cloud navigation path and map publishing platform of the present invention (it is a short-distance bus connection case, the outbound journey is a green line, and the return journey is is the red line) and the grid slam feature map it passes through (bright blue background).

Through the design disclosed above, the present invention has the following advantages:

1. The adaptive navigation method of the present invention can calculate a navigation path between two fixed points required by a self-driving platform in the cloud, construct a SLAM feature map corresponding to the navigation path, and combine the navigation path with the SLAM feature map. The data is transmitted back to the self-driving platform, thereby eliminating the computing and storage burden of the self-driving platform. In other words, the method of the present invention can effectively reduce the computing power and data storage space requirements of a self-driving platform, thereby significantly reducing the subsequent maintenance of the self-driving platform. Shipping costs.

2. The cloud navigation route and map publishing platform of the present invention can effectively reduce the computing power and data storage space requirements of multiple self-driving platforms that are wirelessly connected to it through the above-mentioned adaptive navigation method, thereby significantly reducing the subsequent follow-up of each self-driving platform. Maintenance costs.

What is disclosed in this case is a preferred embodiment. Any partial changes or modifications derived from the technical ideas of this case and easily inferred by those familiar with the art will not deviate from the scope of the patent rights of this case.

To sum up, regardless of the purpose, means and effects of this case, it shows that it is completely different from the conventional technology, and that the invention is practical first, and indeed meets the patent requirements for inventions. I sincerely ask the review committee to take a clear look and grant the patent as soon as possible for your benefit. Society is a prayer for the Supreme Being.

10:Wireless network 100: Navigation route and map publishing platform 101:Network interface 102: Central processing unit 103:Global path calculation module 104: Regional path calculation module 105: High-precision electronic map storage unit 106: Grid SLAM feature map storage unit 106a:SLAM feature map 110:Self-driving platform Step a: Execute a route planning operation based on the starting point and end point specified by a self-driving platform. The route planning operation includes calculating the shortest distance, shortest time or weight based on the road network and weight in the map information stored in a high-precision electronic map storage unit. A global navigation path with the lowest energy consumption, in which the weight factors include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes a two-dimensional set composed of longitude and latitude, consisting of the The height information corresponding to the global navigation path constitutes a one-dimensional set, a one-dimensional set constituted by the distance to the stop line ahead, and a one-dimensional set constituted by the distance to the end point. Step b: Read the SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and perform a gridding process on the SLAM feature map to obtain a grid SLAM feature map Step c: Transmit the sets of global navigation paths and the grid SLAM feature map to the self-driving platform

FIG. 1 illustrates a block diagram of an embodiment of the cloud navigation path and map publishing platform of the present invention. Figure 2 is a schematic diagram of the operation of the cloud navigation path and map publishing platform in Figure 1 to obtain the global navigation path and grid SLAM feature map of the present invention. Figure 3 is a schematic diagram of the operation of the cloud navigation path and map publishing platform in Figure 1 to obtain the regional detour path and grid SLAM feature map of the present invention. FIG. 4 illustrates a flow chart of an embodiment of the adaptive navigation method of the present invention. Figure 5 is a schematic diagram of the grid map used in the present invention. Figure 6a is a structured vector map in the high-precision electronic map used in the present invention. Figure 6b is an illustration of expanding the attributes of points, lines, and surfaces in the vector map of Figure 6a and displaying lane widths and traffic lights. Figure 7 shows the global path and the grid slam feature map passed back to a self-driving platform by the cloud navigation path and map publishing platform of the present invention.

Step a: Execute a route planning operation based on the starting point and end point specified by a self-driving platform. The route planning operation includes calculating the shortest distance, shortest time or weight based on the road network and weight in the map information stored in a high-precision electronic map storage unit. A global navigation path with the lowest energy consumption, in which the weight factors include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes a two-dimensional set composed of longitude and latitude, consisting of the The height information corresponding to the global navigation path constitutes a one-dimensional set, a one-dimensional set constituted by the distance to the stop line ahead, and a one-dimensional set constituted by the distance to the end point.

Step b: Read the SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and perform a gridding process on the SLAM feature map to obtain a grid SLAM feature map

Step c: Transmit the sets of global navigation paths and the grid SLAM feature map to the self-driving platform

Claims (6)

An adaptive navigation method is implemented by a cloud navigation path and map publishing platform, which includes: Execute a route planning operation based on the starting point and end point specified by a self-driving platform. The route planning operation includes calculating the shortest distance, shortest time or lowest energy consumption based on the road network and weight in the map information stored in a high-precision electronic map storage unit. A global navigation path, in which the weight factors include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes a two-dimensional set composed of longitude and latitude. The corresponding height information constitutes a one-dimensional set, a one-dimensional set constituted by the distance to the front stop line, and a one-dimensional set constituted by the distance to the end point; Read the SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and perform a gridding process on the SLAM feature map to obtain a grid SLAM feature map; and The sets of global navigation paths and the grid SLAM feature map are transmitted to the self-driving platform. The adaptive navigation method described in item 1 of the patent application further includes executing a detour path planning operation to provide at least one regional detour path when an obstacle appears in front of the self-driving platform and requires a detour. As for the adaptive navigation method described in item 2 of the patent application, the detour path planning operation includes: Receive the current position, heading, and speed information of the self-driving platform and combine it with the lane width, number of lanes, road edge width, road slope, and road regulations in the current driving direction in the map information of the high-precision electronic map storage unit to perform at least Planning of a regional detour path, and then guiding it to converge with the previous path in the global navigation path, where each regional detour path includes a two-dimensional set consisting of longitude and latitude, and is composed of the global navigation path. The height information corresponding to the path constitutes a one-dimensional set, the distance to the front stop line constitutes a one-dimensional set, and the distance to the end point constitutes a one-dimensional set; Read the SLAM feature maps within the scope of each detour route in the area from the high-precision electronic map storage unit; Obtain a grid SLAM feature map based on the SLAM feature map; and Each area detour path and the grid SLAM feature map are sent to the self-driving platform. A cloud navigation path and map publishing platform that implements an adaptive navigation method, which method includes: Execute a route planning operation based on the starting point and end point specified by a self-driving platform. The route planning operation includes calculating the shortest distance, shortest time or lowest energy consumption based on the road network and weight in the map information stored in a high-precision electronic map storage unit. A global navigation path, in which the weight factors include lane width, number of lanes, road edge width, road slope and road regulations. The global navigation path includes a two-dimensional set composed of longitude and latitude. The corresponding height information constitutes a one-dimensional set, a one-dimensional set constituted by the distance to the front stop line, and a one-dimensional set constituted by the distance to the end point; Read the SLAM feature map within the range of the global path from the high-precision electronic map storage unit, and perform a gridding process on the SLAM feature map to obtain a grid SLAM feature map; and The sets of global navigation paths and the grid SLAM feature map are transmitted to the self-driving platform. For example, the cloud navigation path and map publishing platform described in item 4 of the patent application scope, wherein the adaptive navigation method further includes executing a detour path planning calculation to provide a detour when an obstacle appears in front of the self-driving platform and requires a change of lane. At least one area detour. For the cloud navigation path and map publishing platform described in item 5 of the patent application, the detour path planning operation includes: Receive the current position, heading, and speed information of the self-driving platform and combine it with the lane width, number of lanes, road edge width, road slope, and road regulations in the current driving direction in the map information of the high-precision electronic map storage unit to perform at least Planning of a regional detour path, and then guiding it to converge with the previous path in the global navigation path, where each regional detour path includes a two-dimensional set consisting of longitude and latitude, and is composed of the global navigation path. The height information corresponding to the path constitutes a one-dimensional set, the distance to the front stop line constitutes a one-dimensional set, and the distance to the end point constitutes a one-dimensional set; Read the SLAM feature maps within the scope of each detour route in the area from the high-precision electronic map storage unit; Obtain a grid SLAM feature map based on the SLAM feature map; and Each area detour path and the grid SLAM feature map are sent to the self-driving platform.