CN116383321A

CN116383321A - Decision environment construction method, device, vehicle and storage medium

Info

Publication number: CN116383321A
Application number: CN202211657711.7A
Authority: CN
Inventors: 杜鹏; 邱利宏; 马晨翔
Original assignee: Chongqing Changan Automobile Co Ltd
Current assignee: Chongqing Changan Automobile Co Ltd
Priority date: 2022-12-22
Filing date: 2022-12-22
Publication date: 2023-07-04

Abstract

The application relates to the technical field of automatic driving automobile decision making, in particular to a decision making environment construction method, a decision making environment construction device, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring a first center line set and a first boundary line set of the road around the vehicle; determining the center line of the lane where the vehicle is currently located from the first center line set according to the current position of the vehicle, and searching a reference center line sequence of the vehicle according to the center line of the lane where the vehicle is currently located; and acquiring the transverse distance between each central line in the reference central line sequence and each boundary line in the first boundary line set, and associating the central line and the boundary line of which the transverse distance meets the association condition to obtain a reference boundary line sequence associated with the reference central line sequence, and constructing a decision environment of the vehicle based on the reference boundary line sequence. Therefore, the method solves the problems that the vehicle does not quickly and accurately construct lane boundary lines and road boundaries associated with the central line based on the crowdsourcing map, prepares for related operation of the automatic driving vehicle, and has certain limitation.

Description

Decision environment construction method, device, vehicle and storage medium

Technical Field

The present disclosure relates to the field of automated driving vehicle decision making technology, and in particular, to a decision making environment construction method, apparatus, vehicle and storage medium.

Background

The automatic driving of the intelligent automobile needs to meet the traffic rules of lane driving and generally runs according to the central line of a road, however, lane changing, obstacle detouring, up-down ramp and the like need to consider the influence of lane boundary lines and road boundaries, the existing high-precision map making needs to rely on high-precision acquisition equipment and a large amount of later manual verification, the drawing cost is high, the period is long, and the application range of the automatic driving is limited, so that the crowdsourcing map is adopted to acquire the relevant information of the road, and the reliability of the automatic driving is realized.

The crowdsourcing map is to detect the change of the surrounding environment, such as lane boundary lines, road boundaries, signboards, traffic lights and the like, in real time by using a large number of vehicle-mounted sensors for acquiring vehicles in a non-professional manner, compare the map with a high-precision map, and upload data to a cloud platform and then issue the data to other vehicles if the road change or other conditions are found, so that the map data can be updated rapidly.

The environment is built through the automatic driving decision module, left and right boundary line selection, middle lane filling and front and rear boundary line connection relation determination can be carried out according to the driving requirements under the scenes of certain divergence and confluence and lane number change, meanwhile, the decision module only carries out the association of the lane boundary lines aiming at the central line matched with navigation, so that the online consumption can be reduced, and the online application is realized.

In the related technology, most manufacturers add a part for manual verification to the processing after crowdsourcing mapping, and find out different information in the crowdsourcing map and the high-precision map manually to verify, so that the information cannot be automatically generated and can not be applied in a large range, and the method has certain limitation and wastes manpower and material resources; and the decision module of automatic driving only carries out the association of lane boundary line based on the high-precision map matching central line, can not know the relevant information of road in real time and causes the security of vehicle to reduce and have certain limitation.

Disclosure of Invention

The application provides a decision environment construction method, a decision environment construction device, a vehicle and a storage medium, which are used for solving the problems that in the related art, the vehicle does not quickly and accurately construct a lane boundary line and a road boundary which are associated with a central line based on a crowdsourcing map, preparation is made for related operation of an automatic driving vehicle, and certain limitation exists.

An embodiment of a first aspect of the present application provides a method for constructing a decision environment, including the following steps: acquiring a first center line set and a first boundary line set of the road around the vehicle; determining the center line of a lane where the vehicle is currently located from the first center line set according to the current position of the vehicle, and searching a reference center line sequence of the vehicle according to the center line of the lane where the vehicle is currently located; and acquiring the transverse distance between each central line in the reference central line sequence and each boundary line in the first boundary line set, associating the central line and the boundary line, of which the transverse distance meets association conditions, to obtain a reference boundary line sequence associated with the reference central line sequence, and constructing a decision environment of the vehicle based on the reference central line sequence and the reference boundary line sequence.

According to the technical means, the method comprises the steps of obtaining a first center line set and a first boundary line set of a road around a vehicle, determining the center line of a lane where a current vehicle is located according to the first center line set, and searching a reference center line sequence of the vehicle; the method for constructing the decision environment model based on the crowdsourcing map can quickly and accurately construct the center line matched with the navigation path and the corresponding lane boundary line sequence required by the decision, and prepare for the subsequent path selection and planning of the vehicle, and has wider application range.

Optionally, the acquiring the lateral distance between each centerline in the reference centerline sequence and each boundary line in the first boundary line set includes: converting the first coordinate of each boundary line in the first boundary line set into a second coordinate under a central line Frenet coordinate system, and calculating the longitudinal distance and the transverse distance between the first point and the last point of each boundary line and the end point of the central line respectively according to the second coordinate; searching a second boundary line set which is longitudinally overlapped with the central line and is not intersected in the first boundary line set according to the longitudinal distance, wherein if the longitudinal distances corresponding to the first point and the last point of the boundary line are all outside the central line terminal point longitudinal coordinate range, it is determined that a longitudinal overlapped area is not present between the boundary line and the central line; if the transverse coordinates corresponding to the first point and the last point are in different quadrants, judging that the boundary line intersects with the central line; and identifying the minimum value of the transverse distances between the first point and the last point in the second boundary line set and the end point of the central line respectively, and determining the transverse distance between each central line and each boundary line in the first boundary line set based on the minimum value.

According to the technical means, the method and the device convert the first coordinate of each boundary line in the first boundary line set into the second coordinate under the central line Frenet coordinate system, calculate the longitudinal and transverse distances between the first and last points of each boundary line and the end points of the central line according to the second coordinate, search the second boundary line set which is longitudinally overlapped with the central line and is not intersected in the first boundary line set based on the longitudinal distances, identify the minimum value of the transverse distances between the first and last points and the end points of the central line, determine the transverse distances between each central line and each boundary line in the first boundary line based on the minimum value, judge the transverse and longitudinal distances by using the Frenet coordinate system, avoid the influence of the bending of the central line on the longitudinal and transverse distance judgment, and ensure the accuracy of the vehicle on path selection and planning.

Optionally, the associating the center line and the boundary line of which the transverse distance meets the association condition to obtain a reference boundary line sequence associated with the reference center line sequence includes: acquiring longitudinal coordinates of a first point and a last point of a boundary line with the minimum transverse distance between the first point and the central line; judging whether the longitudinal coordinates of the first point and the last point are contained in the longitudinal coordinate range of the central line or not; if so, associating the boundary line with the central line, otherwise, searching the longitudinal coordinates of the first point and the last point contained in the longitudinal coordinate range of the central line according to the sequence from small to large of the transverse distance, and storing the boundary line with the minimum transverse distance under the same longitudinal coordinate of the central line until the longitudinal coordinate searching of all searching positions of the central line is completed, so as to obtain the reference boundary line sequence.

According to the technical means, in the embodiment of the application, the longitudinal coordinates of the first and last points of the boundary line with the minimum transverse distance from the central line are obtained, whether the longitudinal coordinates of the first and last points are contained in the longitudinal coordinate range of the central line is judged, if so, the boundary line and the central line are related, if not, the longitudinal coordinates of the first and last points contained in the longitudinal coordinate range of the central line are searched according to the sequence from small to large of the transverse distance, the boundary line with the minimum transverse distance under the same longitudinal coordinate of the central line is stored until the longitudinal coordinate search of all search positions is completed to obtain a reference boundary line sequence, and the lane boundary line and the road boundary near the central line of the vehicle are searched, so that whether the left lane and the right lane are feasible or not is determined, the related search amount can be reduced, the demand on calculation force is reduced, and the accuracy of the path selection and the planning of the vehicle is ensured.

Optionally, the reference boundary line sequence includes a road boundary line sequence and a lane boundary line sequence, the correlation transverse distance satisfies a central line and a boundary line of the correlation condition, and the reference boundary line sequence correlated with the reference central line sequence is obtained, and further includes: and the lane boundary line sequence which is related to the central line and has an overlapping area with the central line and is not intersected is counted into the lane boundary line sequence, so that the lane boundary line sequence with the minimum transverse distance in the longitudinal distance of the central line is obtained.

According to the technical means, the road boundary line sequence associated with the central line is counted into the lane boundary line sequence which has an overlapping area with the central line and is not intersected with the central line, so that the lane boundary line sequence with the smallest transverse distance in the longitudinal distance of the central line is obtained, a general method for quickly searching the smallest transverse distance under the condition of complex longitudinal and transverse distances is provided, the completeness and the accuracy of the result are ensured, and the accuracy of the following vehicle on path selection and planning is ensured.

Optionally, the boundary line includes a lane boundary line, and the searching for the reference center line sequence of the vehicle according to the center line of the lane where the vehicle is currently located includes: identifying an actual type of lane boundary line associated with the center line of the lane in which the current lane is located; if the actual type is the non-crossing type, carrying out subsequent center line searching according to the center line of the current lane and the current navigation path searching to obtain the reference center line sequence; otherwise, the center line of the current lane is related to the center line of the adjacent lane, and the subsequent center line search is performed according to the center line of the current lane, the related center line of the adjacent lane and the current navigation path search, so as to obtain the reference center line sequence.

According to the technical means, the embodiment of the application carries out subsequent central line searching according to the central line of the current lane and the current navigation path searching to obtain the reference central line sequence by identifying the actual type of the lane boundary line related to the central line of the current lane, if the actual type is the non-crossing type, otherwise, carries out subsequent central line searching according to the central line of the current lane and the central line of the related adjacent lane, and carries out subsequent central line searching according to the central line of the current lane, the central line of the related adjacent lane and the current navigation path searching to obtain the reference central line sequence, thereby determining the passable state of the current lane and each side lane, and facilitating the subsequent decision module to carry out selection and path planning of the reference path according to the output reference central line sequence to ensure the safe running of the vehicle.

Optionally, the associating the center line of the adjacent lane according to the center line of the lane where the current is located includes: converting the third coordinate of the center line of the adjacent lane to the fourth coordinate in the Frenet coordinate system of the center line of the lane where the current lane is located; calculating the longitudinal coordinates of the center line of the lane where the vehicle is currently located according to the fourth coordinates, and searching a second center line set containing the position of the vehicle according to the longitudinal coordinates of the first point and the last point in the first center line set; and selecting a center line with the smallest transverse distance in the left-right direction from the second center line set to obtain the center line of the adjacent lane.

According to the technical means, in the embodiment of the application, the third coordinate of the center line of the adjacent lane is converted to the fourth coordinate in the Frenet coordinate system of the center line of the current lane, the longitudinal coordinate of the center line of the current lane is calculated according to the fourth coordinate, the second center line set containing the position of the vehicle is searched according to the longitudinal coordinates of the first point and the last point in the first center line set, the center line with the smallest transverse distance in the left-right direction is selected in the second center line set, the center line of the adjacent lane is obtained, and the accuracy of the following vehicle on path selection and planning is facilitated.

Optionally, before associating the center line and the boundary line, the lateral distance of which satisfies the association condition, the method further comprises: acquiring the longitudinal distance between the vehicle and the central line terminal point of the current lane; and if the longitudinal distance is smaller than the lane change longitudinal length limit value, adding a subsequent central line according to the subsequent central line in the central line attribute until the longitudinal distance is greater than or equal to the lane change longitudinal length limit value, obtaining a third central line set in the longitudinal distance limit value, and carrying out boundary line association based on the third central line set.

According to the technical means, the embodiment of the application obtains the longitudinal distance between the center line terminal points of the lane where the vehicle is located at present from the lane, if the longitudinal distance is smaller than the lane change longitudinal length limit value, the subsequent center line is added according to the subsequent center line in the center line attribute until the longitudinal distance is larger than or equal to the lane change longitudinal length limit value, a third center line set in the longitudinal distance limit value is obtained, boundary line association is carried out based on the third center line set, the association search amount can be reduced according to the reference center line sequences of the current lane and the left and right feasible lanes, the demand on calculation force is reduced, and online deployment is realized.

Optionally, the determining, according to the current position of the vehicle, the center line of the lane where the vehicle is currently located from the first center line set includes: deleting the navigation path according to the lane center line where the vehicle is currently located and the first center line set to obtain a fourth center line set under the navigation path; calculating the central line of the fourth central line set and the central line of the heading of the host vehicle, wherein the deviation angle of the central line and the heading of the host vehicle selects the central line of the heading deviation within a preset range, and a fifth central line set is obtained; and calculating the transverse distance from the current vehicle coordinate to the center line of the fifth center line set, deleting the center line with the smallest transverse distance, and obtaining the center line of the lane where the current vehicle is located.

According to the technical means, the navigation path is deleted according to the current lane center line and the first center line set of the vehicle to obtain the fourth center line set under the navigation path, the center line of which the deviation angle with the heading of the vehicle is within the preset range is calculated to obtain the fifth center line set, the transverse distance from the coordinates of the current vehicle to the center line of the fifth center line set is calculated to delete the center line with the smallest transverse distance to obtain the center line of the current lane, so that the vehicle can accurately judge the current lane center line, the accuracy of path selection and planning of the vehicle is ensured, and the safe running of the vehicle is ensured.

Optionally, the acquiring the first center line set and the first boundary line set of the road around the host vehicle includes: acquiring a crowdsourcing map of the vehicle; and reading a first center line set and a first boundary line set in the preset range of the vehicle from the crowdsourcing map according to the current position of the vehicle.

According to the technical means, the crowd-sourced map of the vehicle is obtained, and the center line set, the road boundary line set and the lane boundary line set in the preset range of the vehicle are read from the crowd-sourced map according to the current position of the vehicle, so that the center line matched with the navigation path and the corresponding lane boundary line set required by decision making can be quickly and accurately constructed, the crowd-sourced map has good universality, and safe running of the vehicle is guaranteed.

An embodiment of a second aspect of the present application provides a decision environment construction apparatus, including: the acquisition module is used for acquiring a first center line set and a first boundary line set of the road around the vehicle; the searching module is used for determining the center line of the lane where the vehicle is currently located from the first center line set according to the current position of the vehicle and searching the reference center line sequence of the vehicle according to the center line of the lane where the vehicle is currently located; the construction module is used for acquiring the transverse distance between each central line in the reference central line sequence and each boundary line in the first boundary line set, associating the central line and the boundary line, the transverse distance of which meets association conditions, to obtain a reference boundary line sequence associated with the reference central line sequence, and constructing a decision environment of the vehicle based on the reference central line sequence and the reference boundary line sequence.

An embodiment of a third aspect of the present application provides a vehicle, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize the decision environment construction method according to the embodiment.

An embodiment of a fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program that is executed by a processor for implementing the decision making environment construction method as described in the above embodiment.

Therefore, the application has at least the following beneficial effects:

(1) According to the method, a first center line set and a first boundary line set of the road around the vehicle are obtained, the center line of a lane where the current vehicle is located is determined according to the first center line set, and a reference center line sequence of the vehicle is searched; the method for constructing the decision environment model based on the crowdsourcing map can quickly and accurately construct the center line matched with the navigation path and the corresponding lane boundary line sequence required by the decision, and prepare for the subsequent path selection and planning of the vehicle, and has wider application range.

(2) According to the method and the device, the first coordinate of each boundary line in the first boundary line set is converted into the second coordinate under the Frenet coordinate system of the central line, the longitudinal and transverse distance between the first and the last points of each boundary line and the end point of the central line is calculated according to the second coordinate, the second boundary line set which is longitudinally overlapped with the central line and is not intersected in the first boundary line set is searched based on the longitudinal distance, the minimum value of the transverse distance between the first and the last points and the end point of the central line is identified, the transverse distance between each central line and each boundary line in the first boundary line is determined based on the minimum value, the Frenet coordinate system is used for judging the transverse and longitudinal distances, the influence of the bending of the central line on the longitudinal and transverse distance judgment can be avoided, and the accuracy of path selection and planning of a vehicle is guaranteed.

(3) In the embodiment of the application, the longitudinal coordinates of the first and last points of the boundary line with the minimum transverse distance from the central line are obtained, whether the longitudinal coordinates of the first and last points are contained in the longitudinal coordinate range of the central line is judged, if so, the boundary line and the central line are related, if not, the longitudinal coordinates of the first and last points contained in the longitudinal coordinate range of the central line are searched according to the sequence from small to large of the transverse distance, the boundary line with the minimum transverse distance under the same longitudinal coordinate of the central line is stored until the longitudinal coordinate searching of all searching positions is completed to obtain a reference boundary line sequence, and the lane boundary and the road boundary near the central line of the vehicle are searched, so that whether the left lane and the right lane are feasible is determined, the related searching amount can be reduced, the demand on calculation force is reduced, the on-line deployment is realized, and the accuracy of the vehicle on path selection and planning is ensured.

(4) According to the method, the lane boundary line sequence which is related to the central line and has the overlapping area with the central line and is disjoint is counted into the lane boundary line sequence, the lane boundary line sequence with the smallest transverse distance in the longitudinal distance of the central line is obtained, the method for quickly searching the smallest transverse distance under the condition that a plurality of common transverse distances and different transverse distances are complex is provided, the completeness and the accuracy of the result are guaranteed, and therefore the accuracy of the following vehicle on path selection and planning is guaranteed.

(5) According to the method and the device, the actual type of the lane boundary line related to the center line of the current lane is identified, if the actual type is the non-crossing type, the subsequent center line search is conducted according to the center line of the current lane and the current navigation path search to obtain the reference center line sequence, otherwise, the subsequent center line search is conducted according to the center line of the current lane and the center line of the related adjacent lane, the reference center line sequence is obtained based on the center line of the current lane, the center line of the related adjacent lane and the current navigation path search, and accordingly the passable state of the current lane and each side lane is determined, and the subsequent decision module can conveniently conduct reference path selection and path planning based on the output reference center line sequence, so that safe running of a vehicle is guaranteed.

(6) According to the method and the device, the third coordinates of the center lines of the adjacent lanes are converted to the fourth coordinates in the Frenet coordinate system of the center line of the current lane, the longitudinal coordinates of the center line of the current lane are calculated according to the fourth coordinates, the second center line set containing the positions of the vehicle is searched according to the longitudinal coordinates of the first point and the last point in the first center line set, the center line with the smallest transverse distance in the left-right direction is selected in the second center line set, the center lines of the adjacent lanes are obtained, and the path selection and planning accuracy of the following vehicles are facilitated.

(7) According to the method and the device for achieving the on-line deployment, the longitudinal distance between the vehicle and the central line terminal points of the current lane is obtained, if the longitudinal distance is smaller than the lane change longitudinal length limit value, the subsequent central line is added according to the subsequent central line in the central line attribute until the longitudinal distance is larger than or equal to the lane change longitudinal length limit value, a third central line set in the longitudinal distance limit value is obtained, boundary line association is carried out based on the third central line set, the associated search amount can be reduced according to the reference central line sequences of the current lane and the left and right feasible lanes, the demand for calculation force is reduced, and on-line deployment is achieved.

(8) According to the method and the device, navigation paths are deleted according to the current lane center line and the first center line set of the vehicle, a fourth center line set under the navigation paths is obtained, the center lines of which the deviation angle with the heading of the vehicle is selected and the heading deviation is in a preset range are calculated, a fifth center line set is obtained, the transverse distance from the coordinates of the current vehicle to the center lines of the fifth center line set is calculated, the center line with the smallest transverse distance is deleted, and the center line of the current lane is obtained, so that the vehicle can accurately judge the center line of the current lane, the accuracy of path selection and planning of the vehicle is guaranteed, and the safe running of the vehicle is guaranteed.

(9) According to the method and the device for obtaining the crowd-sourced map of the vehicle, the center line set, the road boundary line set and the lane boundary line set in the preset range of the vehicle are read from the crowd-sourced map according to the current position of the vehicle, so that the center line matched with the navigation path and the corresponding lane boundary line sequence required by decision making can be quickly and accurately built, the universality is good, and the safe running of the vehicle is guaranteed.

Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

FIG. 1 is a flow chart of a method of decision making environment construction provided in accordance with an embodiment of the present application;

FIG. 2 is a schematic diagram of a crowd sourcing map based decision environment model provided in accordance with an embodiment of the present application;

FIG. 3 is a logic block diagram of a current centerline verification module provided according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an associated centerline verification provided according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a relationship between a center line and a road boundary according to an embodiment of the present application;

FIG. 6 is a logic block diagram of a centerline-associated roadway boundary provided in accordance with an embodiment of the present application;

FIG. 7 is a diagram illustrating a result of associating a road boundary with a center line according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a center line versus lane boundary line provided according to an embodiment of the present application;

FIG. 9 is a logical block diagram of a centerline-associated lane boundary line provided in accordance with an embodiment of the present application;

FIG. 10 is a schematic diagram of a centerline-associated lane boundary line result provided in accordance with an embodiment of the present application;

FIG. 11 is a block diagram of left and right associated centerline search logic provided in accordance with an embodiment of the present application;

FIG. 12 is a diagram of left and right associated centerline search results provided in accordance with an embodiment of the present application;

FIG. 13 is a block diagram of a decision context construction apparatus provided in accordance with an embodiment of the present application;

fig. 14 is a schematic structural view of a vehicle according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.

At present, high-precision map making needs to rely on high-precision acquisition equipment and a large amount of manual verification in the later stage, and is high in drawing cost and long in period, so that the application range of automatic driving is limited. The crowd-sourced map is manufactured by means of the lane boundary, the road boundary, the signboards, the traffic lights and the like which are obtained through repeated sensing by the cameras on the mass production vehicle, the map elements such as the lane boundary, the road boundary, the signboards and the traffic lights are automatically clustered offline, meanwhile, the vehicle driving track is inferred according to the vehicle-mounted inertial navigation, the lane center line is built, manual verification is not needed in the whole process, the drawing cost is greatly reduced, the map freshness is high, the application range of automatic driving is expanded, and intelligent driving can be realized according to the customization of the daily driving route.

The output result of the crowdsourcing map in the embodiment of the application comprises a center line sequence, a lane boundary line sequence, a road boundary sequence, no attributes of roads and lane groups, wherein the center line of the crowdsourcing map is inconsistent with the lane boundary line and the road boundary source, the length of the crowdsourcing map is inconsistent, no association relation exists, each center line is derived from different tracks, and the center lines have no association relation from left to right.

The automatic driving of the intelligent automobile needs to meet the traffic rules of lane driving and generally drives according to the central line of the road, however, lane changing, obstacle detouring, up-down ramp and the like need to consider the influence of lane boundary lines and road boundaries, so that in order to realize reliable driving under a crowdsourcing map, the lane boundary lines and the road boundaries related to the central line need to be constructed based on the crowdsourcing map.

Therefore, the embodiment of the application utilizes the crowdsourcing map to construct decision environment on line, can quickly and completely determine the lane boundary line and the road boundary near the central line, and provides for subsequent path selection and planning.

Decision making environment construction methods, devices, vehicles and storage media of embodiments of the present application are described below with reference to the accompanying drawings. Specifically, fig. 1 is a schematic flow chart of a method for constructing a decision environment according to an embodiment of the present application.

As shown in fig. 1, the decision environment construction method includes the following steps:

in step S101, a first center line set and a first boundary line set of the road around the host vehicle are acquired.

The first center line set may be a set of center lines of a lane where the host vehicle is currently located, which is not specifically limited herein.

The boundary line includes a lane boundary line and a road boundary line, and thus, the first boundary line set may be a sequence of lane boundary lines and road boundary lines of a lane where the host vehicle is currently located, which is not specifically limited herein.

It can be appreciated that the embodiment of the application facilitates the subsequent determination of the center line of the lane where the vehicle is currently located by acquiring the first center line set and the first boundary line set of the road around the vehicle.

In an embodiment of the present application, obtaining a first center line set and a first boundary line set of a road around a host vehicle includes: acquiring a crowdsourcing map of a vehicle; and reading a first center line set and a first boundary line set in a preset range of the vehicle from the crowdsourcing map according to the current position of the vehicle.

The preset range may be a range set by a user, for example: the range of 2km with the vehicle as the center radius can be set or adjusted according to the actual intention of the user, and is not particularly limited herein.

It can be understood that by acquiring the crowdsourcing map of the vehicle, the center line set, the road boundary line set and the lane boundary line set in the vehicle range can be read from the crowdsourcing map according to the current position of the vehicle, so that the center line matched with the navigation path and the corresponding road and lane boundary line set required by decision making can be quickly and accurately constructed, the crowdsourcing map has good universality, and the safe running of the vehicle is ensured.

In step S102, a center line of the lane in which the vehicle is currently located is determined from the first center line set according to the current position of the vehicle, and a reference center line sequence of the vehicle is searched according to the center line of the lane in which the vehicle is currently located.

It can be appreciated that the embodiment of the application determines the center line of the lane where the vehicle is currently located from the first center line set according to the current position of the vehicle, and searches the reference center line sequence of the vehicle so as to facilitate the subsequent construction of the decision making environment of the vehicle.

In an embodiment of the present application, determining, from a first center line set, a center line of a lane where a vehicle is currently located according to a current position of the vehicle includes: deleting the navigation path according to the current lane center line of the vehicle and the first center line set to obtain a fourth center line set under the navigation path; calculating the center line of the fourth center line set and the center line of the heading deviation of the host vehicle in a preset range, so as to obtain a fifth center line set; and calculating the transverse distance from the current vehicle coordinate to the center line of the fifth center line set, deleting the center line with the smallest transverse distance, and obtaining the center line of the current lane.

The preset range may be a range set by a user, for example: the navigation deviation is at a center line of 0.5m, and is not particularly limited herein.

It can be understood that, in the embodiment of the application, the navigation path is deleted according to the current lane center line and the first center line set of the host vehicle, so as to obtain a fourth center line set under the navigation path, calculate the center line of which the deviation angle between the navigation path and the host vehicle heading is within the preset range, select the heading deviation, obtain a fifth center line set, calculate the transverse distance from the coordinates of the current host vehicle to the center line of the fifth center line set, delete the center line with the minimum transverse distance, and obtain the center line of the current lane, so that the vehicle can accurately judge the current lane center line, the accuracy of the vehicle on path selection and planning is ensured, and the safe running of the vehicle is ensured.

In the embodiment of the application, searching a reference center line sequence of a vehicle according to the center line of a lane where the vehicle is currently located comprises: identifying an actual type of lane boundary line associated with a center line of a lane where the lane is currently located; if the actual type is the non-crossing type, carrying out subsequent center line searching according to the center line of the current lane and the current navigation path searching to obtain a reference center line sequence; otherwise, the center line of the current lane is related to the center line of the adjacent lane, and the subsequent center line search is performed according to the center line of the current lane, the related center line of the adjacent lane and the current navigation path search, so as to obtain the reference center line sequence.

The non-straddling type may be a center line of double yellow lines, or white solid lines, etc., which indicate that the side lane is not feasible, and is not specifically limited herein.

It can be understood that, in the embodiment of the present application, by identifying the actual type of the lane boundary line associated with the center line of the current lane, if the actual type is the non-spanable type, the subsequent center line search is performed according to the center line of the current lane and the current navigation path search to obtain the reference center line sequence, otherwise, the subsequent center line search is performed according to the center line of the current lane associated with the center line of the adjacent lane, the center line of the associated adjacent lane and the current navigation path search to obtain the reference center line sequence, so as to determine the passable state of the current lane and each side lane, so that the subsequent decision module can conveniently select the reference path and plan the path based on the output reference center line sequence, thereby ensuring the safe driving of the vehicle.

In the embodiment of the application, associating the center line of the adjacent lane according to the center line of the lane where the current lane is located includes: converting the third coordinate of the center line of the adjacent lane to the fourth coordinate in the Frenet coordinate system of the center line of the lane where the current lane is located; calculating the longitudinal coordinates of the center line of the lane where the vehicle is currently located according to the fourth coordinates, and searching a second center line set containing the position of the vehicle according to the longitudinal coordinates of the first point and the last point in the first center line set; and selecting a center line with the smallest transverse distance in the left-right direction from the second center line set to obtain the center line of the adjacent lane.

The third coordinate may be a global coordinate of the adjacent center line, and the fourth coordinate may be a Frenet coordinate of the center line of the adjacent lane converted to the current center line, which is not specifically limited herein.

It can be understood that in the embodiment of the present application, the third coordinates of the center line of the adjacent lane are converted to the fourth coordinates in the Frenet coordinate system of the center line of the current lane, the longitudinal coordinates of the center line of the current lane are calculated according to the fourth coordinates, the second center line set including the position of the vehicle is searched according to the longitudinal coordinates of the first point and the last point in the first center line set, the center line with the smallest lateral distance in the left-right direction is selected in the second center line set, the center line of the adjacent lane is obtained, and the accuracy of the following vehicle on path selection and planning is facilitated.

In step S103, a lateral distance between each center line in the reference center line sequence and each boundary line in the first boundary line set is obtained, the center lines and the boundary lines of which the lateral distances satisfy the association conditions are associated, a reference boundary line sequence associated with the reference center line sequence is obtained, and a decision environment of the vehicle is constructed based on the reference center line sequence and the reference boundary line sequence.

It can be understood that, in the embodiment of the application, the transverse distance between each central line in the reference central line sequence and each boundary line in the first boundary line set is obtained, the central line and the boundary line with the transverse distance meeting the association condition are associated, the decision environment of the vehicle is built based on the transverse distance, the decision environment model building method based on the crowdsourcing map can quickly and accurately build the central line matched with the navigation path and the corresponding lane boundary line sequence required by the decision, and preparation is made for subsequent path selection and planning of the vehicle, so that the application range is wider.

In an embodiment of the present application, obtaining a lateral distance between each center line in the reference center line sequence and each boundary line in the first boundary line set includes: converting the first coordinate of each boundary line in the first boundary line set into a second coordinate under the central line Frenet coordinate system, and calculating the longitudinal distance and the transverse distance between the first point and the last point of each boundary line and the end point of the central line respectively according to the second coordinate; searching a second boundary line set which is longitudinally overlapped with the central line and is not intersected in the first boundary line set according to the longitudinal distance, wherein if the longitudinal distances corresponding to the first point and the last point of the boundary line are all outside the central line end point longitudinal coordinate range, judging that the longitudinal overlapped area is not present between the boundary line and the central line; if the transverse coordinates corresponding to the first point and the last point are in different quadrants, judging that the boundary line intersects with the central line; a minimum value of the lateral distances between the first and last points in the second set of boundary lines and the end points of the center lines, respectively, is identified, and the lateral distance between each center line and each boundary line in the first set of boundary lines is determined based on the minimum value.

It can be understood that, in the embodiment of the present application, the first coordinate of each boundary line in the first boundary line set is converted into the second coordinate under the central line Frenet coordinate system, and the longitudinal and transverse distance between the first and the last points of each boundary line and the end point of the central line is calculated according to the second coordinate, and the second boundary line set which has an overlapping area with the central line in the longitudinal direction and is not intersected in the first boundary line set is searched based on the longitudinal distance, and the minimum value of the transverse distance between the first and the last points and the end point of the central line is identified, and the transverse distance between each central line and each boundary line in the first boundary line is determined based on the minimum value, so that the influence of the bending of the central line on the longitudinal and the transverse distance judgment can be avoided, and the accuracy of the path selection and the planning of the vehicle is ensured.

In the embodiment of the present application, associating the center line and the boundary line, where the lateral distance meets the association condition, to obtain a reference boundary line sequence associated with the reference center line sequence includes: acquiring longitudinal coordinates of a first point and a last point of a boundary line with the minimum transverse distance between the first point and the central line; judging whether the longitudinal coordinates of the first point and the last point are contained in the longitudinal coordinate range of the central line or not; if so, associating the boundary line with the central line, otherwise, searching the longitudinal coordinates of the first point and the last point contained in the longitudinal coordinate range of the central line according to the sequence from small to large in the transverse distance, and storing the boundary line with the minimum transverse distance under the same longitudinal coordinate of the central line until the longitudinal coordinate searching of all searching positions of the central line is completed, thereby obtaining a reference boundary line sequence.

It can be understood that, in the embodiment of the present application, the longitudinal coordinates of the first and last points of the boundary line with the smallest lateral distance from the center line are obtained, whether the longitudinal coordinates of the first and last points are included in the longitudinal coordinate range of the center line is determined, if so, the boundary line and the center line are associated, if not, the longitudinal coordinates of the first and last points included in the longitudinal coordinate range of the center line are searched according to the order of small to large lateral distances, and the boundary line with the smallest lateral distance under the same longitudinal coordinate of the center line is stored until the search of the longitudinal coordinates of all the search positions is completed to obtain the reference boundary line sequence, and the lane boundary and the road boundary near the center line of the vehicle are searched, thereby determining whether the left lane and the right lane are feasible, reducing the associated search amount, reducing the demand on calculation force, realizing the on-line deployment, and ensuring the accuracy of the path selection and the planning of the vehicle.

In this embodiment of the present application, before associating the center line and the boundary line where the lateral distance meets the association condition, the method further includes: acquiring the longitudinal distance between the vehicle and the central line terminal point of the current lane; if the longitudinal distance is smaller than the lane change longitudinal length limit value, adding a subsequent central line according to the subsequent central line in the central line attribute until the longitudinal distance is greater than or equal to the lane change longitudinal length limit value, obtaining a third central line set in the longitudinal distance limit value, and carrying out boundary line association based on the third central line set.

The longitudinal length limit may be a 2s time interval, and is not particularly limited herein.

It can be understood that, in the embodiment of the present application, the longitudinal distance between the center line end points of the lane where the vehicle is located is obtained, if the longitudinal distance is smaller than the lane change longitudinal length limit value, the subsequent center line is added according to the subsequent center line in the center line attribute until the longitudinal distance is greater than or equal to the lane change longitudinal length limit value, a third center line set in the longitudinal distance limit value is obtained, and based on the third center line set, boundary line association is performed, and according to the reference center line sequences of the current lane and the left and right feasible lanes, the association search amount can be reduced, the demand on calculation force is reduced, and online deployment is realized.

According to the decision environment construction method provided by the embodiment of the application, a first central line set and a first boundary line set of the road around the vehicle are obtained, the central line of the lane where the current vehicle is located is determined according to the first central line set, and a reference central line sequence of the vehicle is searched; the method for constructing the decision environment model based on the crowdsourcing map can quickly and accurately construct the center line matched with the navigation path and the corresponding lane boundary line sequence required by the decision, and prepare for the subsequent path selection and planning of the vehicle, and has wider application range. Therefore, the problems that the vehicle in the related art does not quickly and accurately construct a lane boundary line and a road boundary which are associated with a central line based on a crowdsourcing map, prepares for related operation of an automatic driving vehicle, causes certain limitation and the like are solved.

The architecture of the crowd sourcing map based decision environment model will be described in detail with reference to fig. 2 to 12, specifically as follows:

the crowdsourcing map outputs attributes such as a center line set, a boundary line sequence, a road boundary line sequence, a current center line, whether the center line is matched with navigation or not, a center line following the center line and the like through a map middleware, a decision environment model construction structure diagram is shown in fig. 2, and the embodiment specifically comprises the following six modules:

1. checking the current center line

Because the automatic driving vehicle needs to meet the traffic rules of lane driving, the center line of the automatic driving vehicle is the basis of automatic driving, and the follow-up track planning, lane changing operation and the like are all based on the automatic driving vehicle, so that the center line of the automatic driving vehicle needs to be checked at present.

If the current center line is checked and the result is that the center line with the smallest lateral distance within a certain limit value of the course deviation is selected on the navigation path, the specific logic is as shown in fig. 3: firstly, aiming at a given center line of a current lane and a center line set, deleting a navigation path to obtain a center line set L1 under the navigation path; secondly, calculating a deviation angle between the central line of the central line set L1 and the heading of the vehicle, and selecting the central line of which the heading deviation is in a set range to obtain a central line set L2; and finally, calculating the transverse distance from the current vehicle coordinate to the central line in the central line set L2, deleting the central line with the minimum transverse distance, and outputting the central line as the current central line.

And the schematic diagram of the correlation center line id verification result is shown in fig. 4: after the current central line is obtained, the boundary line and the road boundary related to the central line can be searched.

2. Center line determination within lane change longitudinal distance limits

The map middleware issues a center line set, a road boundary set and a boundary line set within the range of 2km of the vehicle radius, in order to reduce the calculation amount of the association relation between the follow-up center line and the boundary line of the lane, the boundary line of the lane where the vehicle is located is firstly judged, if the boundary line of the lane is a solid line within the set longitudinal length limit of the lane change, the center line search and association in the corresponding direction are not needed, the calculation amount of the search association is reduced, and the longitudinal length limit of the lane change set in the embodiment is 2s time interval.

According to the current central line of the self-vehicle association, if the longitudinal distance from the self-vehicle to the current central line end point is smaller than the set channel-changing longitudinal length limit value, adding a subsequent central line according to the subsequent central line in the central line attribute until the central line set length from the self-vehicle exceeds the set channel-changing longitudinal length limit value. Thus, the center line set L3 within the longitudinal distance limit is obtained, and after the center line set L3 within the lane change longitudinal distance limit is obtained, the road boundary and the lane boundary line in the vicinity of the center line are searched for in the next step.

3. Center line associated road boundary search

(1) The actual road boundary and the central line cannot be completely parallel, even the intersecting condition may occur, the lengths are different, and the conditions of longitudinal complete overlapping, partial overlapping, complete non-overlapping and the like exist, as shown in fig. 5.

The road boundary searching purpose is to obtain a road boundary coordinate point with the smallest transverse distance in the longitudinal distance range of the central line, and to facilitate calculation and represent the relationship between the central line and the road boundary, the influence of the curve on distance judgment is reduced, the global coordinate of the road boundary is changed into Frenet coordinate under the central line, and the longitudinal S and transverse L coordinates of each coordinate point of the road boundary are calculated.

(2) The centerline-associated road boundary logic block diagram is shown in fig. 6, specifically:

firstly, converting the global coordinates of a road boundary into longitudinal S and transverse L coordinates under a central line Frenet coordinate system, calculating the distance between the longitudinal S and the transverse L of the first and the last points of the road boundary, and if the longitudinal S value of the first point and the longitudinal S value of the last point are both out of the central line terminal longitudinal S coordinate range, then no longitudinal overlapping area exists between the road boundary and the central line; if the transverse L values of the first and the last points are different from each other, the boundary line is intersected with the central line. A set B1 of road boundaries having an overlapping region longitudinally with the center line and not intersecting can be obtained as in (1) (2) (3) (4) in fig. 5.

In the road boundary set B1, the minimum value of the lateral distance in the first and last points of each road boundary is taken as the lateral distance of the road boundary from the center line.

Firstly, selecting a road boundary with the smallest transverse distance from a central line, and if the longitudinal S coordinate of the first and last points of the road boundary comprises the longitudinal S range of the central line, directly outputting the road boundary coordinate in the longitudinal range of the central line; otherwise, continuously searching the road boundary with the second small transverse distance, judging the relation between the longitudinal S coordinates of the first and last points of the road boundary and the longitudinal S coordinates of the central line and the S coordinates of the first and last points of the associated road boundary, storing the road boundary coordinate point with the smallest transverse distance under the same longitudinal S coordinates until the longitudinal S coordinates of the central line are searched, exiting the road boundary search, and outputting the road boundary coordinate point associated with the central line. The result of the center line association with the road boundary is shown in fig. 7.

4. Center line associated lane boundary line search

(1) In the actual scene, there is a situation that the road boundary is not provided with a lane boundary line, so that the road boundary is required to be used as a virtual lane boundary line to perform joint search with the rest lane boundary lines, and the constraint of the vehicle driving lane is ensured.

The relationship between the actual lane boundary line and the center line may also have a state of complete longitudinal overlap, partial overlap, complete non-overlap, or even equal, as shown in fig. 8, specifically:

the lane boundary line searching purpose is to obtain lane boundary line coordinate points with the smallest transverse distance in the longitudinal distance range of the central line, and also to avoid the influence of the bending line on the distance judgment, the global coordinates are changed into Frenet coordinates, and the longitudinal S and transverse L coordinates of each coordinate point of the lane boundary line under the central line Frenet coordinate system are calculated.

(2) The centerline-associated road boundary logic block diagram is shown in fig. 9, specifically:

and 3, the step of associating the central line with the lane boundary is consistent with the step of associating the central line with the lane boundary, wherein the step is carried out according to the step 3, and the difference is that the lane boundary with the central line which is already associated with the associated lane boundary is added into a lane line sequence Li1 which has an overlapping area with the central line and does not intersect, and finally, the lane boundary coordinate point with the minimum transverse distance is output within the longitudinal S distance of the central line.

And output as a lane boundary line coordinate point associated with the center line, the association result is schematically shown in fig. 10.

5. Left-right associated centerline search

A logical block diagram of left and right associated centerline searches is shown in fig. 11.

If the lane boundary line on the side of the center line in the center line set L3 is of a type such as a solid line which cannot be spanned, and the side lane is not feasible, the search for the corresponding side center line is not required, and the lane passable state on each side can be obtained.

And searching the center line in the corresponding direction according to the traffic state of the lanes on the left side and the right side. And converting global coordinates of adjacent central lines into Frenet coordinates of the current central line, calculating longitudinal S coordinates of the vehicle on the central line, searching a central line set L4 containing the vehicle position in the central line set L1 according to the longitudinal S coordinates of the head and tail points of the central line, and finally selecting the central line with the smallest transverse distance in the left-right direction in the central line set L4 to obtain a feasible central line in the left-right direction.

And a schematic of the left and right associated centerline search results is shown in fig. 12.

6. Reference centerline sequence search

And after obtaining the center line of the own vehicle and the feasible center lines on the left side and the right side, searching the reference center line sequence according to the center line attribute, the subsequent center line and whether the navigation path is on. When there are multiple subsequent centerlines of a centerline, then there are also multiple sets of corresponding reference centerline sequences.

After the reference center line sequence is obtained, carrying out matching search on the road boundary and the lane boundary line of each center line, and finally outputting the road boundary sequence and the lane boundary line sequence corresponding to the center line set.

So far, the construction of the decision environment model based on the crowdsourcing map is completed, and the subsequent decision module carries out the selection of a reference path and the path planning based on the output reference center line sequence and the corresponding road boundary and lane boundary line.

In sum, the embodiment of the application determines whether the left lane and the right lane are feasible or not by searching the lane boundary line and the road boundary near the center line of the own vehicle, and only searches the left, middle and right feasible lanes backwards, so that the matching search amount of the center line association relationship can be reduced; the global coordinate is converted into the Frenet coordinate system of the central line for judgment, so that the influence of the bending of the central line on the distance judgment can be avoided; the transverse distance is selected as the basis of association of the road boundary and the lane center line, so that the universal search under the complex condition of a plurality of lane lines with different longitudinal and transverse distances is realized, the completeness and the correctness of the key transverse constraint are ensured, and the algorithm has universality and is beneficial to modularized development. The method for constructing the decision environment model based on the crowdsourcing map can quickly and accurately construct a center line matched with a navigation path and a corresponding lane boundary line sequence required by decision making.

Next, a decision environment construction apparatus according to an embodiment of the present application will be described with reference to the accompanying drawings.

FIG. 13 is a block schematic diagram of a decision making environment building apparatus of an embodiment of the present application.

As shown in fig. 13, the decision environment construction apparatus 10 includes: an acquisition module 100, a search module 200, and a construction module 300.

The acquiring module 100 is configured to acquire a first center line set and a first boundary line set of a road around the host vehicle; the searching module 200 is configured to determine a center line of a lane where the vehicle is currently located from the first center line set according to a current position of the vehicle, and search a reference center line sequence of the vehicle according to the center line of the lane where the vehicle is currently located; the construction module 300 is configured to obtain a lateral distance between each center line in the reference center line sequence and each boundary line in the first boundary line set, correlate the center line and the boundary line that the lateral distance satisfies the correlation condition, obtain a reference boundary line sequence correlated with the reference center line sequence, and construct a decision environment of the vehicle based on the reference center line sequence and the reference boundary line sequence.

It should be noted that the foregoing explanation of the embodiment of the decision environment construction method is also applicable to the decision environment construction device of this embodiment, and will not be repeated here.

According to the decision environment construction device provided by the embodiment of the application, a first central line set and a first boundary line set of a road around a vehicle are obtained, the central line of a lane where a current vehicle is positioned is determined according to the first central line set, and a reference central line sequence of the vehicle is searched; the method for constructing the decision environment model based on the crowdsourcing map can quickly and accurately construct the center line matched with the navigation path and the corresponding lane boundary line sequence required by the decision, and prepare for the subsequent path selection and planning of the vehicle, and has wider application range. Therefore, the problems that the vehicle in the related art does not quickly and accurately construct a lane boundary line and a road boundary which are associated with a central line based on a crowdsourcing map, prepares for related operation of an automatic driving vehicle, causes certain limitation and the like are solved.

Fig. 14 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle may include:

memory 1401, processor 1402, and a computer program stored on memory 1401 and executable on processor 1402.

The processor 1402 implements the decision context construction method provided in the above embodiments when executing a program.

Further, the vehicle further includes:

a communication interface 1403 for communication between the memory 1401 and the processor 1402.

A memory 1401 for storing a computer program executable on a processor 1402.

The memory 1401 may include high-speed RAM (Random Access Memory ) memory, and may also include non-volatile memory, such as at least one disk memory.

If the memory 1401, the processor 1402, and the communication interface 1403 are implemented independently, the communication interface 1403, the memory 1401, and the processor 1402 can be connected to each other through a bus and perform communication with each other. The bus may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component, external device interconnect) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 14, but not only one bus or one type of bus.

Alternatively, in a specific implementation, if the memory 1401, the processor 1402, and the communication interface 1403 are integrated on a chip, the memory 1401, the processor 1402, and the communication interface 1403 may perform communication with each other through internal interfaces.

The processor 1402 may be a CPU (Central Processing Unit ) or ASIC (Application Specific Integrated Circuit, application specific integrated circuit) or one or more integrated circuits configured to implement embodiments of the present application.

The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the above decision making environment construction method.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless explicitly defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable gate arrays, field programmable gate arrays, and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims

1. The decision environment construction method is characterized by comprising the following steps:

acquiring a first center line set and a first boundary line set of the road around the vehicle;

determining the center line of a lane where the vehicle is currently located from the first center line set according to the current position of the vehicle, and searching a reference center line sequence of the vehicle according to the center line of the lane where the vehicle is currently located;

and acquiring the transverse distance between each central line in the reference central line sequence and each boundary line in the first boundary line set, associating the central line and the boundary line, of which the transverse distance meets association conditions, to obtain a reference boundary line sequence associated with the reference central line sequence, and constructing a decision environment of the vehicle based on the reference central line sequence and the reference boundary line sequence.

2. The method of claim 1, wherein the obtaining the lateral distance between each centerline in the sequence of reference centerlines and each boundary line in the first set of boundary lines comprises:

converting the first coordinate of each boundary line in the first boundary line set into a second coordinate under a central line Frenet coordinate system, and calculating the longitudinal distance and the transverse distance between the first point and the last point of each boundary line and the end point of the central line respectively according to the second coordinate;

searching a second boundary line set which is longitudinally overlapped with the central line and is not intersected in the first boundary line set according to the longitudinal distance, wherein if the longitudinal distances corresponding to the first point and the last point of the boundary line are all outside the central line terminal point longitudinal coordinate range, it is determined that a longitudinal overlapped area is not present between the boundary line and the central line; if the transverse coordinates corresponding to the first point and the last point are in different quadrants, judging that the boundary line intersects with the central line;

and identifying the minimum value of the transverse distances between the first point and the last point in the second boundary line set and the end point of the central line respectively, and determining the transverse distance between each central line and each boundary line in the first boundary line set based on the minimum value.

3. The method according to claim 2, wherein the correlating the center line and the boundary line of the lateral distance satisfying the correlation condition to obtain the reference boundary line sequence correlated with the reference center line sequence includes:

acquiring longitudinal coordinates of a first point and a last point of a boundary line with the minimum transverse distance between the first point and the central line;

judging whether the longitudinal coordinates of the first point and the last point are contained in the longitudinal coordinate range of the central line or not;

if so, associating the boundary line with the central line, otherwise, searching the longitudinal coordinates of the first point and the last point contained in the longitudinal coordinate range of the central line according to the sequence from small to large of the transverse distance, and storing the boundary line with the minimum transverse distance under the same longitudinal coordinate of the central line until the longitudinal coordinate searching of all searching positions of the central line is completed, so as to obtain the reference boundary line sequence.

4. A method according to claim 3, wherein the reference boundary line sequence comprises a road boundary line sequence and a lane boundary line sequence, the associating the center line and the boundary line of which the lateral distance satisfies the association condition, obtaining the reference boundary line sequence associated with the reference center line sequence, further comprises:

And the lane boundary line sequence which is related to the central line and has an overlapping area with the central line and is not intersected is counted into the lane boundary line sequence, so that the lane boundary line sequence with the minimum transverse distance in the longitudinal distance of the central line is obtained.

5. The method of claim 1, wherein the boundary line comprises a lane boundary line, the searching for a reference center line sequence of the vehicle based on a center line of the current lane comprises:

identifying an actual type of lane boundary line associated with the center line of the lane in which the current lane is located;

if the actual type is the non-crossing type, carrying out subsequent center line searching according to the center line of the current lane and the current navigation path searching to obtain the reference center line sequence;

otherwise, the center line of the current lane is related to the center line of the adjacent lane, and the subsequent center line search is performed according to the center line of the current lane, the related center line of the adjacent lane and the current navigation path search, so as to obtain the reference center line sequence.

6. The method of claim 5, wherein said associating the center line of the adjacent lane according to the center line of the current lane comprises:

Converting the third coordinate of the center line of the adjacent lane to the fourth coordinate in the Frenet coordinate system of the center line of the lane where the current lane is located;

calculating the longitudinal coordinates of the center line of the lane where the vehicle is currently located according to the fourth coordinates, and searching a second center line set containing the position of the vehicle according to the longitudinal coordinates of the first point and the last point in the first center line set;

and selecting a center line with the smallest transverse distance in the left-right direction from the second center line set to obtain the center line of the adjacent lane.

7. The method of claim 1, further comprising, prior to associating the centerline and boundary line at which the lateral distance satisfies the association condition:

acquiring the longitudinal distance between the vehicle and the central line terminal point of the current lane;

and if the longitudinal distance is smaller than the lane change longitudinal length limit value, adding a subsequent central line according to the subsequent central line in the central line attribute until the longitudinal distance is greater than or equal to the lane change longitudinal length limit value, obtaining a third central line set in the longitudinal distance limit value, and carrying out boundary line association based on the third central line set.

8. The method of claim 1, wherein determining a center line of a lane in which the vehicle is currently located from the first set of center lines based on the current position of the vehicle comprises:

Deleting the navigation path according to the lane center line where the vehicle is currently located and the first center line set to obtain a fourth center line set under the navigation path;

calculating the central line of the fourth central line set and the central line of the heading of the host vehicle, wherein the deviation angle of the central line and the heading of the host vehicle selects the central line of the heading deviation within a preset range, and a fifth central line set is obtained;

and calculating the transverse distance from the current vehicle coordinate to the center line of the fifth center line set, deleting the center line with the smallest transverse distance, and obtaining the center line of the lane where the current vehicle is located.

9. The method of claim 1, wherein the obtaining the first set of centerlines and the first set of boundary lines for the roadway around the host vehicle comprises:

acquiring a crowdsourcing map of the vehicle;

and reading a first center line set and a first boundary line set in the preset range of the vehicle from the crowdsourcing map according to the current position of the vehicle.

10. A decision making environment construction apparatus, comprising:

the acquisition module is used for acquiring a first center line set and a first boundary line set of the road around the vehicle;

the searching module is used for determining the center line of the lane where the vehicle is currently located from the first center line set according to the current position of the vehicle and searching the reference center line sequence of the vehicle according to the center line of the lane where the vehicle is currently located;

The construction module is used for acquiring the transverse distance between each central line in the reference central line sequence and each boundary line in the first boundary line set, associating the central line and the boundary line, the transverse distance of which meets association conditions, to obtain a reference boundary line sequence associated with the reference central line sequence, and constructing a decision environment of the vehicle based on the reference central line sequence and the reference boundary line sequence.

11. A vehicle, characterized by comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the decision environment construction method according to any of claims 1-9.

12. A computer readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor for implementing the decision environment construction method according to any of claims 1-9.