A navigation method and system for an autonomous driving vehicle, and a driving control device

By generating road-level navigation paths using high-precision map data and a breadth-first search algorithm, the problem of frequent lane changes by autonomous vehicles is solved, resulting in smarter and more economical navigation.

CN113532448BActive Publication Date: 2024-11-05GUANGZHOU AUTOMOBILE GROUP CO LTD
View PDF 29 Cites 0 Cited by

Patent Information

Application Number
CN202010287107.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-04-13
Publication Date
2024-11-05
Estimated Expiration
2040-04-13

AI Technical Summary

Technical Problem

Autonomous vehicles frequently change lanes during navigation, which reduces driving economy and comfort, and also results in insufficient intelligence.

Method used

The system uses high-precision map data and a breadth-first search algorithm to generate the optimal travel route. Combined with road topology and lane attributes, it generates a road-level navigation route and controls the vehicle to perform autonomous driving at the road level, avoiding frequent lane changes.

Benefits of technology

It improves the intelligence of autonomous driving, reduces the number of lane changes, and enhances driving economy and comfort.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113532448B_ABST
    Figure CN113532448B_ABST
Patent Text Reader

Abstract

The present invention relates to a navigation method and system of an automatic driving vehicle, and a driving control device thereof. The method comprises: obtaining multiple target positions, wherein the multiple target positions include a starting position and an end position, or a starting position, several passing positions and an end position; obtaining an optimal passage path between the starting position and the end position according to high-precision map data, a breadth-first search algorithm and the multiple target positions; wherein the optimal passage path includes several passage roads; obtaining passage direction information according to a road topological relationship and several passage roads of the optimal passage path; wherein the passage direction information includes the passage direction when the vehicle enters another road from one road when traveling on several passage roads of the optimal passage path; generating a road-level navigation path according to the optimal passage path, the passage direction information and the end position. The implementation of the present invention can improve the intelligence of automatic driving and avoid frequent lane changes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a navigation method and system for an autonomous driving vehicle, and a driving control device. Background Art

[0002] At present, autonomous driving vehicles mainly rely on navigation to provide a global reference waypoint, and then perform local path planning based on the obstacles around the vehicle. After changing lanes, the vehicle still needs to return to the reference path. The lane attributes after changing lanes may be the same as the original lane, and it can pass through the intersection correctly. In this way, autonomous driving will appear to be not smart enough and requires frequent lane changes, which reduces the economy and comfort of vehicle driving. Summary of the invention

[0003] The present invention aims to propose a navigation method and system of an autonomous driving vehicle, and a driving control device, so as to improve the intelligence of autonomous driving and avoid frequent lane changes.

[0004] In a first aspect, an embodiment of the present invention provides a navigation method for an autonomous driving vehicle, the method comprising:

[0005] Acquire multiple target locations, wherein the multiple target locations include a starting location and an end location, or a starting location, a plurality of intermediate locations, and an end location;

[0006] Obtaining an optimal travel path between a starting position and an end position according to high-precision map data, a breadth-first search algorithm, and the plurality of target positions; wherein the optimal travel path includes a plurality of travel roads;

[0007] Obtaining travel direction information according to the road topological relationship and the plurality of travel roads of the optimal travel path; wherein the travel direction information includes the travel direction when the vehicle enters another road from one road when traveling on the plurality of travel roads of the optimal travel path;

[0008] A road-level navigation path is generated according to the optimal travel path, travel direction information and terminal location.

[0009] According to the above method, the optimal path between the starting position and the end position is obtained according to the high-precision map data, the breadth-first search algorithm and the multiple target positions, specifically including:

[0010] Get the road number of each target location;

[0011] Based on high-precision map data, a breadth-first search algorithm is used to perform path search to obtain the optimal path between every two adjacent target positions, and the optimal path between the starting position and the end position is obtained based on the optimal path between every two adjacent target positions; wherein the optimal path between the starting position and the end position includes the road numbers of the roads that are passed in sequence from the starting position to the end position.

[0012] According to the above method, the path search is performed using a breadth-first search algorithm to obtain the optimal path between every two adjacent target locations, specifically including:

[0013] Assuming that two adjacent target positions are the first target position and the second target position, the road number of the road where the first target position is located is used as the first-level tree node of the breadth-first search tree, and the traversal search is performed layer by layer;

[0014] Among them, when traversing and searching all tree nodes of a certain layer, if a tree node N k When the road number corresponding to the second target location is consistent with the road number corresponding to the second target location, the search is stopped and the tree node N is used to k 、Tree node N 0 and determining the optimal travel path by breadth-first search of the tree; if a tree node having the same road number as the second target position is not found after traversing and searching all tree nodes of a certain layer, optimizing all paths corresponding to all tree nodes of the layer by using a preset path optimization algorithm to obtain an optimal searched tree node, and performing a search of the next layer based on the searched tree node;

[0015] The road corresponding to the tree node of the i+1th layer is the forward road of the road corresponding to the optimal searched tree node, and i is greater than 0.

[0016] The road corresponding to the tree node of the i+1th layer is the forward road of the optimal road corresponding to the searched tree node.

[0017] According to the above method, the road topology relationship is generated using the following algorithm:

[0018] Step S1, setting each road to have a number of waypoints, taking the last waypoint information of each road as the road end point, taking the first waypoint information of each road as the road start point, and obtaining the road start points and road end points of all roads;

[0019] Step S2: obtaining a road topological relationship between all roads according to the road starting points and road end points of all roads; the road topological relationship includes the communication direction between each road; wherein:

[0020] Taking any road as the current road, respectively calculating the distance between the end point of the current road and the starting point of other roads;

[0021] Determine whether the distance between the end point of the current road and the starting point of any other road is less than a preset threshold; if so, the road where the starting point of the road is located is a road connected to the current road, and determine the travel direction between the current lane and the road where the starting point of the road is located according to the heading information of the current road; if greater than or equal to the preset threshold, the road where the starting point of the road is located is a road not connected to the current road.

[0022] According to the above method, generating a road-level navigation path according to the optimal travel path, travel direction information and terminal location specifically includes:

[0023] Determine a number of lanes that the vehicle can pass through when exiting each intersection according to the travel direction information and the lane attributes of each lane of each road of the optimal travel path;

[0024] Determine, according to the lane type of each lane of each passable road of the optimal passable path, a number of lanes that are not passable when a vehicle enters another road from one road;

[0025] A road-level navigation path is generated according to the optimal travel path, travel direction information, a number of lanes passable when the vehicle exits each intersection, and a number of lanes not passable when the vehicle enters another road from one road.

[0026] According to the above method, the method further comprises: performing autonomous driving according to the road-level navigation path;

[0027] The autonomous driving specifically includes:

[0028] The vehicle is controlled to pass through several passable roads of the optimal passable path in sequence according to the optimal passable path and the passable direction information, and when the vehicle exits each intersection, any lane among several passable lanes is selected to drive and exit the intersection; when the vehicle enters another road from one road, any lane except several impassable lanes is selected to drive and enter another road.

[0029] In a second aspect, an embodiment of the present invention provides a navigation system for an autonomous driving vehicle, comprising:

[0030] An information acquisition unit, used to acquire a plurality of target positions, wherein the plurality of target positions include a starting position and an end position, or a starting position, a plurality of passing positions and an end position;

[0031] A path search unit, configured to obtain an optimal travel path between a starting position and an end position according to high-precision map data, a breadth-first search algorithm, and the plurality of target positions; wherein the optimal travel path includes a plurality of travel roads;

[0032] a passing direction determining unit, configured to obtain passing direction information according to a road topological relationship and a plurality of passing roads of the optimal passing path; wherein the passing direction information includes a passing direction when a vehicle enters another road from one road when traveling on the plurality of passing roads of the optimal passing path; and

[0033] The navigation path determination unit is used to generate a road-level navigation path according to the optimal travel path, travel direction information and terminal position.

[0034] According to the above system, the path search unit specifically includes:

[0035] A road number acquisition unit, used to acquire a road number of a road where each target location is located; and

[0036] A path optimization unit is used to perform path search based on high-precision map data using a breadth-first search algorithm to obtain an optimal path between every two adjacent target positions, and to obtain an optimal path between a starting position and an end position based on the optimal path between every two adjacent target positions; wherein the optimal path between the starting position and the end position includes the road numbers of the roads that are passed in sequence from the starting position to the end position.

[0037] According to the above system, the path optimization unit is specifically used for:

[0038] Assuming that two adjacent target positions are the first target position and the second target position, the road number of the road where the first target position is located is used as the first-level tree node of the breadth-first search tree, and the traversal search is performed layer by layer;

[0039] Among them, when traversing and searching all tree nodes of a certain layer, if a tree node N k When the road number corresponding to the second target location is consistent with the road number corresponding to the second target location, the search is stopped and the tree node N is used to k 、Tree node N 0 and determining the optimal travel path by breadth-first search of the tree; if a tree node having the same road number as the second target position is not found after traversing and searching all tree nodes of a certain layer, optimizing all paths corresponding to all tree nodes of the layer by using a preset path optimization algorithm to obtain an optimal searched tree node, and performing a search of the next layer based on the searched tree node;

[0040] The road corresponding to the tree node of the i+1th layer is the forward road of the road corresponding to the optimal searched tree node, and i is greater than 0.

[0041] The road corresponding to the tree node at the i+1th layer is the forward road corresponding to the optimal searched tree node.

[0042] According to the above system, the navigation path determination unit specifically includes:

[0043] A first lane determination unit, configured to determine a number of lanes that the vehicle can pass through when exiting each intersection according to the passing direction information and the lane attributes of each lane of each road of the optimal passing path;

[0044] A second lane determination unit is used to determine a number of lanes that are not passable when a vehicle enters another road from one road according to the lane type of each lane of each passable road of the optimal passable path; and

[0045] The navigation path generation unit is used to generate a road-level navigation path according to the optimal travel path, travel direction information, a number of lanes that are passable when the vehicle exits each intersection, and a number of lanes that are not passable when the vehicle enters another road from one road.

[0046] According to the above system, the system also includes an automatic driving unit for automatic driving according to the road-level navigation path; wherein: the automatic driving unit controls the vehicle to pass through several passable roads of the optimal passable path in sequence according to the optimal passable path and the passable direction information, and when the vehicle exits each intersection, the vehicle is controlled to select any lane among several passable lanes to drive out of the intersection; when the vehicle enters another road from one road, the vehicle is controlled to select any lane except several impassable lanes to drive into another road.

[0047] In a third aspect, an embodiment of the present invention proposes a driving control device, comprising: a navigation system according to the above-mentioned autonomous driving vehicle; or, a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the navigation method according to the above-mentioned autonomous driving vehicle.

[0048] The embodiment of the present invention proposes a navigation method and system of an automatic driving vehicle, and a driving control device, which obtains the optimal passage path between each two adjacent target positions according to high-precision map data and multiple target position information input by the user, and further combines them into the optimal passage path between the starting position and the end position; wherein the optimal passage path includes a plurality of passage roads, and the passage direction information is obtained according to the road topological relationship and the plurality of passage roads of the optimal passage path, and finally a road-level navigation path is generated according to the optimal passage path, the passage direction information and the end position; the road-level navigation path is used to control the vehicle to perform automatic driving. The traditional global reference waypoints are limited to a certain lane in the road, while the road-level navigation path of the embodiment of the present invention uses the road as a reference factor during the vehicle driving process, and is not specifically limited to a certain lane of the road. Therefore, the vehicle automatic driving system only needs to drive on the corresponding road. Specifically, based on the obstacle avoidance function of the automatic driving system, local path planning can be performed according to the obstacle situation around the vehicle to realize operations such as obstacle bypassing and lane changing. When the lane attribute after the lane change is the same as the original lane, there is no need to return to the original lane, thereby improving the intelligence of the automatic driving and avoiding frequent lane changes.

[0049] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be embodied by the implementation of the present invention. The objects and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. Of course, it is not necessary to achieve all the advantages described above at the same time for any product or method implementing the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A flowchart of a navigation method for an autonomous driving vehicle according to an embodiment of the present invention is shown.

[0052] Figure 2 Schematic diagram of a breadth-first search tree in one embodiment of the present invention.

[0053] Figure 3 Schematic diagram of lane types in one embodiment of the present invention.

[0054] Figure 4 A schematic structural diagram of a navigation system for an autonomous driving vehicle according to another embodiment of the present invention. DETAILED DESCRIPTION

[0055] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0056] In addition, in order to better illustrate the present invention, numerous specific details are provided in the specific examples below. It should be understood by those skilled in the art that the present invention can also be implemented without certain specific details. In some examples, means well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present invention.

[0057] An embodiment of the present invention provides a navigation method for an autonomous driving vehicle. Figure 1 FIG. 1 is a flowchart of a navigation method for an autonomous driving vehicle according to Embodiment 1. Figure 1 , the method of this embodiment includes the following steps:

[0058] Step S101, obtaining multiple target positions, wherein the multiple target positions include a starting position and an end position, or a starting position, several passing positions and an end position;

[0059] Specifically, before starting the automatic driving, multiple target positions are obtained, and the target positions include at least a starting position and an end position. Optionally, several path positions between the starting position and the end position can be added, wherein the starting position is the current position of the vehicle, the end position is the destination, the starting position, the path position, and the end position are position points on the road, the starting position can be obtained by the vehicle's positioning device, and the path position and the end position are input by the user. It can be understood that when the starting position and the end position are close, it is not meaningful to set the path position, but when the starting position and the end position are far apart, there may be more choices for the path between the starting position and the end position, but some users have their own driving habits and may tend to prefer to take a certain road (for example, fewer traffic lights, no traffic jams, etc.). Therefore, the user sets several path positions, which can actually be understood as narrowing the path range, that is, the user prefers to consider paths passing through certain path positions;

[0060] At the same time, it can also reduce the processing workload of subsequent steps and shorten the time spent on path planning.

[0061] Step S102, obtaining an optimal travel path between a starting position and an end position according to high-precision map data, a breadth-first search algorithm and the plurality of target positions; wherein the optimal travel path includes a plurality of travel roads;

[0062] Step S103, obtaining travel direction information according to the road topological relationship and the plurality of travel roads of the optimal travel path; wherein the travel direction information includes the travel direction when the vehicle enters another road from one road when traveling on the plurality of travel roads of the optimal travel path;

[0063] Specifically, the previous step S102 has obtained several passable roads that the current driving task needs to pass through, but it is necessary to know the relationship between adjacent roads. Therefore, step S103 further determines the relationship between the several passable roads based on the road topological relationship, that is, the direction of travel when entering another passable road from one passable road, for example, turning left through the intersection to enter another passable road, turning right through the intersection to enter another passable road, going straight through the intersection to enter another passable road, making a U-turn through the intersection to enter another passable road, and so on.

[0064] Step S104: Generate a road-level navigation path according to the optimal travel path, travel direction information and destination location.

[0065] Specifically, based on the several roads, travel direction information and terminal positions obtained in the previous steps S101-S103, it can be determined how the vehicle passes through which roads in sequence during the automatic driving process and where it finally arrives. Accordingly, a road-level navigation path can be generated according to the optimal travel path and travel direction information, and output to the driving decision system. The driving decision system is used to control the automatic driving of the vehicle. It can realize automatic driving according to the road-level navigation path, and perform obstacle avoidance, lane change, acceleration, braking and other operations according to the vehicle's surrounding environment, and finally reach the terminal position.

[0066] The road-level navigation path of the embodiment of the present invention takes the road as a reference factor during vehicle driving and is not specifically limited to a certain lane of the road. Therefore, the vehicle automatic driving system only needs to travel on the corresponding road. Specifically, based on the obstacle avoidance function of the automatic driving system, local path planning can be performed according to the obstacles around the vehicle to implement operations such as changing lanes around obstacles. When the lane attributes after changing lanes are the same as the original lane, there is no need to return to the original lane, thereby improving the intelligence of automatic driving and avoiding frequent lane changes.

[0067] In a specific embodiment, the step S102 specifically includes:

[0068] Step S201, obtaining the road number of each target location;

[0069] Step S202: Based on the high-precision map data, a breadth-first search algorithm is used to perform a path search to obtain an optimal path between every two adjacent target positions, and an optimal path between the starting position and the end position is obtained according to the optimal path between every two adjacent target positions;

[0070] The optimal travel path between the starting position and the end position includes the road numbers of the roads that are passed in sequence from the starting position to the end position.

[0071] Specifically, when the target location only has a starting location and an end location, the optimal path between the starting location and the end location is obtained, such as road ①->road ③->road ④->road ②; when the target location includes the starting location, several passing locations and the end location, the optimal path between the two adjacent locations is obtained respectively, and finally integrated to obtain the complete path, such as road ①->road ③->road ④+road ④->road ⑤->road ⑥, which can be understood as a form of dividing into multiple subtasks, and the passing location is located on road ④.

[0072] In a specific embodiment, the step S202 specifically includes:

[0073] Assume that two adjacent target positions are the first target position and the second target position, and use the road number of the road where the first target position is located as the first-level tree node N of the breadth-first search tree. 0 , traverse and search layer by layer;

[0074] The layer-by-layer traversal search specifically includes:

[0075] Step S301, initializing the search layer number i=1;

[0076] Step S302: traverse and search all tree nodes in the i-th layer. If a tree node N is found in the layer, k When the corresponding road number is consistent with the road number corresponding to the second target position, step S304 is entered. If no tree node with the same road number as the second target position is found after traversing and searching all tree nodes of the i-th layer, step S303 is entered. Step S303: optimize all paths corresponding to all tree nodes of the layer using a preset path optimization algorithm to obtain an optimal searched tree node, and search the next layer based on the searched tree node, i.e., let i=i+1, and return to step S302; wherein, the road corresponding to the tree node of the i+1th layer is the forward road of the road corresponding to the optimal searched tree node, and i is greater than 0.

[0077] Step S304: Stop searching and select the node N from the tree. k 、Tree node N 0Specifically, the method of this embodiment stops searching once the target node, that is, the tree node with the same road number as the second target location, is found. It can be seen from the tree structure of the breadth-first search tree that the target tree node N k With the starting tree node N 0 There is a unique tree connection relationship between them, so it can be obtained from tree node N 0 To tree node N k The path is the optimal path.

[0078] Exemplarily, the path optimization algorithm can be represented by a weight function, which can reflect the selection of the optimal path by factors such as length, road conditions, and congestion. For example, the weight function can be set to f = L*α*β*…, where L refers to the road length, α refers to the road condition influencing factor (the better the road condition, the smaller the value), and β refers to the congestion influencing factor (the more severe the congestion, the larger the value). The influencing factor can be set when the high-precision map is collected. For example, the first target position and the second target position correspond to road number ① and road number ② respectively. From the first target position to the second target position, after searching layer by layer by the breadth-first search algorithm, the road number ② is searched in a tree node on the fourth layer, and the search is stopped. The optimal path can be obtained as ①->⑤->⑥->②. For another example, from the optimal path ①->⑤->④->②, it can be seen that the tree nodes corresponding to ⑤ and ⑥ are obtained through the path optimization algorithm. Assuming that the third layer includes tree nodes ④ and ⑥, after traversing and searching all tree nodes in the third layer, the target node ② is not found, then the path optimization is performed. At this time, there are two paths, path 1 is ①->⑤->④, and path 2 is ①->⑤->⑥. The length of the road corresponding to ④ is 1.3km, the road condition impact factor is 0.8, and the congestion impact factor is 0.9. The length of the road corresponding to ⑥ is 0.8km, the road condition impact factor is 0.7, and the congestion impact factor is 1, then:

[0079] The calculated value of path 1 is: 1.3×0.8×0.9=0.936;

[0080] The calculated value of path 2 is: 0.8×0.7×0.9=0.504;

[0081] Comparing the calculated values ​​of path 1 and path 2, it can be seen that the optimal path from the first target location to the second target location should be path 2, that is, the optimal searched tree node is ⑥.

[0082] In a specific embodiment, the road topology relationship is generated using the following algorithm:

[0083] Step S401, set each road to have a number of waypoints, and the waypoints are distributed in order according to the road heading, set the last waypoint information of each road as the road end point, and the first waypoint information of each road as the road starting point, and obtain the road starting points and road end points of all roads;

[0084] Step S402: Obtain the road topological relationship between all roads according to the road starting points and road end points of all roads; the road topological relationship includes the communication direction between each road; wherein:

[0085] Taking any road as the current road, respectively calculating the distance between the end point of the current road and the starting point of other roads;

[0086] Determine whether the distance between the end point of the current road and the starting point of any other road is less than a preset threshold value. If it is less than the preset threshold value, it indicates that the distance between the two roads is very close and meets the condition of a connected road. In this case, the road where the starting point of the road is located is a road connected to the current road, and the travel direction between the current lane and the road where the starting point of the road is located is determined according to the heading information of the current road. If it is greater than or equal to the preset threshold value, it indicates that the distance between the two roads is relatively close and does not meet the condition of a connected road. In this case, the road where the starting point of the road is located is a road not connected to the current road.

[0087] In a specific embodiment, the step S104 specifically includes:

[0088] Step S501, determining a number of lanes that a vehicle can pass through when exiting each intersection according to the travel direction information and the lane attributes of each lane of each road of the optimal travel path;

[0089] Specifically, each lane is provided with a corresponding unique lane number, and the information of the passable lanes in the step is output in the form of lane numbers; wherein the lane attribute indicates whether the lane can go straight, turn left, turn right, or make a U-turn, which can be determined according to the direction of the ground arrow in the lane. For example, when the current road has a dedicated right-turn lane, the vehicle can only enter the rightmost lane when entering the next road.

[0090] Step S502: determining a number of lanes that are inaccessible when a vehicle enters another road from one road according to the lane type of each lane of each passable road of the optimal passable path;

[0091] Specifically, the information of several impassable lanes in the step is also output in the form of lane numbers; among them, Figure 3 As shown, lane types are divided into ordinary lanes, newly added lanes and dead-end lanes; illustratively, when a vehicle passes through an intersection and enters the next road, the vehicle cannot enter the newly added lane of the next road, but can enter the ordinary lane or dead-end lane of the next road.

[0092] Step S503: Generate a road-level navigation path based on the optimal travel path, travel direction information, a number of lanes that are passable when the vehicle exits each intersection, and a number of lanes that are not passable when the vehicle enters another road from one road.

[0093] In a specific embodiment, the method further includes: performing autonomous driving according to the road-level navigation path;

[0094] The autonomous driving specifically includes:

[0095] The vehicle is controlled to pass through several passable roads of the optimal passable path in sequence according to the optimal passable path and the passable direction information, and when the vehicle exits each intersection, any lane among several passable lanes is selected to drive and exit the intersection; when the vehicle enters another road from one road, any lane except several impassable lanes is selected to drive and enter another road.

[0096] In addition, another embodiment of the present invention provides a navigation system for an autonomous driving vehicle, which is used to implement the navigation method for the autonomous driving vehicle described in the above embodiment. Figure 4 , the system of this embodiment includes:

[0097] An information acquisition unit 1 is used to acquire multiple target locations, wherein the multiple target locations include a starting location and an end location, or a starting location, a plurality of passing locations and an end location;

[0098] A path search unit 2, configured to obtain an optimal travel path between a starting position and an end position according to high-precision map data, a breadth-first search algorithm and the plurality of target positions; wherein the optimal travel path includes a plurality of travel roads;

[0099] A travel direction determination unit 3, configured to obtain travel direction information according to a road topological relationship and a plurality of travel roads of the optimal travel path; wherein the travel direction information includes a travel direction when a vehicle enters another road from one road when traveling on the plurality of travel roads of the optimal travel path; and

[0100] The navigation path determination unit 4 is used to generate a road-level navigation path according to the optimal travel path, travel direction information and terminal position.

[0101] In a specific embodiment, the path search unit 2 specifically includes:

[0102] A road number acquisition unit 21 is used to acquire a road number of a road where each target position is located; and

[0103] The path optimization unit 22 is used to perform a path search based on high-precision map data using a breadth-first search algorithm to obtain an optimal path between every two adjacent target positions, and obtain an optimal path between the starting position and the end position based on the optimal path between every two adjacent target positions; wherein the optimal path between the starting position and the end position includes the road numbers of the roads that are passed in sequence from the starting position to the end position.

[0104] In a specific embodiment, the path optimization unit 22 is specifically used for:

[0105] Assuming that two adjacent target positions are the first target position and the second target position, the road number of the road where the first target position is located is used as the first-level tree node of the breadth-first search tree, and the traversal search is performed layer by layer;

[0106] Among them, when traversing and searching all tree nodes of a certain layer, if a tree node N k When the road number corresponding to the second target location is consistent with the road number corresponding to the second target location, the search is stopped and the tree node N is used to k 、Tree node N 0 and determining the optimal travel path by breadth-first search of the tree; if a tree node having the same road number as the second target position is not found after traversing and searching all tree nodes of a certain layer, optimizing all paths corresponding to all tree nodes of the layer by using a preset path optimization algorithm to obtain an optimal searched tree node, and performing a search of the next layer based on the searched tree node;

[0107] The road corresponding to the tree node of the i+1th layer is the forward road of the road corresponding to the optimal searched tree node, and i is greater than 0.

[0108] In a specific embodiment, the navigation path determination unit 4 specifically includes:

[0109] A first lane determination unit 41 is used to determine a number of lanes that the vehicle can pass through when exiting each intersection according to the passing direction information and the lane attributes of each lane of each road of the optimal passing path;

[0110] A second lane determination unit 42 is used to determine a number of lanes that are not passable when a vehicle enters another road from one road according to the lane type of each lane of each passable road of the optimal passable path; and

[0111] The navigation path generation unit 43 is used to generate a road-level navigation path according to the optimal travel path, travel direction information, a number of lanes that are passable when the vehicle exits each intersection, and a number of lanes that are not passable when the vehicle enters another road from one road.

[0112] In a specific embodiment, the system also includes an automatic driving unit 5 for automatic driving according to the road-level navigation path; wherein: the automatic driving unit 5 controls the vehicle to pass through several passable roads of the optimal passable path in sequence according to the optimal passable path and the passable direction information, and when the vehicle exits each intersection, the vehicle is controlled to select any lane among several passable lanes to drive out of the intersection; when the vehicle enters another road from one road, the vehicle is controlled to select any lane except several impassable lanes to drive into another road.

[0113] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] It should be noted that the system described in the above embodiment corresponds to the method described in the above embodiment. Therefore, the undetailed parts of the system described in the above embodiment can be obtained by referring to the contents of the method described in the above embodiment, and will not be repeated here.

[0115] Furthermore, if the navigation system of the autonomous driving vehicle described in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0116] An embodiment of the present invention further proposes a driving control device, comprising: a navigation system for an autonomous driving vehicle according to the above embodiment; or, a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the navigation method for the autonomous driving vehicle according to the above embodiment.

[0117] Of course, the driving control device may also have components such as a wired or wireless network interface, a keyboard, and an input / output interface for input and output. The driving control device may also include other components for realizing the functions of the device, which will not be elaborated here.

[0118] Exemplarily, the computer program may be divided into one or more units, which are stored in the memory and executed by the processor to complete the present invention. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the driving control device.

[0119] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the driving control device, and various interfaces and lines are used to connect various parts of the entire driving control device.

[0120] The memory can be used to store the computer program and / or unit, and the processor realizes various functions of the driving control device by running or executing the computer program and / or unit stored in the memory, and calling the data stored in the memory. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0121] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A navigation method for an autonomous driving vehicle, characterized in that: include: Acquire multiple target locations, wherein the multiple target locations include a starting location and an end location, or a starting location, a plurality of intermediate locations, and an end location; The optimal pass path between the starting position and the end position is obtained according to the high-precision map data, the breadth-first search algorithm and the multiple target positions, wherein the optimal pass path includes a plurality of pass roads; wherein the search for the optimal pass path between each two adjacent target positions includes: assuming that the two adjacent target positions are the first target position and the second target position, the road number of the road where the first target position is located is used as the first-layer tree node N0 of the breadth-first search tree, and a traversal search is performed layer by layer; when all tree nodes of a certain layer are traversed and searched, if a tree node N exists in the layer, k When the road number corresponding to the second target location is consistent with the road number corresponding to the second target location, the search is stopped and the tree node N is used to k , tree node N0 and breadth-first search tree to determine the optimal passage path; if a tree node with the same road number as the second target position is not found after traversing and searching all tree nodes of a certain layer, all paths corresponding to all tree nodes of the layer are optimized using a preset path optimization algorithm to obtain an optimal searched tree node, and the next layer search is performed based on the searched tree node; the road corresponding to the tree node of the i+1th layer is the forward road of the road corresponding to the optimal searched tree node, and i is greater than 0; the optimal passage path includes several passage roads; the passage direction information is obtained according to the road topological relationship and the several passage roads of the optimal passage path; wherein the passage direction information includes the passage direction when the vehicle enters another road from one road when traveling on the several passage roads of the optimal passage path; Generate a road-level navigation path according to the optimal travel path, travel direction information and terminal location; Automatic driving is performed according to the road-level navigation path, including controlling the vehicle to pass through several passable roads of the optimal passable path in sequence according to the optimal passable path and the passable direction information, and when the vehicle exits each intersection, any lane among several passable lanes is selected to drive out of the intersection; when the vehicle enters another road from one road, any lane except several impassable lanes is selected to drive into another road.

2. The navigation method of the autonomous driving vehicle according to claim 1, characterized in that: The optimal travel path between the starting position and the end position includes the road numbers of the roads that are passed in sequence from the starting position to the end position.

3. The navigation method of the autonomous driving vehicle according to claim 1, characterized in that: The road topology relationship is generated using the following algorithm: Step S1, setting each road to have a number of waypoints, taking the last waypoint information of each road as the road end point, taking the first waypoint information of each road as the road start point, and obtaining the road start points and road end points of all roads; Step S2: Obtain the road topological relationship between all roads according to the road starting points and road end points of all roads; the road topological relationship includes the travel directions between the roads; wherein: Taking any road as the current road, respectively calculating the distance between the end point of the current road and the starting point of other roads; Determine whether the distance between the end point of the current road and the starting point of any other road is less than a preset threshold; if so, the road where the starting point of the road is located is a road connected to the current road, and determine the travel direction between the current lane and the road where the starting point of the road is located according to the heading information of the current road; if greater than or equal to the preset threshold, the road where the starting point of the road is located is a road not connected to the current road.

4. The navigation method of the autonomous driving vehicle according to claim 1, characterized in that: Generating a road-level navigation path according to the optimal travel path, travel direction information, and terminal location specifically includes: Determine a number of lanes that the vehicle can pass through when exiting each intersection according to the travel direction information and the lane attributes of each lane of each road of the optimal travel path; Determine, according to the lane type of each lane of each passable road of the optimal passable path, a number of lanes that are not passable when a vehicle enters another road from one road; A road-level navigation path is generated according to the optimal travel path, travel direction information, a number of lanes passable when the vehicle exits each intersection, and a number of lanes not passable when the vehicle enters another road from one road.

5. A navigation system for an autonomous driving vehicle, characterized in that: include: An information acquisition unit, used to acquire a plurality of target positions, wherein the plurality of target positions include a starting position and an end position, or a starting position, a plurality of passing positions and an end position; A path search unit is used to obtain an optimal pass path between a starting position and an end position according to high-precision map data, a breadth-first search algorithm and the multiple target positions, wherein the optimal pass path includes a plurality of pass roads; wherein the search for the optimal pass path between each two adjacent target positions includes: assuming that the two adjacent target positions are a first target position and a second target position, taking the road number of the road where the first target position is located as the first-layer tree node N0 of the breadth-first search tree, and performing a traversal search layer by layer; when traversing and searching all the tree nodes of a certain layer, if a tree node N0 is found to exist in the layer, k When the road number corresponding to the second target location is consistent with the road number corresponding to the second target location, the search is stopped and the tree node N is used to k , tree node N0 and breadth-first search tree to determine the optimal pass path; if a tree node with the same road number as the second target position is not found after traversing and searching all tree nodes of a certain layer, all paths corresponding to all tree nodes of the layer are optimized using a preset path optimization algorithm to obtain an optimal searched tree node, and the next layer is searched based on the searched tree node; the road corresponding to the tree node of the i+1th layer is the forward road of the road corresponding to the optimal searched tree node, i is greater than 0; the optimal pass path includes a number of pass roads; a passing direction determining unit, configured to obtain passing direction information according to a road topological relationship and a plurality of passing roads of the optimal passing path; wherein the passing direction information includes a passing direction when a vehicle enters another road from one road when traveling on the plurality of passing roads of the optimal passing path; and A navigation path determination unit, configured to generate a road-level navigation path according to the optimal travel path, travel direction information, and end point location; The automatic driving unit is used to perform automatic driving according to the road-level navigation path, including controlling the vehicle to pass through several passable roads of the optimal passable path in sequence according to the optimal passable path and the passable direction information, and when the vehicle exits each intersection, controlling the vehicle to select any lane among several passable lanes to drive out of the intersection; when the vehicle enters another road from one road, controlling the vehicle to select any lane except several impassable lanes to drive into another road.

6. The navigation system for an autonomous driving vehicle according to claim 5, characterized in that: The optimal travel path between the starting position and the end position includes the road numbers of the roads that are passed in sequence from the starting position to the end position.

7. The navigation system for an autonomous driving vehicle according to claim 5, characterized in that: The navigation path determination unit specifically includes: A first lane determination unit, configured to determine a number of lanes that the vehicle can pass through when exiting each intersection according to the passing direction information and the lane attributes of each lane of each road of the optimal passing path; A second lane determination unit is used to determine a number of lanes that are not passable when a vehicle enters another road from one road according to the lane type of each lane of each passable road of the optimal passable path; and The navigation path generation unit is used to generate a road-level navigation path according to the optimal travel path, travel direction information, a number of lanes that are passable when the vehicle exits each intersection, and a number of lanes that are not passable when the vehicle enters another road from one road.

8. A driving control device comprising: A navigation system for an autonomous driving vehicle according to any one of claims 1-4; or, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the navigation method for an autonomous driving vehicle according to any one of claims 1-4.

Citation Information

Patent Citations

  • Method and device for determining navigation path

    CN102116635A

  • In-vehicle navigation devices and route guidance methods

    CN102261919A

  • Navigation path programming method and device as well as navigation system

    CN102636177A

  • Method for determining urban road optimal path of automobile by geographic information system

    CN102927990A

  • Navigation method, navigation apparatus and real-time navigation system

    CN104101353A