CN117906593B - Map construction method, terminal device and storage medium - Google Patents
Map construction method, terminal device and storage medium Download PDFInfo
- Publication number
- CN117906593B CN117906593B CN202410309282.7A CN202410309282A CN117906593B CN 117906593 B CN117906593 B CN 117906593B CN 202410309282 A CN202410309282 A CN 202410309282A CN 117906593 B CN117906593 B CN 117906593B
- Authority
- CN
- China
- Prior art keywords
- road boundary
- road
- topology
- point
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 46
- 230000008447 perception Effects 0.000 claims abstract description 60
- 238000000034 method Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims 2
- 230000008569 process Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 235000008694 Humulus lupulus Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3815—Road data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3863—Structures of map data
- G01C21/3867—Geometry of map features, e.g. shape points, polygons or for simplified maps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a map construction method, terminal equipment and a storage medium, wherein the map construction method comprises the following steps: acquiring perception data of a vehicle; acquiring a navigation path based on the sensing data, and generating a plurality of reference points on the navigation path; determining road boundary points corresponding to the reference points respectively based on the reference points and the perception data; and constructing a map containing road topology based on the road boundary points corresponding to the reference points. Based on the scheme of the application, the characteristic of fewer jumps of the navigation path is utilized to generate a stable reference point, and then the map containing road topology is constructed based on the reference point and the perception data, so that the stability of the constructed map is improved.
Description
Technical Field
The present application relates to the field of driving assistance technologies, and in particular, to a map construction method, a terminal device, and a storage medium.
Background
The high-precision map is an electronic map that records road information in detail, and is used for navigation-assisted driving. However, the maintenance cost of the high-precision map is high, and it is difficult to cope with rapid changes in urban environments. Therefore, navigation-assisted driving without a high-precision map is becoming an important development direction. The navigation assisted driving dependence sensing data without the high-precision map directly determines road topology, and further constructs a corresponding map for the intelligent driving downstream program to predict, decide or route plan. But the constructed map has instability problems due to perceived instability and occlusion.
Disclosure of Invention
The application mainly aims to provide a map construction method, terminal equipment and storage medium, and aims to solve the problem that a map constructed by the navigation auxiliary driving technology without a high-precision map is unstable at present.
In order to achieve the above object, the present application provides a map construction method, including:
acquiring perception data of a vehicle;
Acquiring a navigation path based on the perception data, and generating a plurality of datum points on the navigation path;
Determining road boundary points corresponding to the reference points respectively based on the reference points and the perception data;
and constructing a map containing road topology based on the road boundary points corresponding to the reference points.
Optionally, the step of acquiring a navigation path based on the perceived data includes:
acquiring a track to be driven of the vehicle based on the perception data;
and generating a navigation path corresponding to the track to be driven based on a preset interface protocol.
Optionally, the step of acquiring the track to be driven of the vehicle based on the perception data includes:
constructing a road collision constraint based on the perceived data;
constructing a cost function based on a preset navigation path point;
and generating a track to be driven of the vehicle based on a preset A star algorithm, the road collision constraint and the cost function.
Optionally, the step of generating the navigation path corresponding to the track to be driven based on a preset interface protocol includes:
And generating a navigation path corresponding to the track to be driven based on a preset advanced driving assistance system interface specification 2 nd edition of ADASIS-V2 protocol.
Optionally, the step of determining the road boundary points corresponding to the plurality of reference points based on the plurality of reference points and the perception data includes:
determining at least one first side perceived road boundary and at least one second side perceived road boundary based on the perceived data;
And respectively determining a first side road boundary point and a second side road boundary point corresponding to each of the plurality of datum points based on the at least one first side perceived road boundary and the at least one second side perceived road boundary.
Optionally, the step of determining the first side road boundary point and the second side road boundary point corresponding to the plurality of reference points respectively based on the at least one first side perceived road boundary and the at least one second side perceived road boundary includes:
traversing the plurality of reference points, and generating a target normal of the navigation path by taking the target reference points as intersection points aiming at any traversed target reference point;
Constructing a first point set according to the intersection point of the target normal and the at least one first side perception road boundary; constructing a second point set according to the intersection point of the target normal and the at least one second side perception road boundary;
Determining an intersection point of the first point set, which is closest to the track to be driven, as a first side road boundary point corresponding to the target datum point; and determining an intersection point of the second point set, which is closest to the track to be driven, as a second side road boundary point corresponding to the target datum point.
Optionally, the step of constructing a map including a road topology based on the road boundary points corresponding to the reference points includes:
Constructing a first side road boundary topology based on the first side road boundary points corresponding to the reference points; constructing a second side road boundary topology based on the second side road boundary points corresponding to the plurality of reference points respectively;
Constructing the road topology based on the first side road boundary topology and the second side road boundary topology;
And constructing a road level map based on the road topology.
Optionally, the step of constructing the road topology based on the first side road boundary topology and the second side road boundary topology comprises:
Constructing a first segment of a road topology based on the first side road boundary topology and the second side road boundary topology;
constructing a second segment of the road topology based on the navigation path;
And splicing the first road topology section and the second road topology section to obtain the road topology.
The embodiment of the application also provides a terminal device, which comprises a memory, a processor and a map construction program stored on the memory and capable of running on the processor, wherein the map construction program realizes the steps of the map construction method when being executed by the processor.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a map construction program, and the map construction program realizes the steps of the map construction method when being executed by a processor.
The map construction method, the terminal equipment and the storage medium provided by the embodiment of the application acquire the perception data of the vehicle; acquiring a navigation path based on the perception data, and generating a plurality of datum points on the navigation path; determining road boundary points corresponding to the reference points respectively based on the reference points and the perception data; and constructing a map containing road topology based on the road boundary points corresponding to the reference points. Based on the scheme of the application, the characteristic of fewer jumps of the navigation path is utilized to generate a stable reference point, and then the map containing road topology is constructed based on the reference point and the perception data, so that the stability of the constructed map is improved.
Drawings
FIG. 1 is a flow chart of a first exemplary embodiment of a map construction method of the present application;
FIG. 2 is a first view of a construction process involved in the map construction method of the present application;
FIG. 3 is a second view of the construction process involved in the map construction method of the present application;
FIG. 4 is a third view of the construction process involved in the map construction method of the present application;
FIG. 5 is a flowchart of a second exemplary embodiment of a map construction method of the present application;
FIG. 6 is a flowchart of a third exemplary embodiment of a map construction method of the present application;
FIG. 7 is a flowchart of a fourth exemplary embodiment of a map construction method of the present application;
FIG. 8 is a flowchart of a map construction method according to a fifth exemplary embodiment of the present application;
FIG. 9 is a flowchart of a map construction method according to a sixth exemplary embodiment of the present application;
FIG. 10 is a flowchart of a map construction method according to a seventh exemplary embodiment of the present application;
fig. 11 is a flowchart of an eighth exemplary embodiment of the map construction method of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The main solutions of the embodiments of the present application are: acquiring perception data of a vehicle; acquiring a navigation path based on the perception data, and generating a plurality of datum points on the navigation path; determining road boundary points corresponding to the reference points respectively based on the reference points and the perception data; and constructing a map containing road topology based on the road boundary points corresponding to the reference points. Based on the scheme of the application, the characteristic of fewer jumps of the navigation path is utilized to generate a stable reference point, and then the map containing road topology is constructed based on the reference point and the perception data, so that the stability of the constructed map is improved.
Referring to fig. 1, a first embodiment of a map construction method according to the present application provides a flowchart, where the map construction method includes:
Step S10, obtaining perception data of the vehicle.
Specifically, the high-precision map is an electronic map that records road information in detail, and is used for navigation-assisted driving. However, the maintenance cost of the high-precision map is high, and it is difficult to cope with rapid changes in urban environments. Therefore, navigation-assisted driving without a high-precision map is becoming an important development direction. The navigation assisted driving without the high-precision map directly determines road topology according to the perception data, and then a corresponding map is constructed. But the constructed map has instability problems due to perceived instability and occlusion.
In order to solve the above problems, the present embodiment proposes a method for implementing map construction in combination with navigation paths. First, the vehicle according to the present embodiment needs to have an environment sensing capability, for example, the vehicle acquires data of the surrounding environment using various sensing devices (cameras, lidar, millimeter wave radar, etc.) mounted thereon. These sensing devices are capable of sensing information about roads, vehicles, pedestrians, obstacles, etc. around the vehicle. The perception data may include images shot by a camera, intersection point cloud data scanned by a laser radar, object positions detected by millimeter wave radar, and the like. In connection with fig. 2, the perceived data includes the perceived road boundaries shown in fig. 2, which are generally two-dimensional line segments with height attributes based on the perceived determined road edge locations of the vehicle. Further, sensory data of the vehicle is acquired.
Step S20, a navigation path is acquired based on the perception data, and a plurality of datum points are generated on the navigation path.
Specifically, the perceived data is processed and analyzed based on the relevant protocol, so that a road suitable for driving can be identified, and a driving path suitable for the vehicle is planned, namely, a navigation path is obtained. The navigation path generally has a start point and an end point, the start point being the current position or start point of the vehicle, and the end point being the destination of the vehicle, the start point and the end point being formed by line segments.
On the basis of the obtained navigation path, a plurality of reference points need to be further generated on the navigation path. The process of generating a plurality of reference points may be performed based on a preset reference point pitch, that is, the pitch between two adjacent reference points is constant.
Or to generate a number of fiducial points in non-equidistant fashion, in which case a corresponding size of fiducial point spacing needs to be adaptively set for the line segments in the navigation path. In the same line segment in the navigation path, the distance between the datum points is equal; the fiducial point spacing may not be equal within different line segments in the navigation path.
Taking fig. 3 as an example, n reference points are generated at equal intervals B1 to bn in fig. 3, and the n reference points constitute a reference point set B.
Step S30, determining road boundary points corresponding to the plurality of reference points respectively based on the plurality of reference points and the perception data.
In particular, since the navigation path rarely hops between consecutive frames, the navigation path has better stability. While each fiducial is located at a particular location on the navigation path, the fiducial may be considered stable based on the stability of the navigation path.
In an actual scenario, there may be multiple perceived road boundaries on both sides of the navigation path, some of which may not belong to the road on which the vehicle is traveling. For a plurality of perceived road boundaries on either side, a perceived road boundary corresponding to the road from which the vehicle is to travel needs to be determined.
The track to be driven is located in the road on which the vehicle is driven, and the perceived road boundary corresponding to the road on which the vehicle is driven is closest to the track to be driven, so that the perceived road boundaries on two sides of the navigation path can be determined based on the perceived data, and the intersection point on the perceived road boundary closest to the track to be driven is further determined to be the road boundary point corresponding to the datum point. It will be appreciated that for any reference point, the corresponding road boundary points determined correspond to both sides of the road because of the two.
And step S40, constructing a map containing road topology based on the road boundary points corresponding to the reference points.
Specifically, after determining the road boundary points corresponding to the plurality of reference points, the road boundary points belonging to the first side (for example, the left side of the navigation path) among the road boundary points corresponding to the plurality of reference points may be included in the first point set, and the first side road boundary topology may be constructed using the first point set; and incorporating road boundary points belonging to a second side (for example, the right side of the navigation path) among the road boundary points corresponding to the reference points into a second point set, and constructing a second side road boundary topology by using the second point set. Further, a road topology is constructed based on the first side road boundary topology and the second side road boundary topology, and a road level map is constructed based on the road topology.
Taking fig. 4 as an example, it can be seen that there are two perceived road boundaries on both the left and right sides of the navigation path. For the reference points b1 to bn on the navigation path, an intersection point on a perceived road boundary closest to the track to be driven can be determined based on each reference point, and then a road boundary topology of a road on which the vehicle is to drive can be constructed based on the determined intersection point, and the road topology can be constructed based on the road boundary topology. And finally, constructing a road level map by using the road topology.
In one possible implementation, the reference point may cooperate with a cloud to provide real-time navigation services for the vehicle. For example, the current position of the vehicle is obtained, and the plurality of reference points generated based on the navigation path and the current position of the vehicle are uploaded to the cloud. The cloud correspondingly analyzes a plurality of reference points generated based on the navigation path and the current position of the vehicle. If the current position of the vehicle is matched with a specific datum point in the datum points, a navigation instruction can be issued to the vehicle by the cloud. The vehicle receives the navigation instruction and controls the vehicle to run according to the navigation instruction. Thus, the problem that the vehicle is difficult to obtain navigation service in a specific scene can be solved. Especially in some complex road sections, intelligent driving decisions based on perception may not be good, and cloud assisted navigation can well cope with challenges brought by complex road sections.
In this embodiment, the acquired navigation path is fixed and unchanged in each frame without resetting the navigation. The characteristic of fewer hops of the navigation path is utilized to generate a stable datum point. The positions of the front and rear frame datum points in space can be stable and unchanged, and the stability of the constructed map is improved by recording the relative positions of the datum points on the navigation path and further constructing the map containing road topology based on the datum points and the perception data.
Further, referring to fig. 5, a second embodiment of the map construction method of the present application provides a flowchart, based on the embodiment shown in fig. 1, the step of further refining the "obtaining a navigation path based on the perceived data" in step S20 includes:
Step S21, acquiring a track to be driven of the vehicle based on the perception data;
Step S22, generating a navigation path corresponding to the track to be driven based on a preset interface protocol.
In particular, since the perception data provides detailed information of the surrounding environment of the vehicle, including road structures, obstacle positions, etc., it is an important basis for planning a safe and efficient driving path. Therefore, the trajectory to be traveled of the vehicle can be generated based on the perception data and the preset travel trajectory generation algorithm. It can be understood that the road section where the track to be driven is located can be characterized as a road section for representing that the vehicle is driven according to the navigation requirement, and is used as a basis of the navigation path in the subsequent steps.
Further, a proper interface protocol is preset, and the generated track to be driven is converted into a data format conforming to the selected interface protocol. This may involve encoding and packaging information of the track to be travelled to meet the message structure and communication requirements defined by the interface protocol. And then, the converted track to be driven is processed by utilizing an interface protocol, so that a navigation path corresponding to the track to be driven can be generated, and the navigation path is used for guiding the vehicle to safely reach the destination.
Alternatively, the driving track generation algorithm may be selected from an a star (a x) algorithm, a Dijkstra (Dijkstra) algorithm, an RRT (Rapidly-exploring Random Trees, fast explored random tree) algorithm, and the interface protocol may be a communication protocol for vehicle navigation, such as ADASIS-V2 (advanced driving assistance system interface specification version 2), openDRIVE (open driving scene description language), ROS Navigation Stack (ROS navigation stack), and the like.
In this embodiment, the track to be driven is obtained through the sensing data of the surrounding environment of the vehicle. Then, using this trajectory to be traveled, a navigation path of the vehicle is generated according to the interface protocol. The process effectively combines the perception data and the standardized interface protocol, and ensures the accuracy and the reliability of navigation path planning.
Further, referring to fig. 6, a flow chart is provided in a third embodiment of the map construction method according to the present application, based on the embodiment shown in fig. 5, the step S21 of obtaining the trajectory to be driven of the vehicle based on the perceived data further includes:
Step S211, constructing road collision constraint based on the perception data;
Step S212, constructing a cost function based on a preset navigation path point;
Step S213, generating a track to be driven of the vehicle based on a preset A star algorithm, the road collision constraint and the cost function.
Specifically, in order to acquire a trajectory to be traveled of a vehicle, it is first necessary to identify, based on perceived data, an obstacle that may exist on a travel path of the vehicle, such as a vehicle, a pedestrian, road construction, or the like. And then determining an effective area for running the vehicle according to the position of the obstacle and the size of the vehicle, and constructing road collision constraint to avoid collision with the obstacle. Notably, the road collision constraints also meet the requirements of the kinematic constraints.
Further, a cost function is constructed based on preset navigation path points (comprising a starting point and an ending point of vehicle driving), and cost factors of different path segments are defined by the cost function in consideration of factors such as smoothness, safety and efficiency of a vehicle driving path. And weighing each cost factor according to the current position of the vehicle and the target point, and determining the optimal driving path. Further, searching is performed by utilizing a preset A star algorithm and combining road collision constraint and cost function. In the searching process, a track to be driven of the vehicle is generated according to collision constraint and cost function, and the vehicle is ensured to safely and stably drive to a destination.
The above-described a-star algorithm is a heuristic search algorithm for finding the shortest path in a graph or network. It is based on heuristic evaluation functions in the graph, taking into account the already found path length and the estimated distance to the target, to select the most promising path for exploration. By continuously updating the priority queue of the path, the a star algorithm can efficiently find the optimal path from the start point to the end point.
Taking fig. 2,3 and 4 as examples, the track to be driven is obtained by searching based on an A star algorithm, and the track to be driven can meet the requirements of smoothness, safety, efficiency and the like.
In the embodiment, the road collision constraint and the cost function are constructed, and the track to be driven is generated by combining the A-algorithm, so that the safety and the efficiency of the path are ensured. Meanwhile, the track to be driven provides a data basis for the subsequent navigation path planning and road level map construction.
Further, referring to fig. 7, a flowchart is provided in a fourth embodiment of the map construction method according to the present application, based on the embodiment shown in fig. 5, the generating the navigation path corresponding to the track to be driven in step S22 based on the preset interface protocol further includes:
Step S221, generating a navigation path corresponding to the track to be driven based on a preset advanced driving assistance system interface specification 2 nd edition ADAIS-V2 protocol.
Specifically, the ADASIS-V2 (ADVANCED DRIVER ASSISTANCE SYSTEMS INTERFACE Specifications Version, advanced driving assistance system interface specification version 2) protocol is a communication protocol for a vehicle driving assistance system, and defines an interface specification between a vehicle and a map data provider, including a message format, a data exchange manner, and the like, so as to realize functions of vehicle navigation, automatic driving, and the like. The ADASS-V2 protocol promotes effective interaction between the vehicle and the map data through a standardized communication mode, and provides support for vehicle safety and driving experience.
In order to acquire the navigation path, the to-be-driven track obtained based on the perception data can be processed and analyzed based on the ADAIS-V2 protocol, and the navigation path corresponding to the to-be-driven track is generated, so that the navigation path is smooth, safe and efficient, and accurate navigation guidance is provided.
In this embodiment, the process of obtaining the navigation path is only illustrated by using the ADASIS-V2 protocol, and theoretically, as long as there is a related protocol that can process and analyze the track to be driven to generate the navigation path corresponding to the track to be driven, the protocol can be replaced by the ADASIS-V2 protocol in this embodiment, so as to achieve a similar effect.
In the embodiment, the navigation path corresponding to the track to be driven is generated through the ADASS-V2 protocol, so that the standardization and compatibility of path planning are ensured. Meanwhile, on the premise of not resetting navigation, the navigation path obtained based on the ADAIS-V2 protocol is fixed and unchanged in each frame, so that the subsequent reference point generated based on the navigation path can be kept stable.
Further, referring to fig. 8, a fifth embodiment of the map construction method according to the present application provides a flowchart, based on the embodiment shown in fig. 5, for further refinement of "determining road boundary points corresponding to the plurality of reference points based on the plurality of reference points and the sensing data" in step S30, including:
step S31, determining at least one first side perception road boundary and at least one second side perception road boundary based on the perception data;
step S32, determining a first side road boundary point and a second side road boundary point corresponding to each of the plurality of reference points based on the at least one first side perceived road boundary and the at least one second side perceived road boundary.
In particular, in an actual scenario, there may be multiple perceived road boundaries on both sides of the navigation path, some of which may not belong to the road on which the vehicle is traveling. In this case, based on the perception data, at least one first side perceived road boundary and at least one second side perceived road boundary may be determined.
It can be appreciated that the perceived road boundary corresponding to the road on which the vehicle is to travel is closest to the trajectory to be traveled. Therefore, for any reference point, the distance from the track to be driven to at least one first side perceived road boundary can be analyzed based on the reference point, and the intersection point on the first side perceived road boundary closest to the track to be driven is determined to be the first side road boundary point corresponding to the reference point; similarly, the distance from the track to be driven to at least one second side perceived road boundary can be analyzed based on the reference point, and the intersection point on the second side perceived road boundary closest to the track to be driven is determined to be the second side road boundary point corresponding to the reference point. That is, for each reference point, there is a corresponding one of the first side road boundary points and one of the second side road boundary points.
Because the number of the datum points is a plurality of, a traversing mode can be adopted to respectively determine the first side road boundary point and the second side road boundary point corresponding to the datum points, so that the shape and the structure of the road can be accurately described on both sides of the road.
In one possible implementation manner, the jump caused by the change of the front frame and the rear frame can be stably perceived by analyzing the first side road boundary point and the second side road boundary point corresponding to the same datum point of the front frame and the rear frame.
In this embodiment, based on the perceived data and the plurality of reference points, the perceived road boundary corresponding to each reference point is determined, so that a map including road topology can be constructed later, and the stability of the constructed map is effectively improved.
Further, referring to fig. 9, a sixth embodiment of the map construction method according to the present application provides a flowchart, based on the embodiment shown in fig. 8, for further refinement of "determining a first side road boundary point and a second side road boundary point corresponding to each of the plurality of reference points based on the at least one first side perceived road boundary and the at least one second side perceived road boundary" in step S32, including:
step S321, traversing the plurality of datum points, and generating a target normal of the navigation path by taking the target datum point as an intersection point aiming at any traversed target datum point;
Step S322, constructing a first point set according to the intersection point of the target normal line and the at least one first side perception road boundary; constructing a second point set according to the intersection point of the target normal and the at least one second side perception road boundary;
Step S323, determining an intersection point of the first set of points, which is closest to the to-be-driven track, as a first side road boundary point corresponding to the target reference point; and determining an intersection point of the second point set, which is closest to the track to be driven, as a second side road boundary point corresponding to the target datum point.
Specifically, a plurality of reference points are traversed, and for any traversed target reference point, a target normal of the navigation path is generated by taking the target reference point as an intersection point. The target normal line passes through the datum point and is perpendicular to the navigation path, points to the outside of the navigation path and respectively intersects the path to be driven, all first side perception road boundaries and all second side perception road boundaries.
Then, constructing a first point set according to the intersection point of the target normal line and at least one first side perception road boundary; and constructing a second point set according to the intersection point of the target normal line and at least one second side perception road boundary. Determining an intersection point of the first point set, which is closest to the path to be driven, as a first side road boundary point corresponding to the target datum point; and determining an intersection point of the second point set, which is closest to the path to be driven, as a second side road boundary point corresponding to the target datum point. In one possible implementation manner, the distances between each point in the first point set and the second point set and the path to be driven are calculated along the corresponding normal lines.
Taking fig. 4 as an example, for the traversed reference point bx, a normal line of the corresponding navigation path is generated with the reference point bx as an intersection point. Constructing a first point set according to intersection points h1 and h2 of a normal corresponding to the reference point bx and the left perceived road boundary; and constructing a second point set according to intersection points h3 and h4 of the normal corresponding to the reference point bx and the right second side perception road boundary. Then, determining an intersection point of the first point set, which is closest to the path to be driven, as a first side road boundary point corresponding to the reference point bx; and determining an intersection point of the second point set, which is closest to the path to be driven, as a second side road boundary point corresponding to the reference point bx. Due to the adoption of the traversing mode, the first side road boundary point and the second side road boundary point corresponding to the base stations b1 to bn can be obtained finally.
In this embodiment, by traversing the reference points and generating normals of the navigation path, combining the two-side perceived road boundaries to construct a first point set and a second point set corresponding to the reference points, finding out an intersection point corresponding to a road on which the vehicle is to travel from the first point set and the second point set corresponding to the reference points, and using the intersection point as a road boundary point corresponding to the reference points, a stable road-level map is constructed based on the road boundary points corresponding to the reference points, and stability of the constructed map is effectively improved.
Further, referring to fig. 10, a seventh embodiment of the map construction method according to the present application provides a flowchart, based on the embodiment shown in fig. 8, for further refinement of the map comprising road topology "based on the road boundary points corresponding to the plurality of reference points in step S40, which includes:
Step S41, constructing a first side road boundary topology based on the first side road boundary points corresponding to the reference points; constructing a second side road boundary topology based on the second side road boundary points corresponding to the plurality of reference points respectively;
step S42, constructing the road topology based on the first side road boundary topology and the second side road boundary topology;
step S43, constructing a road grade map based on the road topology.
Specifically, according to the sequence of the plurality of reference points, the first side road boundary points corresponding to the plurality of reference points are connected, so that a first side road boundary topology can be constructed; and connecting the second side road boundary points corresponding to the reference points according to the sequence of the reference points, so as to construct a second side road boundary topology.
Further, a road topology may be constructed using the first side road boundary topology and the second side road boundary topology. A road level map can then be constructed using the road topology. It will be appreciated that the road level map contains a road topology corresponding to the road on which the vehicle is to travel.
In the embodiment, the road boundary topologies at two sides are constructed based on the road boundary points corresponding to the reference points, and the road topologies are constructed by combining the road boundary topologies at two sides, so that the road structure can be completely described, and the reliability and consistency of the map are improved. And finally, constructing a road grade map based on the road topology, so that the road grade map has higher stability.
Further, referring to fig. 11, an eighth embodiment of the map construction method of the present application provides a flowchart, based on the embodiment shown in fig. 10, for further refinement of "constructing the road topology based on the first side road boundary topology and the second side road boundary topology" in step S42, including:
Step S421, constructing a first segment of the road topology based on the first side road boundary topology and the second side road boundary topology;
step S422, constructing a second road topology segment based on the navigation path;
Step S423, splicing the first road topology segment and the second road topology segment to obtain the road topology.
In particular, the navigation auxiliary driving technology without a high-precision map at present has larger dependence on perception data, and cannot provide road topology information with beyond-the-horizon. In order to realize navigation assisted driving without a high-precision map, the embodiment uses the navigation path obtained by the embodiment, and constructs a first road topology segment by using a first side road boundary topology and a second side road boundary topology determined based on the perception data and the reference point.
Then, a second segment of the road topology is constructed using the navigation path. The process firstly needs to acquire standard-definition map road topology information after a first road topology segment, generates a plurality of beyond-view distance reference points on a navigation path after the first road topology segment, determines a first side road boundary point and a second side road boundary point which correspond to the beyond-view distance reference points respectively in a similar manner in a sixth embodiment of the application, and constructs a second road topology segment based on the first side road boundary point and the second side road boundary point which correspond to the beyond-view distance reference points respectively. And finally, splicing the first road topology section and the second road topology section to construct the road topology.
In the embodiment, the first subsection of the road topology is determined based on the perception data, so that the accuracy is high; the second road topology segment is determined based on the road topology information of the standard precise map, has lower precision compared with the first road topology segment, and has higher reference significance in the beyond-the-horizon road section where the perception data are difficult to acquire. The road topology is constructed by utilizing the first road topology section and the second road topology section, and due to the existence of the second road topology section, the problem of beyond-sight distance can be solved to a certain extent for navigation assisted driving, and the accuracy and the reliability of the prediction, decision and path planning of the downstream intelligent driving program are improved.
In addition, the embodiment of the application also provides a terminal device, which comprises a memory, a processor and a map construction program stored on the memory and capable of running on the processor, wherein the map construction program realizes the steps of the map construction method when being executed by the processor.
Because the local map building program is executed by the processor and adopts all the technical schemes of all the embodiments, the local map building program has at least all the beneficial effects brought by all the technical schemes of all the embodiments and is not described in detail herein.
In addition, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a map construction program, and the map construction program realizes the steps of the map construction method when being executed by a processor.
Because the local map building program is executed by the processor and adopts all the technical schemes of all the embodiments, the local map building program has at least all the beneficial effects brought by all the technical schemes of all the embodiments and is not described in detail herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to perform the method of each embodiment of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (9)
1. A map construction method, characterized in that the map construction method comprises:
acquiring perception data of a vehicle;
Acquiring a navigation path and a track to be driven of the vehicle based on the perception data, and generating a plurality of datum points on the navigation path;
Determining road boundary points corresponding to the reference points respectively based on the reference points and the perception data, wherein the perception data is used for determining at least one first side perception road boundary and at least one second side perception road boundary, the road boundary points comprise a first side road boundary point and a second side road boundary point, and the step of determining the first side road boundary point and the second side road boundary point based on the at least one first side perception road boundary and the at least one second side perception road boundary comprises the following steps:
traversing the plurality of reference points, and generating a target normal of the navigation path by taking the target reference points as intersection points aiming at any traversed target reference point;
Constructing a first point set according to the intersection point of the target normal and the at least one first side perception road boundary; constructing a second point set according to the intersection point of the target normal and the at least one second side perception road boundary;
Determining an intersection point of the first point set, which is closest to the track to be driven, as a first side road boundary point corresponding to the target datum point; determining an intersection point of the second point set, which is closest to the track to be driven, as a second side road boundary point corresponding to the target datum point;
and constructing a map containing road topology based on the road boundary points corresponding to the reference points.
2. The map construction method according to claim 1, wherein the step of acquiring a navigation path based on the perceived data comprises:
acquiring a track to be driven of the vehicle based on the perception data;
and generating a navigation path corresponding to the track to be driven based on a preset interface protocol.
3. The map construction method according to claim 2, wherein the step of acquiring the trajectory to be traveled of the vehicle based on the perception data includes:
constructing a road collision constraint based on the perceived data;
constructing a cost function based on a preset navigation path point;
and generating a track to be driven of the vehicle based on a preset A star algorithm, the road collision constraint and the cost function.
4. The map construction method according to claim 2, wherein the step of generating the navigation path corresponding to the trajectory to be traveled based on a preset interface protocol includes:
And generating a navigation path corresponding to the track to be driven based on a preset advanced driving assistance system interface specification 2 nd edition of ADASIS-V2 protocol.
5. The map construction method according to claim 2, wherein the step of determining road boundary points to which the plurality of reference points each correspond based on the plurality of reference points and the perception data includes:
determining at least one first side perceived road boundary and at least one second side perceived road boundary based on the perceived data;
And respectively determining a first side road boundary point and a second side road boundary point corresponding to each of the plurality of datum points based on the at least one first side perceived road boundary and the at least one second side perceived road boundary.
6. The map construction method according to claim 5, wherein the step of constructing a map including a road topology based on the road boundary points to which the plurality of reference points correspond respectively includes:
Constructing a first side road boundary topology based on the first side road boundary points corresponding to the reference points; constructing a second side road boundary topology based on the second side road boundary points corresponding to the plurality of reference points respectively;
Constructing the road topology based on the first side road boundary topology and the second side road boundary topology;
And constructing a road level map based on the road topology.
7. The map construction method of claim 6, wherein the step of constructing the road topology based on the first side road boundary topology and the second side road boundary topology comprises:
Constructing a first segment of a road topology based on the first side road boundary topology and the second side road boundary topology;
constructing a second segment of the road topology based on the navigation path;
And splicing the first road topology section and the second road topology section to obtain the road topology.
8. A terminal device, characterized in that it comprises a memory, a processor and a mapping program stored on the memory and executable on the processor, which mapping program, when executed by the processor, implements the steps of the mapping method according to any of claims 1-7.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a mapping program which, when executed by a processor, implements the steps of the mapping method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309282.7A CN117906593B (en) | 2024-03-19 | 2024-03-19 | Map construction method, terminal device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309282.7A CN117906593B (en) | 2024-03-19 | 2024-03-19 | Map construction method, terminal device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117906593A CN117906593A (en) | 2024-04-19 |
| CN117906593B true CN117906593B (en) | 2024-08-09 |
Family
ID=90694125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410309282.7A Active CN117906593B (en) | 2024-03-19 | 2024-03-19 | Map construction method, terminal device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117906593B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114894206A (en) * | 2022-03-18 | 2022-08-12 | 北京智行者科技有限公司 | Path planning method and device, vehicle, storage medium |
| CN116734828A (en) * | 2023-04-12 | 2023-09-12 | 高德软件有限公司 | Determination of road topology information, electronic map data processing method and electronic equipment |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2530433B1 (en) * | 2011-06-01 | 2015-04-22 | Harman Becker Automotive Systems GmbH | Method of generating a database for a navigation device |
| JP6529463B2 (en) * | 2016-06-14 | 2019-06-12 | 日本電信電話株式会社 | Road structuring device, road structuring method, and road structuring program |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
| CN110599570B (en) * | 2019-09-17 | 2022-09-20 | 武汉中海庭数据技术有限公司 | Map generation method and system based on crowdsourcing data open scene |
| CN113532456B (en) * | 2020-04-21 | 2025-01-07 | 百度在线网络技术（北京）有限公司 | Method and device for generating navigation route |
| CN111982143B (en) * | 2020-08-11 | 2024-01-19 | 北京汽车研究总院有限公司 | Vehicle and vehicle path planning method and device |
| CN112328718B (en) * | 2020-10-31 | 2022-05-17 | 武汉中海庭数据技术有限公司 | Road topology construction system and method based on vehicle dynamic trajectory tracking |
| CN112985444B (en) * | 2021-03-31 | 2023-03-24 | 上海商汤临港智能科技有限公司 | Method and device for constructing navigation elements in map |
| CN115406453A (en) * | 2021-05-27 | 2022-11-29 | 阿里巴巴新加坡控股有限公司 | Navigation method, device and computer storage medium |
| CN114419145B (en) * | 2022-03-29 | 2022-07-01 | 腾讯科技（深圳）有限公司 | Road element labeling method, device, equipment and storage medium |
| CN117664156A (en) * | 2022-08-23 | 2024-03-08 | 北京初速度科技有限公司 | Path planning method, device, equipment, medium and vehicle |
| CN117664157A (en) * | 2022-08-23 | 2024-03-08 | 北京初速度科技有限公司 | Determination method, device, equipment, medium and vehicle of high-precision navigation path |
| CN116576874A (en) * | 2023-04-28 | 2023-08-11 | 重庆长安汽车股份有限公司 | Vehicle driving path optimization method and device, electronic equipment and storage medium |
| CN117091617A (en) * | 2023-08-21 | 2023-11-21 | 重庆长安汽车股份有限公司 | Path planning method, device, equipment and storage medium based on passable area |
| CN117029861A (en) * | 2023-08-28 | 2023-11-10 | 中国人民解放军陆军军事交通学院镇江校区 | Global path planning method, device, system and storage medium |
| CN116817957B (en) * | 2023-08-28 | 2023-11-07 | 无锡科技职业学院 | Unmanned vehicle driving path planning method and system based on machine vision |
| CN117109623B (en) * | 2023-10-09 | 2024-09-13 | 深圳市微克科技股份有限公司 | Intelligent wearable navigation interaction method, system and medium |
| CN117387646A (en) * | 2023-10-18 | 2024-01-12 | 华人运通(上海)自动驾驶科技有限公司 | Cloud-based path planning method, device, system, equipment and storage medium |
-
2024
- 2024-03-19 CN CN202410309282.7A patent/CN117906593B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114894206A (en) * | 2022-03-18 | 2022-08-12 | 北京智行者科技有限公司 | Path planning method and device, vehicle, storage medium |
| CN116734828A (en) * | 2023-04-12 | 2023-09-12 | 高德软件有限公司 | Determination of road topology information, electronic map data processing method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117906593A (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111750886B (en) | Local path planning method and device | |
| CN111857160B (en) | Unmanned vehicle path planning method and device | |
| CN112880693B (en) | Map generation method, positioning method, device, equipment and storage medium | |
| CN107851125B (en) | System and method for two-step object data processing via vehicle and server databases to generate, update and communicate accurate road characteristics databases | |
| US20230125581A1 (en) | Routing autonomous vehicles using temporal data | |
| CN113906414A (en) | Distributed processing for generating pose maps for high definition maps for navigating autonomous vehicles | |
| US20190138823A1 (en) | Automatic occlusion detection in road network data | |
| JP7659720B2 (en) | Method, device, and computer program for drawing U-turn driving route on electronic map | |
| US11953901B2 (en) | Determining autonomous vehicle routes | |
| US11685398B2 (en) | Lane based routing system for autonomous driving vehicles | |
| US9098088B2 (en) | Method for building outdoor map for moving object and apparatus thereof | |
| CN114255260A (en) | Trajectory generation method and system using road network model | |
| KR102274502B1 (en) | Method for updating Navigation Map | |
| CN109870681B (en) | High Definition 3D Mapping | |
| CN114322799B (en) | Vehicle driving method and device, electronic equipment and storage medium | |
| CN111204342B (en) | Map information system | |
| CN110440819B (en) | Navigation method, device and system | |
| CN114442633A (en) | Method for planning local path of logistics vehicle in unmanned park | |
| CN114839993A (en) | Unmanned vehicle line patrol obstacle avoidance method, device, equipment and storage medium | |
| CN115892076B (en) | Lane obstacle screening method and device and domain controller | |
| CN117906593B (en) | Map construction method, terminal device and storage medium | |
| CN113790725B (en) | Path planning method, path planning device, storage medium and mobile device | |
| CN113778102B (en) | AVP global path planning system, method, vehicle and storage medium | |
| CN114623842A (en) | Path planning method and device, storage medium and electronic equipment | |
| EP3779363A1 (en) | Method and system for vehicle routing based on parking probabilities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |