CN110570495A - virtual lane generation method, device and storage medium - Google Patents

virtual lane generation method, device and storage medium Download PDF

Info

Publication number
CN110570495A
CN110570495A CN201910849392.1A CN201910849392A CN110570495A CN 110570495 A CN110570495 A CN 110570495A CN 201910849392 A CN201910849392 A CN 201910849392A CN 110570495 A CN110570495 A CN 110570495A
Authority
CN
China
Prior art keywords
lane
target
determining
candidate
lanes
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.)
Granted
Application number
CN201910849392.1A
Other languages
Chinese (zh)
Other versions
CN110570495B (en
Inventor
陈映冰
程杰
唐铭锴
熊学良
郑林伟
刘天瑜
郭子彤
王鲁佳
刘明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Yiqing Creative Technology Ltd
Original Assignee
Shenzhen Yiqing Creative Technology Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Yiqing Creative Technology Ltd filed Critical Shenzhen Yiqing Creative Technology Ltd
Priority to CN201910849392.1A priority Critical patent/CN110570495B/en
Publication of CN110570495A publication Critical patent/CN110570495A/en
Application granted granted Critical
Publication of CN110570495B publication Critical patent/CN110570495B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • 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
    • G06T11/203—Drawing of straight lines or curves
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

The application relates to a virtual lane generation method, a virtual lane generation device and a storage medium. The method comprises the following steps: determining a reference lane of a segmented region; acquiring environmental information of a segmented area; determining lane parameters of the segmented region according to the environment information; and carrying out translation processing on the reference lane based on the lane parameters to obtain a target lane. By adopting the method, the safety of unmanned driving can be improved.

Description

Virtual lane generation method, device and storage medium
Technical Field
the present application relates to the field of computer technologies, and in particular, to a method and an apparatus for generating a virtual lane, and a storage medium.
background
in autonomous driving, an unmanned vehicle automatically determines surrounding image information, detects a lane driven ahead, and automatically travels on a road according to the detected lane.
At present, most of the methods adopt a camera installed in a vehicle to acquire image information of a road, then carry out binarization on the image information, and identify a lane line in the image by using a Hough transform and other methods. However, the image information collected in this way is limited by the surrounding terrain, adverse weather conditions (e.g., snow, rain, and fog), and road conditions, thereby easily causing the lane line recognition to fail, and thus reducing the safety of unmanned driving.
disclosure of Invention
in view of the above, it is desirable to provide a virtual lane generation method, device, and storage medium capable of improving unmanned safety.
A virtual lane generation method, the method comprising:
determining a reference lane of a segmented region;
acquiring environmental information of the segmented area;
determining lane parameters of the segmented region according to the environment information;
and carrying out translation processing on the reference lane based on the lane parameters to obtain a target lane.
In one embodiment, before the determining the reference lane of the segment region, the method further includes:
Determining a breakpoint of the road width mutation in the target area;
And segmenting the target region at the breakpoint position to obtain a plurality of segmented regions.
in one embodiment, after performing the translation process on the reference lane based on the lane parameter to obtain the target lane, the method includes:
Aligning and splicing the reference lanes in the two adjacent segmented regions;
determining the parallel distance between the target lane in the subsection area and the target lane in the adjacent subsection area according to the distance between the target lane and the spliced reference lane;
And splicing the two target lanes with the minimum parallel distance in the two adjacent segmentation areas to obtain the target lane in the target area.
in one embodiment, determining the lane parameters of the segmented region according to the environment information comprises:
determining the lane width of the segmentation region according to the road flatness and the road curvature;
Determining the number of lanes of the segment region based on the road width and the lane width.
in one embodiment, the method further comprises the following steps:
when the segmentation area has direction indication marks, determining the lane direction of each target lane according to the direction indication marks;
And when the direction guide mark does not exist, determining the lane direction of each target lane according to the preset relative position and number proportion of lanes in different directions.
in one embodiment, after obtaining the target lane, the method further includes:
Collecting field data of a section area where the unmanned vehicle is located;
acquiring lane parameters of a plurality of target lanes in the segmentation area; the target lane comprises a current lane where the unmanned vehicle is located and a plurality of candidate lanes;
Determining a spatial distance of each candidate lane relative to the unmanned vehicle based on the field data;
Determining the lane change cost corresponding to each candidate lane according to the lane parameters and the space distance;
and controlling the unmanned vehicle to change from the current lane to the candidate lane with the lane change cost meeting the condition.
in one embodiment, the determining the lane change cost corresponding to each candidate lane according to the lane parameter and the spatial distance includes:
Obtaining the blocking attribute of the candidate lane;
determining lane change span according to the number of lanes between each candidate lane and the current lane;
screening candidate lanes of which the blocking attributes and the lane change span both accord with lane change conditions;
And determining the lane change cost of each candidate lane obtained by screening according to the lane parameters and the spatial distance.
in one embodiment, the determining the lane change cost corresponding to each candidate lane according to the lane parameter and the spatial distance includes:
determining the lane direction of the current lane as a reference direction;
when the reference direction is a first direction, obtaining a mapping value corresponding to the first direction, and calculating the lane change cost of each candidate lane according to the space distance and the mapping value;
and when the reference direction is the second direction, determining the lane change priority of the corresponding candidate lane according to the lane direction, and calculating the lane change cost of each candidate lane according to the spatial distance, the mapping value and the lane change priority.
A virtual lane generation apparatus, the apparatus comprising:
a reference lane generation module for determining a reference lane of the segment region;
The lane parameter acquisition module is used for acquiring environmental information of the segmented area; determining lane parameters of the segmented region according to the environment information;
and the target lane acquisition module is used for carrying out translation processing on the reference lane based on the lane parameters to obtain a target lane.
a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
determining a reference lane of a segmented region;
acquiring environmental information of the segmented area;
determining lane parameters of the segmented region according to the environment information;
And carrying out translation processing on the reference lane based on the lane parameters to obtain a target lane.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
determining a reference lane of a segmented region;
Acquiring environmental information of the segmented area;
Determining lane parameters of the segmented region according to the environment information;
and carrying out translation processing on the reference lane based on the lane parameters to obtain a target lane.
according to the virtual lane generation method, the virtual lane generation device and the storage medium, the server only needs to perform translation processing on the reference lane based on the lane parameters, and the target lane can be obtained, so that the target lane can be generated quickly, and the generation efficiency of the target lane is improved. Because the target lane is obtained by translating the reference lane, compared with the traditional method that the target lane can be generated only after the lane line is identified based on the image characteristics, the virtual lane generation method can generate the target lane without identifying the lane line even under a severe environment, thereby improving the generation efficiency of the target lane and further improving the safety of automatic driving.
drawings
FIG. 1 is a diagram of an application scenario of a virtual lane generation method in one embodiment;
FIG. 2 is a flow diagram illustrating a virtual lane method according to one embodiment;
FIG. 3 is a schematic view of a reference lane in one embodiment;
FIG. 4 is a schematic view of a target lane in one embodiment;
FIG. 5 is a schematic diagram of a segmentation region in one embodiment;
FIG. 6 is a live image of a segmented region in one embodiment;
FIG. 7 is a live image of a segmented region in another embodiment;
FIG. 8 is a live image of a segmented region in yet another embodiment;
FIG. 9 is a block diagram showing the structure of a virtual lane generating apparatus according to an embodiment;
FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
the virtual lane generation method provided by the application can be applied to the application environment shown in fig. 1. An unmanned vehicle control module is built in the unmanned vehicle 102, or the unmanned vehicle control module is integrated in the server 104. The unmanned vehicle 102 is connected to the server 104 via a network. The unmanned vehicle 102 communicates with the server 104 via a network. The server 104 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers. The virtual lane generation method may be performed in the terminal 102 or the server 104, and the terminal 102 may generate the virtual lane by using the virtual lane generation method after collecting the environmental information. Or after the terminal 102 collects the environmental information, the environmental information is sent to the server 104 through the network, and the server 104 generates the virtual lane by using the virtual lane generation method.
The server 104 acquires the position information and the environment information of the reference lane of the segment area, determines the lane width and the total number of the target lanes of each target lane according to the environment information, and performs translation processing on the reference lane according to the lane width and the total number of the target lanes to obtain at least one target lane. The server 104 then transmits the position information of the target lane to the unmanned vehicle 102 so that the unmanned vehicle can travel on the target lane according to the position information of the target lane. The server only needs to perform translation processing on the reference lane based on the lane parameters, so that the target lane can be obtained, the target lane can be generated quickly, and the generation efficiency of the target lane is improved. Because the target lane is obtained by translating the reference lane, compared with the traditional method that the target lane can be generated only after the lane line is identified based on the image characteristics, the virtual lane generation method can generate the target lane without identifying the lane line even under a severe environment, thereby improving the generation efficiency of the target lane and further improving the safety of automatic driving.
in one embodiment, as shown in fig. 2, a virtual lane generation method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
step 202, determining a reference lane of the segmented region.
the target area is an area through which the unmanned vehicle passes when the unmanned vehicle runs from a task starting point to a task end point according to a running task; the segmentation region is a section of region obtained by segmenting the target region; the reference lane is a lane composed of the position information of the historical path; the location information includes longitude information and latitude information.
Specifically, the server stores reference lanes of a plurality of target areas in advance. And when the unmanned vehicle receives the driving task, the unmanned vehicle sends the driving task to the server. The server receives the driving task, determines a target area according to a task starting point and a task ending point in the driving task, divides the target area into at least one segmentation area, acquires a longitude range and a latitude range of the segmentation area, and extracts a reference lane located within the longitude range and the latitude range of the segmentation area from pre-stored reference lanes according to the longitude range and the latitude range.
for example, fig. 3 is a schematic diagram of a reference lane, wherein 310 is the reference lane. And when the unmanned vehicle receives the driving task and drives autonomously according to the driving task, the server judges whether a reference lane corresponding to the driving task exists or not according to the driving task. If the reference lane corresponding to the driving task does not exist, the driver can drive the unmanned vehicle to drive from the task starting point to the task ending point, and at the moment, the unmanned vehicle can collect the position information of the historical path passed by the unmanned vehicle in the driving process through the positioning system and upload the position information of the historical path to the server. And the server receives the position information of the historical path, and then sorts the position information of the historical path to obtain a historical path. After the historical path is obtained, the server or a simple path optimization algorithm is used for optimizing the historical path, and finally the reference lane of the target area is obtained. And after receiving the driving task, the unmanned vehicle sends the driving task to the server. The server determines a reference lane in the segment area according to the driving task.
for another example, before the unmanned vehicle receives a travel task and autonomously drives according to the travel task, the driver inputs a task start point and a task end point in a high-precision map according to the travel task. And the high-precision map automatically plans a driving path according to the task starting point and the task ending point. The server acquires a driving path planned by the high-precision map, calculates the driving path through a path planning algorithm to obtain the position information of the driving path, and then generates a corresponding reference lane according to the position information of the driving path. And after receiving the driving task, the unmanned vehicle sends the driving task to the server. The server determines a reference lane in the segment area according to the driving task.
step 204, obtaining the environmental information of the segment area.
The environment information includes the flatness of the road in the segment area, the width of the road and the curvature of the road.
Specifically, the server stores in advance a correspondence relationship between the environmental information and the location information. After the server determines the segment area, the server screens the environmental information in the segment area from the pre-stored environmental information according to the position information of the segment area.
for example, distance measuring devices are arranged outside a chassis and a carriage of the unmanned vehicle, and a positioning system is arranged in the carriage. Before the unmanned vehicle receives a driving task and carries out automatic driving, when a driver drives the unmanned vehicle to drive from a task starting point to a task ending point, a distance measuring device of a chassis of the unmanned vehicle measures the distance between the chassis and the ground in real time, a distance measuring device outside a carriage measures the distance between road edges in real time, and then the unmanned vehicle sends the distance between the chassis and the ground, the distance between the road edges and corresponding position information to a server.
And the server receives the distance between the chassis and the ground, the distance between the road edges and the position information, and screens out the distance between the chassis and the ground and the distance between the road edges in the segmentation area from the uploaded distance between the chassis and the ground and the uploaded distance between the road edges according to the position information. And the server counts the distance between the screened chassis and the ground, calculates the mean square error of the distance between the screened chassis and the ground, and takes the mean square error obtained after calculation as the flatness of the road in the segmentation area. And the server counts the distances between the screened road edges, and performs mean calculation on the distances between the screened road edges to obtain the average value of the distances between the road edges in the segment area, which is used as the road width of the segment area. After receiving the position information uploaded by the unmanned vehicle, the server screens the position information in the segment area from the uploaded position information according to the longitude and latitude information in the position information, then determines the driving path of the unmanned vehicle in the segment area according to the position information, and determines the curvature of the road according to the curvature information of the driving path. And after the server obtains the road width, the road flatness and the road curvature in the segmented area, the road width, the road flatness, the road curvature and the position information are correspondingly stored.
for another example, a camera and a positioning system are arranged on the unmanned vehicle, when the unmanned vehicle is determined to be in the segment area by the positioning system, the unmanned vehicle acquires at least one road image in front by the camera and sends the road image and the position information to the server, the server receives the road image and the position information, determines the road width, the road flatness and the road curvature of the segment area from the road image, and then correspondingly stores the road width, the road flatness, the road curvature and the position information.
And step 206, determining lane parameters of the segmented areas according to the environment information.
The lane parameters comprise lane width and lane number.
specifically, after the server obtains the road flatness and the road camber of the segment area, the server performs weighted calculation on the road camber and the road flatness to obtain an environment value. The server determines the width of the lane according to the environment value. For example, the server judges whether the environment value is greater than the environment threshold value, when the environment value is greater than the environment threshold value, the road in the segmented interval can be considered to be a curved and uneven road, the larger the transverse movement amplitude of the unmanned vehicle is, the more unsafe the unmanned vehicle runs, and in order to ensure the driving safety of the unmanned vehicle, the server determines the lane width to be 0.1 times of the vehicle width; when the environment value is smaller than the environment threshold value, the road in the segmented interval can be considered as a flat straight road, and the lane width is set to be 0.5 times of the vehicle width by the server at the moment. The server obtains the road width in the subsection interval, and subtracts one after dividing the road width by the lane width to obtain the number of lanes in the subsection interval.
and step 208, performing translation processing on the reference lane based on the lane parameters to obtain a target lane.
Specifically, fig. 4 is a schematic diagram of a target lane, where 410 is a reference lane and 420 is a target lane. The server performs translation processing on the reference lane according to the lane width and the number of lanes to obtain at least one target lane as shown in fig. 4.
For example, the server determines the position information of the road edge according to the high-precision map, then calculates the transverse distance between the reference lane and the left edge according to the position information of the road edge and the position information of the reference lane, divides the transverse distance by the lane width to obtain the number of lanes needing to be translated on the left side of the reference lane, and subtracts the number of lanes on the left side of the reference lane from the number of lanes to obtain the number of lanes on the right side of the reference lane, so that the reference lane can be translated according to the number of target lanes on the left side and the right side of the reference lane.
for another example, the unmanned vehicle is equipped with a distance measuring device and a positioning system. The unmanned vehicle collects position information of the road edge while measuring the width of the road, and reports the position information of the road edge to the server. The server calculates the transverse distance between the reference lane and the road edge according to the position information, and determines the number of the target lanes on the left side and the right side of the reference lane according to the transverse distance, so that the reference lane is translated according to the number of the target lanes on the left side and the right side of the reference lane.
in this embodiment, according to the environmental information of the segment region, the lane parameters of the segment region may be determined; according to the lane parameters, the reference lane can be subjected to translation processing to obtain the target lane. The server only needs to translate the reference lane according to the lane parameters to obtain the target lane, so that the target lane can be generated quickly, and the generation efficiency of the target lane is improved. Because the target lane is obtained by translating the reference lane, compared with the traditional method that the target lane can be generated only after the lane line is identified based on the image characteristics, the virtual lane generation method can generate the target lane without identifying the lane line even under a severe environment, thereby improving the generation efficiency of the target lane and further improving the safety of automatic driving.
in one embodiment, before determining the reference lane of the segment region, the method further includes: determining a breakpoint of the road width mutation in the target area; and segmenting the target region at the breakpoint position to obtain a plurality of segmented regions.
Specifically, fig. 5 is a schematic diagram of the segment area provided in this embodiment, where 510 is a breakpoint position, and 520 is a segment area. The server acquires width information of a road in the target area, determines a breakpoint position of sudden change of the road width according to the width information, and divides the target area according to the breakpoint position to obtain a plurality of segment areas. For example, unmanned vehicles have a range finding device and a positioning system thereon. The method comprises the steps that the width of a road in a target area is measured according to preset frequency in the driving process of the unmanned vehicle, and the width of the road and the position information of the edge of the road are uploaded to a server. And the server receives the width and position information of the road, and subtracts the preamble width value from the subsequent width value of the two adjacent width values to obtain a width difference value. The server judges whether the width difference is larger than a threshold value or not, when the width difference is larger than the threshold value, the server judges whether the width difference is larger than zero or not, if the width difference is larger than zero, the width of the road in the target area can be considered to be widened from narrow to wide, at the moment, the server acquires position information corresponding to the subsequent width, and the position of the subsequent breakpoint is determined as the breakpoint position according to the position information; if the width difference is smaller than zero, it can be considered that the road width in the target area is being narrowed from wide to narrow, at this time, the server determines the position corresponding to the preamble width as the breakpoint position, and then the server divides the target area according to the breakpoint position to obtain a plurality of segment areas.
for another example, the server acquires the road width of the target area from the high-precision map, determines the position of the abrupt width change from the road width of the target area as the breakpoint position, and divides the target area according to the breakpoint position to obtain a plurality of segment areas.
In this embodiment, the server may divide the target region into a plurality of segment regions according to the width discontinuity point of the road, so that the subsequent server may generate the target lane in a targeted manner according to the characteristics of the segment regions.
In one embodiment, the method further comprises: aligning and splicing the reference lanes in the two adjacent segmented regions; determining the parallel distance between the target lane in the subsection area and the target lane in the adjacent subsection area according to the distance between the target lane and the spliced reference lane; and splicing the two target lanes with the minimum parallel distance in the two adjacent segmentation areas to obtain the target lane in the target area.
Specifically, after obtaining the target lanes of the segment regions, the server may splice the target lanes in each segment region. Specifically, the server firstly splices the reference lanes of two adjacent segment areas to obtain a spliced reference lane. Then the server respectively acquires the target lanes in the two adjacent segmented regions and calculates the parallel distance of each target lane in the two adjacent segmented regions from the reference lane. For example, the distance of the target lane located on the left of the reference lane from the reference lane is set to a positive value, and the parallel distance of the target lane located on the right of the reference lane from the reference lane is set to a negative value. The server obtains the parallel distance between each target lane in the two adjacent segmentation areas and the reference lane, and subtracts the parallel distance between each target lane in the preceding segmentation area and the reference lane from the parallel distance between each target lane in the subsequent segmentation area and the reference lane to obtain the parallel distance between the target lane in the preceding segmentation area and the target lane in the subsequent segmentation area. And the server splices the two target lanes with the minimum parallel distance in the two adjacent segmentation areas to obtain the target lane in the target area.
For example, the server first splices the reference lanes of two adjacent segment regions to obtain a spliced reference lane. The server draws an extension line of each target lane in the pre-order segmentation area in the two adjacent segmentation areas, calculates the transverse distance between each target lane in the post-order segmentation area and each extension line, and then splices the two target lanes with the minimum transverse distance to obtain the target lanes in the target area.
In the embodiment, the two adjacent segmented areas are spliced according to the reference lane, so that a reference is set for splicing the subsequent target lane, and the target lane can be accurately spliced subsequently; because the number and the positions of the target lanes in the two adjacent segmentation areas are possibly different, the target lanes in the two adjacent segmentation areas can be spliced by acquiring the parallel distance between the target lanes in the two adjacent segmentation areas, so that the unmanned vehicle can smoothly run in the target lanes in the target areas.
in one embodiment, determining the lane parameters of the segment region according to the environment information comprises: determining the lane width of a segmented area according to the road flatness and the road curvature; and determining the number of lanes of the segmentation area based on the road width and the lane width.
specifically, before determining the lane width of the segment area, a driver collects flatness and camber information of a large number of roads, drives an unmanned vehicle to start lane change on the corresponding road by taking the width of 0.1 times of the vehicle as the lane width, records the stable driving degree of the vehicle when the current lane width is used for lane change, increases the lane width if the unmanned vehicle can perform stable lane change under the current lane width, and drives the unmanned vehicle to change the lane by the increased lane width until the unmanned vehicle cannot perform stable lane change under the increased lane width, and records the corresponding lane width when the unmanned vehicle cannot perform stable lane change at the moment. For example, when the driver collects that the smoothness of the road a is 20 and the curve is 30, the driver drives the unmanned vehicle to move transversely on the road a by 0.1 times the vehicle width, and the driver determines whether the unmanned vehicle can drive smoothly when the unmanned vehicle moves transversely by 0.1 times the vehicle width, if the unmanned vehicle can move smoothly, the driver moves transversely by 0.2 times the vehicle width, and if the unmanned vehicle cannot drive smoothly under the condition of 0.2 times the vehicle width, the driver records that the maximum transverse movement width of the road a is 0.2 times the vehicle width. The driver uploads the flatness, the camber and the maximum lateral movement width of the road to the server, for example, the vehicle width of the road a with the flatness of 20, the camber of 30 and the maximum lateral movement width of 0.2 times is uploaded to the server. And the server receives the flatness, the camber and the maximum transverse movement width of the road, calculates the influence of the flatness and the camber on the maximum transverse movement width according to the flatness, the camber and the maximum transverse movement width of the road, and respectively obtains the weights of the flatness and the camber. According to the flatness and the weight of the curvature, the server carries out weighted calculation on the road curvature and the road flatness to obtain an environment value, when the environment value is larger than a threshold value, the server determines the lane width to be 0.1 times of the vehicle width, and when the environment value is smaller than the threshold value, the server sets the lane width to be 0.5 times of the vehicle width. The server obtains the road width in the subsection interval, and subtracts one after dividing the road width by the lane width to obtain the number of lanes in the subsection interval.
In this embodiment, through analyzing the roughness and the camber of a large amount of roads, the importance degree of the roughness and the camber to the lane width can be obtained, so that the lane width can be accurately calculated according to the importance degree of the roughness and the camber to the lane width, and then the number of lanes can be determined according to the lane width.
in one embodiment, the method further comprises: when the direction guide marks exist in the segmented areas, determining the lane direction of each target lane according to the direction guide marks; and when the direction guide mark does not exist, determining the lane direction of each target lane according to the preset relative position and number proportion of lanes in different directions.
Wherein the lane parameters include a direction of the lane; the direction guide sign is a signboard disposed above the road to indicate the driving direction of the lane, or an icon drawn directly on the road to indicate the driving direction of the lane.
Specifically, after generating a target lane of a segment area, the server determines whether a direction guide mark exists in the segment area according to a live image, if the direction guide mark exists, the server divides a road of the segment area into a forward area, a reverse area and a middle area according to the direction guide mark, for example, the road of the segment area is known to be four lanes according to the live image, the lane width of each real lane is calculated according to the width of the road, and then the latitude and longitude ranges of the forward area, the reverse area and the middle area are determined based on the lane width. The server determines the longitude and latitude range of the forward area, the longitude and latitude range of the reverse area and the longitude and latitude range of the middle area, then determines a target lane in the forward area as a forward lane, determines a target lane in the reverse area as a reverse lane and determines a target lane in the middle area as a middle lane. If the direction guide does not exist, the server determines the target lane positioned on the right side of the reference lane as a forward lane, determines the target lane positioned on the left side of the reference lane and closest to the reference lane as a middle lane, and determines the rest target lanes as reverse lanes. If only one target lane is arranged on the right side of the reference lane, the middle lane is not arranged.
In the embodiment, under the condition that the direction guide mark exists, the lane direction of the target lane can be determined through simple direction guide mark recognition, so that the lane direction setting efficiency is improved; under the condition that no direction guide mark exists, the lane direction of the target lane can be determined according to the relative positions and the number of lanes in different directions, so that the efficiency of setting the lane direction is improved.
in one embodiment, the method further comprises: collecting field data of a section area where the unmanned vehicle is located; acquiring lane parameters of a plurality of target lanes in a segmentation area; the target lane comprises a current lane where the unmanned vehicle is located and a plurality of candidate lanes; determining a spatial distance of each candidate lane relative to the unmanned vehicle based on the field data; determining the lane change cost corresponding to each candidate lane according to the lane parameters and the spatial distance; and controlling the unmanned vehicle to change from the current lane to the candidate lane with the lane change cost meeting the condition.
The field data comprises the position of the unmanned vehicle and the position information of obstacles on each target lane; the space distance comprises the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located and the longitudinal distance between the obstacle on the candidate lane and the unmanned vehicle; the lane change cost reflects the feasibility of changing the lane of the unmanned vehicle from the current lane to the candidate lane. The larger the lane change cost value is, the smaller the feasibility of changing lanes to the candidate lanes is represented.
Specifically. The unmanned vehicle is provided with a camera, a distance measuring device and a positioning system. The unmanned vehicle acquires field data within a preset range at a specific frequency through the camera, the distance measuring device and the positioning system in the process of running in the segmentation area, and transmits the acquired field data to the server. For example, the positioning system collects the position information of the vehicle, and the camera and the distance measuring device collect the position information of the obstacles on the target lane within 20 meters and 10 meters in front of and behind the unmanned vehicle. After receiving the field data sent by the unmanned vehicle, the server extracts the position information of the unmanned vehicle from the field data, and then determines the segment area of the unmanned vehicle according to the position information of the unmanned vehicle. The server acquires a plurality of target lanes within the segmentation area and determines lane directions of the plurality of target lanes within the segmentation area.
the server extracts position information of the obstacle from the field data, judges whether the obstacle is located on the candidate lane or not according to the position information of the obstacle, and if the obstacle is not located on the candidate lane, the server acquires the transverse distance between the obstacle and the candidate lane and translates the position of the obstacle to the candidate lane with the minimum transverse distance. The server acquires the position information of the unmanned vehicle, and determines the transverse distance between the candidate lane where the translated obstacle is located and the current lane where the unmanned vehicle is located according to the position information. The server translates the position information of the unmanned vehicle from the current lane to the lane where the obstacle is located, and determines the longitudinal distance between the obstacle on the candidate lane and the unmanned vehicle according to the translated position information of the unmanned vehicle and the translated position information of the obstacle.
after the server acquires the direction of each candidate lane, the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located and the longitudinal distance between the obstacle on the candidate lane and the unmanned vehicle, the lane change cost from lane change to each candidate lane can be calculated according to the direction of the candidate lane, the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located and the longitudinal distance between the obstacle on the candidate lane and the unmanned vehicle, for example, weighting calculation can be performed. And the server screens the candidate lanes with the lane change cost smaller than the threshold value and controls the unmanned vehicle to change lanes from the current lane to the screened candidate lanes.
In this embodiment, since the server determines the lane to be changed according to the lane parameters and the spatial distance, compared with the conventional method of determining where the lane should be changed according to the distance from the obstacle vehicle or the obstacle, the lane changing method for the unmanned vehicle can select the lane to be changed according to the field information, thereby improving the flexibility of lane changing.
In one embodiment, determining the lane change cost corresponding to each candidate lane according to the lane parameters and the spatial distance includes: obtaining the blocking attribute of the candidate lane; determining lane change span according to the number of lanes between each candidate lane and the current lane; screening candidate lanes of which the blocking attributes and the lane change span both accord with lane change conditions; and determining the lane change cost of each candidate lane obtained by screening according to the lane parameters and the spatial distance.
wherein the congestion attribute is information reflecting a degree of the clear or congested lane.
Specifically, after the server acquires the position information of the obstacle, the server determines the longitudinal distance between the obstacle and the unmanned vehicle according to the position information of the obstacle and the position information of the unmanned vehicle, when the longitudinal distance is smaller than a distance threshold, it can be considered that the unmanned vehicle cannot normally change the lane to the candidate lane, and the server determines the candidate lane as the candidate lane of the lane unchangeable.
the server determines the transverse distance between the obstacle and the unmanned vehicle according to the position information of the obstacle and the position information of the unmanned vehicle, calculates the number of lanes between the candidate lane and the current lane where the unmanned vehicle is located according to the transverse distance and the lane width, and judges the candidate lane as an lane-unchangeable lane when the number of lanes between the candidate lane and the current lane where the unmanned vehicle is located is larger than a lane threshold value. The server screens out candidate lanes which can be changed from the candidate lanes, acquires the direction of the candidate lane of the variable lane, the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located and the longitudinal distance between obstacles on the candidate lane and the unmanned vehicle, and then calculates the lane change cost from the lane change to the candidate lane of each variable lane according to the direction of the candidate lane, the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located and the longitudinal distance between obstacles on the candidate lane and the unmanned vehicle, for example, weighting calculation can be carried out. And the server screens the candidate lanes with the lane change cost smaller than the cost threshold value and controls the unmanned vehicle to change lanes from the current lane to the screened candidate lanes.
for example, since the risk of lane change of the unmanned vehicle to the reverse lane is greater than the risk of lane change to the forward lane or the middle lane, the distance threshold of the reverse lane set by the server is greater than the distance threshold of the forward lane or the middle lane, for example, when the obstacle is located in the reverse lane and the longitudinal distance of the obstacle from the unmanned vehicle is less than 15 meters, the candidate lane can be determined as an unchangeable lane candidate, and when the obstacle is located in the forward lane or the middle lane and the longitudinal distance of the obstacle from the unmanned vehicle is less than 10 meters, the candidate lane can be determined as an unchangeable lane candidate lane. Fig. 6 is a live view of a segmentation region, wherein 610 is a forward lane, 620 is a center lane, and 630 is a reverse lane. As can be seen from fig. 6, the obstacles are all located on the reverse lanes, and the longitudinal distance from the obstacle to the unmanned vehicle is less than 15 meters, so that all the reverse lanes are lane-unchangeable candidate lanes. Setting a lane threshold value as 3 lane widths, setting the current lane where the unmanned vehicle is located as a No. 4 lane, and deleting candidate lanes with the transverse distance larger than 3 lanes, wherein the candidate lanes meeting lane change conditions at the moment are No. 1, No. 2, No. 3, No. 5, No. 6 and No. 7 lanes. And the server calculates lane change costs of the lanes 1, 2, 3, 5, 6 and 7 according to the lane parameters and the space distances of the lanes 1, 2, 3, 5, 6 and 7.
in the embodiment, the lane change cost is calculated by introducing a plurality of factors, so that the influence of various factors on the lane change decision can be embodied; the candidate lanes meeting the lane change requirement are screened out from the candidate lanes according to the blocking attribute and the lane change span, and then the lane change cost of each candidate lane obtained through screening is calculated, so that the server does not need to calculate the lane change cost for each candidate lane, the calculation resources are saved, and the calculation efficiency of the lane change cost is improved.
in one embodiment, determining the lane change cost corresponding to each candidate lane according to the lane parameters and the spatial distance includes: determining the lane direction of the current lane as a reference direction; when the reference direction is the first direction, obtaining a mapping value corresponding to the first direction, and calculating the lane change cost of each candidate lane according to the spatial distance and the mapping value; and when the reference direction is the second direction, determining the lane change priority of the corresponding candidate lane according to the lane direction, and calculating the lane change cost of each candidate lane according to the spatial distance, the mapping value and the lane change priority.
Specifically, the server obtains a lane direction of a current lane where the unmanned vehicle is located, and determines whether the lane direction of the current lane is a first direction, for example, whether the unmanned vehicle is located in a middle lane or a forward lane. If the lane direction of the current lane where the unmanned vehicle is located is the first direction, the server determines a mapping value of the first direction according to a preset mapping relation, and then calculates the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located, the longitudinal distance between the obstacle on the candidate lane and the unmanned vehicle and the mapping value to obtain the lane change cost of the candidate lane, for example, the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located, the longitudinal distance between the obstacle on the candidate lane and the unmanned vehicle and the mapping value are subjected to weighted calculation.
For example, as shown in the unmanned vehicle scene image in fig. 7, the current lane where the unmanned vehicle is located is lane No. 4, and the lane direction of lane No. 4 is the forward lane. When the distance measuring device on the unmanned vehicle detects and finds that an obstacle exists in the front of the unmanned vehicle within 8 meters, the unmanned vehicle generates a prompt message according to the detection and the finding, and the prompt message is sent to the server. And the server receives the prompt message and generates a lane change instruction according to the prompt message. Specifically, when the lane direction is set as a forward lane or a middle lane, the corresponding mapping value is negative 1, and when the lane direction is a reverse lane, the corresponding mapping value is 1; when the lane direction of the current lane where the unmanned vehicle is located is a forward lane, a preset lane change cost calculation formula is that k is equal to f1ecost1+k2ecost2+k3ecost3the weights of K1, K2 and K3 are, cost1 represents the transverse distance between the candidate lane and the current lane where the unmanned vehicle is located, cost2 represents the longitudinal distance between the obstacle on the candidate lane and the unmanned vehicle, and cost3 represents a mapping value, wherein the larger the f value of the candidate lane is, the less easy the candidate lane is to change to. And the server sequentially calculates the lane change cost of each candidate lane according to a lane change cost formula and controls the unmanned vehicle to change to the candidate lane No. 7 or 8 meeting the lane change condition.
Specifically, when the lane direction of the current lane where the unmanned vehicle is located is the second direction, for example, a reverse lane, the server determines the priority of each candidate lane according to a preset driving habit, then obtains a corresponding priority value according to the priority, for example, the server has a corresponding relationship between the priority and the priority value, and determines the priority value of each candidate lane according to the corresponding relationship. And then, the server calculates the space distance, the mapping value and the priority value to obtain the lane change cost of the candidate lane.
for example, as shown in fig. 8, in the field image of the unmanned vehicle, the lane direction of the current lane where the unmanned vehicle is located is the reverse lane, and at this time, the preset lane change cost calculation formula is that f ═ k1ecost1+k2ecost2+k3ecost3+k4ecost4Wherein K1, K2, K3 and K4 are weights, cost1 represents the transverse distance of the candidate lane from the current lane where the unmanned vehicle is located, cost2 represents the longitudinal distance of the obstacle on the candidate lane from the unmanned vehicle, cost3 represents a mapping value, cost4 represents a priority value, and the larger the f value of the candidate lane is, the less easy the candidate lane is to change to. Setting the driving habit to drive to the right, setting the priority of a reverse lane as low and the priority of a middle lane as medium by the server according to the driving habit, setting the priority of a forward lane as high, and then determining the priority value of each candidate lane according to the corresponding relation between the priority levels and the priority values. And after the priority values of the candidate lanes are obtained, the server sequentially calculates the lane change cost of each candidate lane according to a lane change cost formula, and controls the unmanned vehicle to change to the lane 9 meeting the lane change condition.
In this embodiment, by introducing the mapping value of the lane direction into the lane change cost calculation formula, it is possible to reduce the lane change of the unmanned vehicle to the lane that is not in accordance with the driving habit, and if the driving habit is right-handed, it is possible to reduce the probability of the lane change of the unmanned vehicle to the reverse lane, so that the lane change of the unmanned vehicle is more in accordance with the scenario logic and the driving habit. Because the danger of the unmanned vehicle driving on the reverse lane is greater than that of the unmanned vehicle driving on the forward lane or the middle lane, the unmanned vehicle on the reverse lane can be prompted to change to a safer forward lane or reverse lane by introducing the priority value into the lane change cost calculation formula, and therefore the driving safety of the unmanned vehicle is improved.
The K1, K2, K3 and K4 in the above formula can be determined according to the debugging result, or according to the specific situation. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature.
it should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 9, there is provided a virtual lane generating apparatus including: a reference lane generating module 901, a lane parameter acquiring module 902 and a target lane acquiring module 903, wherein:
a reference lane generating module 901, configured to determine a reference lane of the segmented region;
A lane parameter obtaining module 902, configured to obtain environmental information of a segmented region; determining lane parameters of the segmented region according to the environment information;
And a target lane acquiring module 903, configured to perform translation processing on the reference lane based on the lane parameter to obtain a target lane.
In one embodiment, the apparatus further comprises a segmentation region obtaining module 904, configured to determine a breakpoint of a target region where the road width is suddenly changed; and segmenting the target region at the breakpoint position to obtain a plurality of segmented regions.
in one embodiment, the apparatus further comprises a target lane stitching module 905 for performing aligned stitching on the reference lanes in the two adjacent segment regions; determining the parallel distance between the target lane in the subsection area and the target lane in the adjacent subsection area according to the distance between the target lane and the spliced reference lane; and splicing the two target lanes with the minimum parallel distance in the two adjacent segmentation areas to obtain the target lane in the target area.
in one embodiment, the lane parameter obtaining module 902 further includes a parameter determining module 9021, configured to determine lane widths of the segment regions according to road flatness and road curvature; and determining the number of lanes of the segmentation area based on the road width and the lane width. When the direction guide marks exist in the segmented areas, determining the lane direction of each target lane according to the direction guide marks; and when the direction guide mark does not exist, determining the lane direction of each target lane according to the preset relative position and number proportion of lanes in different directions.
in one embodiment, the apparatus further comprises a lane change module 906 for collecting field data of a segment area where the unmanned vehicle is located; acquiring lane parameters of a plurality of target lanes in a segmentation area; the target lane comprises a current lane where the unmanned vehicle is located and a plurality of candidate lanes; determining a spatial distance of each candidate lane relative to the unmanned vehicle based on the field data; determining the lane change cost corresponding to each candidate lane according to the lane parameters and the spatial distance; and controlling the unmanned vehicle to change from the current lane to the candidate lane with the lane change cost meeting the condition.
in one embodiment, the lane change module 906 further includes a lane change cost calculation module 9061, configured to obtain a blocking attribute of the candidate lane; determining lane change span according to the number of lanes between each candidate lane and the current lane; screening candidate lanes of which the blocking attributes and the lane change span both accord with lane change conditions; determining the lane direction of the current lane as a reference direction; when the reference direction is the first direction, obtaining a mapping value corresponding to the first direction, and calculating lane change cost of the candidate lane meeting the lane change condition according to the spatial distance and the mapping value; and when the reference direction is the second direction, determining the lane change priority of the corresponding candidate lane according to the lane direction, and calculating the lane change cost of the candidate lane meeting the lane change condition according to the spatial distance, the mapping value and the lane change priority.
For specific definition of the virtual lane generation device, reference may be made to the above definition of the virtual lane generation method, which is not described herein again. The modules in the virtual lane generation device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
in one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a pseudo lane generation method.
those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
determining a reference lane of a segmented region;
acquiring environmental information of a segmented area;
Determining lane parameters of the segmented region according to the environment information;
and carrying out translation processing on the reference lane based on the lane parameters to obtain the target lane.
in one embodiment, the processor, when executing the computer program, further performs the steps of: prior to the determining of the reference lane of the segmented region,
Determining a breakpoint of the road width mutation in the target area;
And segmenting the target region at the breakpoint position to obtain a plurality of segmented regions.
In one embodiment, the processor, when executing the computer program, further performs the steps of: after the reference lane is translated based on the lane parameters to obtain the target lane,
aligning and splicing the reference lanes in the two adjacent segmented regions;
Determining the parallel distance between the target lane in the subsection area and the target lane in the adjacent subsection area according to the distance between the target lane and the spliced reference lane;
And splicing the two target lanes with the minimum parallel distance in the two adjacent segmentation areas to obtain the target lane in the target area.
In one embodiment, the environmental information includes road width, road flatness, and road camber; the lane parameters comprise lane width and lane number; the processor, when executing the computer program, further performs the steps of:
determining the lane width of a segmented area according to the road flatness and the road curvature;
And determining the number of lanes of the segmentation area based on the road width and the lane width.
In one embodiment, the lane parameters include a lane direction; the processor, when executing the computer program, further performs the steps of:
When the direction guide marks exist in the segmented areas, determining the lane direction of each target lane according to the direction guide marks;
and when the direction guide mark does not exist, determining the lane direction of each target lane according to the preset relative position and number proportion of lanes in different directions.
In one embodiment, the processor, when executing the computer program, further performs the steps of: after the target lane is obtained, the lane is displayed,
collecting field data of a section area where the unmanned vehicle is located;
Acquiring lane parameters of a plurality of target lanes in a segmentation area; the target lane comprises a current lane where the unmanned vehicle is located and a plurality of candidate lanes;
determining a spatial distance of each candidate lane relative to the unmanned vehicle based on the field data;
Determining the lane change cost corresponding to each candidate lane according to the lane parameters and the spatial distance;
And controlling the unmanned vehicle to change from the current lane to the candidate lane with the lane change cost meeting the condition.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
obtaining the blocking attribute of the candidate lane;
determining lane change span according to the number of lanes between each candidate lane and the current lane;
Screening candidate lanes of which the blocking attributes and the lane change span both accord with lane change conditions;
And determining the lane change cost of each candidate lane obtained by screening according to the lane parameters and the spatial distance.
in one embodiment, the processor, when executing the computer program, further performs the steps of:
determining the lane direction of the current lane as a reference direction;
When the reference direction is the first direction, obtaining a mapping value corresponding to the first direction, and calculating the lane change cost of each candidate lane according to the spatial distance and the mapping value;
And when the reference direction is the second direction, determining the lane change priority of the corresponding candidate lane according to the lane direction, and calculating the lane change cost of each candidate lane according to the spatial distance, the mapping value and the lane change priority.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
determining a reference lane of a segmented region;
acquiring environmental information of a segmented area;
Determining lane parameters of the segmented region according to the environment information;
And carrying out translation processing on the reference lane based on the lane parameters to obtain the target lane.
In one embodiment, the computer program when executed by the processor further performs the steps of: prior to the determining of the reference lane of the segmented region,
Determining a breakpoint of the road width mutation in the target area;
and segmenting the target region at the breakpoint position to obtain a plurality of segmented regions.
In one embodiment, the computer program when executed by the processor further performs the steps of: after the reference lane is translated based on the lane parameters to obtain the target lane,
Aligning and splicing the reference lanes in the two adjacent segmented regions;
determining the parallel distance between the target lane in the subsection area and the target lane in the adjacent subsection area according to the distance between the target lane and the spliced reference lane;
and splicing the two target lanes with the minimum parallel distance in the two adjacent segmentation areas to obtain the target lane in the target area.
In one embodiment, the environmental information includes road width, road flatness, and road camber; the lane parameters comprise lane width and lane number; the computer program when executed by the processor further realizes the steps of:
Determining the lane width of a segmented area according to the road flatness and the road curvature;
and determining the number of lanes of the segmentation area based on the road width and the lane width.
In one embodiment, the lane parameters include a lane direction; the computer program when executed by the processor further realizes the steps of:
When the direction guide marks exist in the segmented areas, determining the lane direction of each target lane according to the direction guide marks;
And when the direction guide mark does not exist, determining the lane direction of each target lane according to the preset relative position and number proportion of lanes in different directions.
In one embodiment, the computer program when executed by the processor further performs the steps of: after the target lane is obtained, the lane is displayed,
collecting field data of a section area where the unmanned vehicle is located;
acquiring lane parameters of a plurality of target lanes in a segmentation area; the target lane comprises a current lane where the unmanned vehicle is located and a plurality of candidate lanes;
Determining a spatial distance of each candidate lane relative to the unmanned vehicle based on the field data;
determining the lane change cost corresponding to each candidate lane according to the lane parameters and the spatial distance;
And controlling the unmanned vehicle to change from the current lane to the candidate lane with the lane change cost meeting the condition.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Obtaining the blocking attribute of the candidate lane;
determining lane change span according to the number of lanes between each candidate lane and the current lane;
screening candidate lanes of which the blocking attributes and the lane change span both accord with lane change conditions;
and determining the lane change cost of each candidate lane obtained by screening according to the lane parameters and the spatial distance.
in one embodiment, the computer program when executed by the processor further performs the steps of:
determining the lane direction of the current lane as a reference direction;
and when the reference direction is the first direction, obtaining a mapping value corresponding to the first direction, and calculating the lane change cost of each candidate lane according to the spatial distance and the mapping value.
And when the reference direction is the second direction, determining the lane change priority of the corresponding candidate lane according to the lane direction, and calculating the lane change cost of each candidate lane according to the spatial distance, the mapping value and the lane change priority.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
the above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A virtual lane generation method, the method comprising:
Determining a reference lane of a segmented region;
acquiring environmental information of the segmented area;
determining lane parameters of the segmented region according to the environment information;
And carrying out translation processing on the reference lane based on the lane parameters to obtain a target lane.
2. The method of claim 1, wherein prior to the determining the reference lane of the segmented region, the method further comprises:
determining a breakpoint of the road width mutation in the target area;
and segmenting the target region at the breakpoint position to obtain a plurality of segmented regions.
3. The method of claim 2, further comprising, after translating the reference lane based on the lane parameters to obtain a target lane:
Aligning and splicing the reference lanes in the two adjacent segmented regions;
Determining the parallel distance between the target lane in the subsection area and the target lane in the adjacent subsection area according to the distance between the target lane and the spliced reference lane;
and splicing the two target lanes with the minimum parallel distance in the two adjacent segmentation areas to obtain the target lane in the target area.
4. The method of claim 1, wherein the environmental information includes road width, road flatness, and road camber; the lane parameters comprise lane width and lane number; the determining of the lane parameters of the segment region according to the environment information includes:
determining the lane width of the segmentation region according to the road flatness and the road curvature;
determining the number of lanes of the segment region based on the road width and the lane width.
5. the method of claim 4, wherein the lane parameters include a lane direction; the method further comprises the following steps:
when the segmentation area has direction indication marks, determining the lane direction of each target lane according to the direction indication marks;
And when the direction guide mark does not exist, determining the lane direction of each target lane according to the preset relative position and number proportion of lanes in different directions.
6. The method of any of claims 1 to 5, wherein after obtaining the target lane, the method further comprises:
collecting field data of a section area where the unmanned vehicle is located;
Acquiring lane parameters of a plurality of target lanes in the segmentation area; the target lane comprises a current lane where the unmanned vehicle is located and a plurality of candidate lanes;
Determining a spatial distance of each candidate lane relative to the unmanned vehicle based on the field data;
determining the lane change cost corresponding to each candidate lane according to the lane parameters and the space distance;
and controlling the unmanned vehicle to change from the current lane to the candidate lane with the lane change cost meeting the condition.
7. The method of claim 6, wherein the determining the lane change cost for each candidate lane according to the lane parameters and the spatial distance comprises:
Obtaining the blocking attribute of the candidate lane;
determining lane change span according to the number of lanes between each candidate lane and the current lane;
Screening candidate lanes of which the blocking attributes and the lane change span both accord with lane change conditions;
And determining the lane change cost of each candidate lane obtained by screening according to the lane parameters and the spatial distance.
8. the method of claim 7, wherein the determining the lane change cost for each candidate lane according to the lane parameters and the spatial distance comprises:
determining the lane direction of the current lane as a reference direction;
When the reference direction is a first direction, obtaining a mapping value corresponding to the first direction, and calculating the lane change cost of each candidate lane according to the space distance and the mapping value;
and when the reference direction is the second direction, determining the lane change priority of the corresponding candidate lane according to the lane direction, and calculating the lane change cost of each candidate lane according to the spatial distance, the mapping value and the lane change priority.
9. an apparatus for generating a virtual lane, the apparatus comprising:
a reference lane generation module for determining a reference lane of the segment region;
the lane parameter acquisition module is used for acquiring environmental information of the segmented area; determining lane parameters of the segmented region according to the environment information;
And the target lane acquisition module is used for carrying out translation processing on the reference lane based on the lane parameters to obtain a target lane.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
CN201910849392.1A 2019-09-09 2019-09-09 Virtual lane generation method, device and storage medium Active CN110570495B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910849392.1A CN110570495B (en) 2019-09-09 2019-09-09 Virtual lane generation method, device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910849392.1A CN110570495B (en) 2019-09-09 2019-09-09 Virtual lane generation method, device and storage medium

Publications (2)

Publication Number Publication Date
CN110570495A true CN110570495A (en) 2019-12-13
CN110570495B CN110570495B (en) 2023-09-19

Family

ID=68778587

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910849392.1A Active CN110570495B (en) 2019-09-09 2019-09-09 Virtual lane generation method, device and storage medium

Country Status (1)

Country Link
CN (1) CN110570495B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115512541A (en) * 2022-09-20 2022-12-23 浙江大学 Road surface accurate information service system for safe driving of vehicle

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108470159A (en) * 2018-03-09 2018-08-31 腾讯科技（深圳）有限公司 Lane line data processing method, device, computer equipment and storage medium
CN109733392A (en) * 2019-01-30 2019-05-10 浙江吉利汽车研究院有限公司 A kind of barrier-avoiding method and device
CN109949611A (en) * 2019-03-28 2019-06-28 百度在线网络技术（北京）有限公司 The lane change method, apparatus and storage medium of unmanned vehicle
CN110136222A (en) * 2019-04-17 2019-08-16 百度在线网络技术（北京）有限公司 Virtual lane line generation method, apparatus and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108470159A (en) * 2018-03-09 2018-08-31 腾讯科技（深圳）有限公司 Lane line data processing method, device, computer equipment and storage medium
CN109733392A (en) * 2019-01-30 2019-05-10 浙江吉利汽车研究院有限公司 A kind of barrier-avoiding method and device
CN109949611A (en) * 2019-03-28 2019-06-28 百度在线网络技术（北京）有限公司 The lane change method, apparatus and storage medium of unmanned vehicle
CN110136222A (en) * 2019-04-17 2019-08-16 百度在线网络技术（北京）有限公司 Virtual lane line generation method, apparatus and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
安文娟 等: ""山区低等级公路运行速度修正研究"", 《公路交通技术》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115512541A (en) * 2022-09-20 2022-12-23 浙江大学 Road surface accurate information service system for safe driving of vehicle
CN115512541B (en) * 2022-09-20 2023-09-01 浙江大学 Pavement accurate information service system for safe driving of vehicle

Also Published As

Publication number Publication date
CN110570495B (en) 2023-09-19

Similar Documents

Publication Publication Date Title
CN110550030B (en) Lane changing control method and device for unmanned vehicle, computer equipment and storage medium
CN110119147B (en) Vehicle automatic driving method, device, computer equipment and storage medium
US10417509B2 (en) Variable speed sign value prediction and confidence modeling
US9726505B2 (en) Methods and systems for generating a horizon for use in advanced driver assistance system (ADAS)
CN114270143A (en) Lateral guidance of a vehicle by means of environmental data detected by other vehicles
KR20200100810A (en) Own vehicle location prediction method and autonomous driving device for autonomous driving
CN111256687A (en) Map data processing method and device, acquisition equipment and storage medium
EP3875905B1 (en) Method, device and medium for detecting environmental change
CN112394725B (en) Prediction and reaction field of view based planning for autopilot
JP7371269B2 (en) Method and device for calibrating camera pitch of a car, and method for continuously learning a vanishing point estimation model for the purpose
KR20200095361A (en) Method for providing robust object distance estimation based on camera by performing pitch calibration of camera more precisely with fusion of information acquired through camera and information acquired through v2v communication and device using the same
US11210941B2 (en) Systems and methods for mitigating anomalies in lane change detection
CN114663804A (en) Driving area detection method, device, mobile equipment and storage medium
CN110570495B (en) Virtual lane generation method, device and storage medium
JP5888275B2 (en) Road edge detection system, method and program
CN112078580A (en) Method, device and storage medium for determining the degree of overlap of an object with a driving band
CN110647146A (en) Unmanned vehicle control method and device, computer equipment and storage medium
CN113033267B (en) Vehicle positioning method, device, computer equipment and storage medium
US20220404506A1 (en) Online validation of lidar-to-lidar alignment and lidar-to-vehicle alignment
CN111427331B (en) Perception information display method and device of unmanned vehicle and electronic equipment
CN115690717A (en) Traffic light detection method and device, computing equipment and storage medium
KR102499976B1 (en) Vehicle and control method thereof
CN115668333A (en) Electronic map generation method and device, computer equipment and storage medium
CN110874549A (en) Target visual field determining method, system, computer device and storage medium
CN113034588B (en) Vehicle positioning method, device, computer equipment and storage medium

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