CN117664157A - Determination method, device, equipment, medium and vehicle of high-precision navigation path - Google Patents

Determination method, device, equipment, medium and vehicle of high-precision navigation path Download PDF

Info

Publication number
CN117664157A
CN117664157A CN202211012896.6A CN202211012896A CN117664157A CN 117664157 A CN117664157 A CN 117664157A CN 202211012896 A CN202211012896 A CN 202211012896A CN 117664157 A CN117664157 A CN 117664157A
Authority
CN
China
Prior art keywords
precision
road
road section
score
precision road
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.)
Pending
Application number
CN202211012896.6A
Other languages
Chinese (zh)
Inventor
张明星
陈子晗
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.)
Beijing Chusudu Technology Co ltd
Original Assignee
Beijing Chusudu Technology Co 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 Beijing Chusudu Technology Co ltd filed Critical Beijing Chusudu Technology Co ltd
Priority to CN202211012896.6A priority Critical patent/CN117664157A/en
Priority to PCT/CN2022/114698 priority patent/WO2024040499A1/en
Publication of CN117664157A publication Critical patent/CN117664157A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30Map- or contour-matching
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968Systems involving transmission of navigation instructions to the vehicle
    • G08G1/0969Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Navigation (AREA)

Abstract

The embodiment of the invention discloses a method, a device, equipment, a medium and a vehicle for determining a high-precision navigation path, wherein the method comprises the following steps: acquiring a traditional navigation path provided by a traditional navigation map, and matching the traditional navigation path with a high-precision map; in the matching process, determining a high-precision road section corresponding to each track point of the integrated navigation path in the high-precision map, wherein the corresponding high-precision road section comprises a first high-precision road section which is matched with each track point in a determining way and a second high-precision road section which is possibly matched with each track point; and screening a plurality of target high-precision road sections with continuous topological relations from the first high-precision road section and the second high-precision road section, and generating a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road sections, wherein the starting road section and the ending road section of the high-precision navigation path are both the first high-precision road section, and the accuracy of the matching result of the traditional navigation path and the high-precision map is improved by adopting the technical scheme.

Description

Determination method, device, equipment, medium and vehicle of high-precision navigation path
Technical Field
The embodiment of the invention relates to the technical field of automatic driving, in particular to a method, a device, equipment, a medium and a vehicle for determining a high-precision navigation path.
Background
At present, in the automatic driving process, because real-time road condition information does not exist in the high-precision map, the navigation function is difficult to directly provide, so in the actual application process of the high-precision map, the traditional navigation path obtained from the traditional navigation map is required to be matched on the high-precision map, and therefore the automatic driving mode of a vehicle end is judged to be started on which road sections and the manual taking over is required on which road sections.
In the related art, a hidden markov model is generally used to match a high-precision navigation map with a conventional navigation path. In the matching process, it is necessary to find a high-precision road segment that is determined to match each track point in the conventional navigation map, and then connect the observed high-precision road segments through the topological connection relationship of the roads. However, due to different manufacturing processes of different maps, inconsistent labels or differences of position accuracy and the like, the matching scheme of the related art can cause a missing matching phenomenon on some high-precision road sections, namely the compatibility of the matching scheme in the related art is poor, and the matching result is still to be improved.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment, a medium and a vehicle for determining a high-precision navigation path, which improve the accuracy of a traditional navigation path and a high-precision map matching result.
The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for determining a high-precision navigation path, including:
acquiring a traditional navigation path provided by a traditional navigation map, and matching the traditional navigation path with a high-precision map;
in the matching process, determining a high-precision road section corresponding to each track point of the integrated navigation path in the high-precision map, wherein the corresponding high-precision road section comprises a first high-precision road section which is matched with each track point in a determining way and a second high-precision road section which is possibly matched with each track point;
screening a plurality of target high-precision road sections with continuous topological relations from the first high-precision road section and the second high-precision road section, and generating a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road sections, wherein a starting road section and an ending road section of the high-precision navigation path are both the first high-precision road section;
the first high-precision road section is a high-precision road section meeting all the following matching conditions, and the second high-precision road section is a high-precision road section meeting any one or two of the following matching conditions, wherein the matching conditions comprise: for any one current track point, the label information of the traditional navigation path corresponding to the current track point is consistent with the label information, the position information and the angle information of the high-precision road section corresponding to the current track point.
According to the scheme, for the high-precision road section which cannot meet all the matching conditions, namely, for the high-precision road section which is possibly matched with the track points in the traditional navigation path, the embodiment of the invention reserves the observation information of the high-precision road section, combines the observation information and the topological connection relation between the high-precision road section and other road sections to obtain the high-precision navigation path matched with the traditional navigation path, avoids the phenomenon of mismatching or missed matching caused by removing the observation information which is possibly matched with the track points in the traditional navigation path, and enables the matching result of the traditional navigation path and the high-precision map to be compatible with the process error, the angle error and the precision error between the traditional navigation map and the high-precision map, and the matching result is more accurate.
Optionally, selecting a plurality of target fine segments with continuous topological relations from the first high-fine segment and the second high-fine segment includes:
scoring the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section, wherein the first observation score is larger than the second observation score;
Respectively scoring transition probabilities of a first high-precision road section and a second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section, wherein the second transition probability score is smaller than the first transition probability score;
for any one current track point, starting from a first high-precision road section which can be observed by the current track point, taking a transition probability score of the first high-precision road section as a weight value, and weighting the observed score of the first high-precision road section based on the weight value to obtain a Viterbi score of the first high-precision road section;
sequentially taking the obtained Viterbi score as an observation score of the next candidate continuous high-precision road section, and continuously executing Viterbi score calculation operation on the candidate continuous high-precision road section based on a transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the last first high-precision road section which can be observed by the last track point is obtained through calculation, wherein the candidate continuous high-precision road section is the first high-precision road section or the second high-precision road section;
And selecting the Viterbi score with the largest value from the plurality of Viterbi scores obtained by calculation, and taking a plurality of continuous high-precision road segments corresponding to the Viterbi score with the largest value as a plurality of target precision road segments with continuous topological relations.
According to the scheme, the second transition probability score is set to be smaller than the first transition probability score, so that the weight of the high-precision road section which is matched with each track point in the whole high-precision navigation path can be increased, and the weight of the high-precision road section which is possibly matched with each track point in the whole high-precision navigation path can be reduced, so that the accuracy of a matching result is improved.
According to the scheme, the screening process can be simplified by adopting the mode of scoring the observed value and the transition probability value and calculating the Viterbi score, and the high-precision road section continuous with the current high-precision road section can be efficiently screened.
Optionally, scoring the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section, including:
scoring the observed value of each first high-precision road segment as 1, and scoring the observed value of each second high-precision road segment as 0.5; in a corresponding manner,
Respectively scoring the transition probabilities of the first high-precision road section and the second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section, wherein the method comprises the following steps:
for any one current high-precision road section, if the observation score of a high-precision road section which is continuous with the current high-precision road section is 1, and when the candidate continuous high-precision road section and the current high-precision road section are the same road section, the transition probability score of the candidate continuous high-precision road section is scored as 1+E, wherein E is a minimum value larger than 0; or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 1+2E; or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is not topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 0; or,
If the observed score of the high-precision road segment continuous with the current high-precision road segment candidate is 0.5, the transition probability score of the high-precision road segment continuous with the candidate is scored as 1.
According to the scheme, for the candidate continuous high-precision road section with the observation score of 1, if the candidate continuous high-precision road section is the same road section as the current high-precision road section, the transition probability score of the candidate continuous high-precision road section is scored as 1+E, and if the candidate continuous high-precision road section is the next road section capable of being in topological connection with the current high-precision road section, the transition probability score of the candidate continuous high-precision road section is scored as 1+2E slightly larger than the transition score of the same road section, and the topologically connectable road section and the same road section are separated, so that the process of observing and searching the next road section is continuously carried out, and the head and tail positions of the road sections can be ensured to be in correct matching connection.
Alternatively, in the case where the observed score of the high-precision road segment selected continuously from the current high-precision road segment is 1 and the transition probability score of the candidate continuous high-precision road segment is 0:
and taking the current high-precision road section as the ending road section of the matched path, taking the high-precision road section continuous with the candidate as the starting road section of the next matched path, and continuously executing scoring operation for the transition probability score according to the topological relation of the high-precision road section and the observation scores of different road sections.
According to the scheme, when the transition probability of the candidate continuous high-precision road section is 0, the situation that the candidate continuous high-precision road section is disconnected from the current high-precision road section, namely, the matching result is discontinuous, is indicated. This is because the high-precision map itself may not be complete, and the road network may be missing, so that discontinuities may occur in the true matching result. The embodiment scores 0 for the transition probability score of the next candidate road segment which does not have the topological connection relationship with the current high-precision road segment, and is compatible with the situation of high-precision map road network missing.
Optionally, the method provided by the embodiment of the invention further includes:
according to the topological relation of the road network, identifying a transverse insertion road section in the traditional navigation path, wherein the transverse insertion road section is as follows: the method comprises the steps that a topological connection relation does not exist between a target observation road section which can be observed by at least two continuous track points in a traditional navigation path, and the navigation road section corresponding to the at least two continuous track points is arranged under the condition that the target observation road section is not a road entrance road section, a non-road starting road section and a non-road ending road section;
correcting the observation scores of the high-precision road sections which can be observed by the track points corresponding to the transverse road sections into second observation scores;
Correspondingly, according to the topological relation of the high-precision road section and the observation scores of different road sections, the transition probabilities of the first high-precision road section and the second high-precision road section are respectively scored, and the method comprises the following steps:
and respectively scoring the transition probabilities of the first high-precision road sections and the second high-precision road sections according to the topological relation of the high-precision road sections and the observation scores corrected by different road sections.
According to the scheme, the transverse road section in the traditional navigation path is identified through the topological relation, the observation score of the target observation road section which can be observed by the transverse road section is corrected to be 0.5, the possibility that the target observation road section serves as the starting point and the end point of the final matching path is eliminated, and the problem of mismatching of the transverse road section is solved.
Optionally, before the transition probability scoring is performed on each first high-precision road segment and each second high-precision road segment according to the topological relation of the high-precision road segments and the observation scores corrected by different road segments, the method provided by the embodiment of the invention further includes:
and according to the direction opposite to the traditional navigation path, starting to search whether an entrance road section exists from a target observation road section which can be observed by a track point of the transverse road section, if the entrance road section can be searched, correcting the observation scores of all high-precision road sections between the target observation road section and the entrance road section to be a second observation score, and correcting the observation scores corresponding to the entrance road section to be a first observation score.
According to the scheme, in the observation process, the observation scores of the entrance road sections and the observation scores of all high-precision road sections from the target observation road section to the entrance road section, which can be observed by the track points of the crossroad road sections, are corrected through the road topology relationship, so that the problem that the accuracy of the high-precision map and the accuracy of the entrance of the traditional navigation path is overlarge is solved, and the accuracy of the matching result is further ensured.
Optionally, the consistent position information means that the track point of the traditional navigation path has an intersection point with the road range corresponding to the high-precision road section;
under the condition that the traditional navigation path passes through the urban road intersection, the road range corresponding to the urban road intersection is as follows: sharing the same road range for all high-precision road sections in the urban road junction; or,
in the case where the conventional navigation path passes through a non-bidirectional road including two road edge lines, the road range corresponding to the non-bidirectional road is: the road boundaries of each high-precision road section are connected end to obtain the road boundary; or,
in the case where the conventional navigation path passes through a bidirectional road including only one road edge line, the road range corresponding to the bidirectional road is: the high-precision map is formed by connecting the road edge line of the current bidirectional road and the edge line of the opposite-side bidirectional road end to end, wherein the opposite-side bidirectional road is a bidirectional road adjacent to the current bidirectional road and opposite to the current bidirectional road in the high-precision map.
Optionally, for a starting section of the high-precision navigation path, a proportion of a first high-precision section within a first distance threshold range from the starting section reaches a first proportion threshold;
for the ending road section of the high-precision navigation path, the proportion of the first high-precision road section within a second distance threshold range from the ending road section reaches a second proportion threshold.
According to the technical scheme, the accuracy of the matching result can be further ensured by increasing the proportion of the high-precision road section which is determined to be matched between the starting road section and the ending road section of the high-precision navigation path.
Optionally, the fact that the label of the traditional navigation path corresponding to the current track point is consistent with the label information of the high-precision road section corresponding to the current track point means that: the labels of the traditional navigation paths corresponding to the third distance threshold range before and after the current track point are consistent with the label information of the high-precision road section corresponding to the current track point.
According to the technical scheme, the setting of the third distance threshold can be compatible with the problem that a certain gap exists between the high-precision map and the position of an entrance road section caused by the difference of manufacturing processes of the traditional navigation map.
In a second aspect, an embodiment of the present invention further provides a device for determining a high-precision navigation path, including:
The traditional navigation path acquisition module is configured to acquire a traditional navigation path provided by a traditional navigation map and match the traditional navigation path with the high-precision map;
an observation module configured to determine, in a matching process, a high-precision road segment corresponding to each of the track points of the conventional navigation path in a high-precision map, the corresponding high-precision road segment including a first high-precision road segment that is determined to be matched with each of the track points and a second high-precision road segment that is likely to be matched with each of the track points;
the matching module is configured to screen out a plurality of target high-precision road sections with continuous topological relations from the first high-precision road section and the second high-precision road section, and generate a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road sections, wherein a starting road section and an ending road section of the high-precision navigation path are both the first high-precision road section;
the first high-precision road section is a high-precision road section meeting all the following matching conditions, and the second high-precision road section is a high-precision road section meeting any one or two of the following matching conditions, wherein the matching conditions comprise: for any one current track point, the label information of the traditional navigation path corresponding to the current track point is consistent with the label information, the position information and the angle information of the high-precision road section corresponding to the current track point.
Optionally, the matching module includes:
the observation value scoring unit is configured to score the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section, wherein the first observation score is larger than the second observation score;
the transition probability value scoring unit is configured to score transition probabilities of the first high-precision road section and the second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections, so as to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section, wherein the second transition probability score is smaller than the first transition probability score;
the Viterbi score calculating unit is configured to, for any one current track point, start from a first high-precision road section which can be observed by the current track point, take a transition probability score of the first high-precision road section as a weight value, and weight the observed score of the first high-precision road section based on the weight value to obtain a Viterbi score of the first high-precision road section; sequentially taking the obtained Viterbi score as an observation score of the next candidate continuous high-precision road section, and continuously executing Viterbi score calculation operation on the candidate continuous high-precision road section based on the transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the last first high-precision road section which can be observed by the last track point is obtained through calculation;
A target fine segment determining unit configured to select a viterbi score value having a largest value from the plurality of viterbi scores obtained by calculation, and to use a plurality of continuous high-fine segments corresponding to the viterbi score value having the largest value as a plurality of target fine segments having a continuous topological relation;
and a high-precision navigation path generation unit configured to generate a high-precision navigation path matched with the conventional navigation path according to a plurality of continuous target high-precision road segments.
Optionally, the observation scoring unit is specifically configured to:
scoring the observed value of each first high-precision road segment as 1, and scoring the observed value of each second high-precision road segment as 0.5; in a corresponding manner,
the transition probability value scoring unit is specifically configured to:
for any one current high-precision road section, if the observation score of a high-precision road section which is continuous with the current high-precision road section is 1, and when the candidate continuous high-precision road section and the current high-precision road section are the same road section, the transition probability score of the candidate continuous high-precision road section is scored as 1+E, wherein E is a minimum value larger than 0; or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 1+2E; or,
If the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is not topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 0; or,
if the observed score of the high-precision road segment continuous with the current high-precision road segment candidate is 0.5, the transition probability score of the high-precision road segment continuous with the candidate is scored as 1.
Optionally, in the case that the observation score of the current high-precision road segment selecting the continuous high-precision road segment is 1, and the transition probability score of the candidate continuous high-precision road segment is 0:
and taking the current high-precision road section as the ending road section of the matched path, taking the high-precision road section continuous with the candidate as the starting road section of the next matched path, and continuously executing scoring operation for the transition probability score according to the topological relation of the high-precision road section and the observation scores of different road sections.
Optionally, the device provided by the embodiment of the present invention further includes:
the system comprises a cross road section identification module, a navigation module and a navigation module, wherein the cross road section identification module is configured to identify a cross road section in a traditional navigation path according to the topological relation of a road network, and the cross road section is: the method comprises the steps that a topological connection relation does not exist between a target observation road section which can be observed by at least two continuous track points in a traditional navigation path, and the navigation road section corresponding to the at least two continuous track points is arranged under the condition that the target observation road section is not a road entrance road section and is also a starting road section and an ending road section of a non-road;
The first observation score correction module is configured to correct the observation scores of the high-precision road sections which can be observed by the track points corresponding to the transverse road sections into second observation scores;
correspondingly, the transition probability value scoring unit comprises:
and the transition probability value scoring subunit is configured to score the transition probability of each first high-precision road segment and each second high-precision road segment according to the topological relation of the high-precision road segments and the observation scores corrected by different road segments.
Optionally, the device provided by the embodiment of the present invention further includes:
the second observation score correction module is specifically configured to, before scoring the transition probabilities of the first high-precision road segments and the second high-precision road segments according to the topological relation of the high-precision road segments and the observation scores after correction of different road segments, search whether an entrance road segment exists from a target observation road segment which can be observed by a track point of a cross road segment according to a direction opposite to a traditional navigation path, and if the entrance road segment can be found, correct the observation scores of all the high-precision road segments between the target observation road segment and the entrance road segment to be second observation scores and correct the observation scores corresponding to the entrance road segment to be first observation scores.
Optionally, the consistent position information means that the track point of the traditional navigation path has an intersection point with the road range corresponding to the high-precision road section;
under the condition that the traditional navigation path passes through the urban road intersection, the road range corresponding to the urban road intersection is as follows: sharing the same road range for all high-precision road sections in the urban road junction; or,
in the case where the conventional navigation path passes through a non-bidirectional road including two road edge lines, the road range corresponding to the non-bidirectional road is: the road boundaries of each high-precision road section are connected end to obtain the road boundary; or,
in the case where the conventional navigation path passes through a bidirectional road including only one road edge line, the road range corresponding to the bidirectional road is: the road edge line of the current bidirectional road and the edge line of the opposite-side bidirectional road are connected end to end, wherein the opposite-side bidirectional road is a bidirectional road adjacent to the current bidirectional road and opposite to the road direction of the current bidirectional road in the high-precision map.
Optionally, for a starting section of the high-precision navigation path, a proportion of a first high-precision section within a first distance threshold range from the starting section reaches a first proportion threshold;
For the ending road section of the high-precision navigation path, the proportion of the first high-precision road section within a second distance threshold range from the ending road section reaches a second proportion threshold.
Optionally, the fact that the label of the traditional navigation path corresponding to the current track point is consistent with the label information of the high-precision road section corresponding to the current track point means that: and the labels of the traditional navigation paths corresponding to the third distance threshold range before and after the current track point are consistent with the label information of the high-precision road section corresponding to the current track point.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a method of determining a high-precision navigation path as provided by any embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention provides a storage medium having a computer program stored thereon, wherein the program when executed by a processor implements a method for determining a high-precision navigation path as provided by any embodiment of the present invention.
In a fifth aspect, an embodiment of the present invention provides a vehicle, where the vehicle includes the determining device for a high-precision navigation path provided in any embodiment of the present invention, or includes the electronic device provided in any embodiment of the present invention.
In a sixth aspect, embodiments of the present invention provide a computer program comprising program instructions which, when executed by a computer, implement a method of determining a high precision navigation path as provided by any of the embodiments of the present invention.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1a is a flowchart of a method for determining a high-precision navigation path according to an embodiment of the present invention;
FIG. 1b is a diagram illustrating a conventional navigation path matching with a high-precision map according to the related art;
FIG. 1c is a schematic diagram of a conventional navigation path matching with a high-precision map according to the related art;
FIG. 1d is a schematic diagram of a matching path according to a first embodiment of the present invention;
FIG. 2a is a flowchart of a method for determining a high-precision navigation path according to a second embodiment of the present invention;
FIG. 2b is a schematic diagram of a cross-road segment according to a second embodiment of the present invention;
fig. 2c is a schematic diagram of matching road sections at an entrance and an exit according to a second embodiment of the present invention;
fig. 3 is a block diagram of a determination device for a high-precision navigation path according to a third embodiment of the present invention;
fig. 4 is a block diagram of an electronic device according to a fourth embodiment of the present invention;
fig. 5 is a schematic diagram of a vehicle according to a fifth embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
In describing embodiments of the present invention, the term "conventional navigational map" is generally accurate at the meter level, where only road-level data, such as road shape, grade, curvature, paving, direction, etc., is recorded. The user of the "conventional navigation map" is mainly the driver.
In describing embodiments of the present invention, the term "high-precision map" has a precision on the order of centimeters. In addition to the data of the road level in the above-described "conventional navigation map", data related to the lane attribute (lane line type, lane width, etc.) such as a large amount of target data of overhead objects, guard rails, trees, road edge type, roadside landmarks, etc. are added to the "high-precision map". The main user of the "high-precision map" is an automatic driving system of an automobile.
The embodiment of the invention discloses a method, a device, equipment, a medium and a vehicle for determining a high-precision navigation path. The following will describe in detail.
Example 1
Fig. 1a is a flowchart of a method for determining a high-precision navigation path according to an embodiment of the present invention, which can be applied to a vehicle-mounted terminal such as a vehicle-mounted computer, a vehicle-mounted industrial control computer (Industrial personal Computer, IPC), etc., and can also be applied to a server, which is not limited in the embodiment of the present invention. The method provided by the embodiment can be applied to the process of matching the high-precision map with the traditional navigation map. The method provided by the embodiment can be performed by a high-precision navigation path determining device, and the device can be implemented by software and/or hardware. As shown in fig. 1a, the method provided in this embodiment specifically includes:
S110, acquiring a traditional navigation path provided by the traditional navigation map, and matching the traditional navigation path with the high-precision map.
In this embodiment, the autopilot system may obtain the conventional navigation path provided by the conventional navigation map according to the departure and destination information. The setting mode of the departure place information and the destination information may be various, for example, the departure place information and the destination information may be manually input by the user through a man-machine interaction interface, or the departure place information and the destination information may be input by voice or the like, which is not limited in particular in this embodiment. After receiving the departure place information and the destination information, the automatic driving system can acquire a traditional navigation path from a traditional navigation map according to the received information, and match the traditional navigation path with a high-precision map.
In this embodiment, the conventional navigation path is matched with the high-precision map, and a way of matching each track point of the conventional navigation path with the road range of each high-precision road section in the high-precision map is adopted. The road range of the high-precision road section in the high-precision map can be obtained by connecting the road boundaries of the high-precision road section end to end. The following describes in detail the way of determining the road ranges of different high-precision road sections:
Non-bidirectional road
The non-bidirectional road refers to a high-precision road section comprising two road edge lines. For this type of high-definition road segment, the road range is obtained by end-to-end connection of road boundaries during the matching process. Due to the technical problem of the high-precision map, the road range of the non-bidirectional road can be in the condition of a non-convex polygon, wherein the convex polygon refers to: if any one of the sides of a road range is extended to a straight line in an infinite way, the other sides are on the same side of the straight line. In the case of a non-convex polygon, the road range is not maximized. In the embodiment, the road range of the high-precision road section of the non-bidirectional road is corrected to the road range with the largest range formed by connecting the boundary points of the largest range of the road edge line end to end, namely, the road range is corrected to the convex polygon with the largest range, so that the accuracy of the road range can be ensured, and the technical problem of a high-precision map is compatible.
(II) bidirectional road
The bidirectional road in the high-precision map is a road which only comprises one road edge line. The original road range of a bi-directional road in a high-precision map is typically composed of its road edge line and another non-road edge line. If the non-road edge line is a traversable road line type, such as a white dotted line, or a virtual line, the original road range of the bidirectional road can be enlarged, and the enlarged bidirectional road range is formed by connecting the road edge line of the current bidirectional road and the edge line of the opposite bidirectional road end to end. The opposite side bidirectional road of the current bidirectional road is: bidirectional roads adjacent to the current bidirectional road and opposite to the road direction of the current bidirectional road in the high-precision map.
As an alternative embodiment, in the case where the bidirectional road to be currently matched is identical to the adjacent opposite-side bidirectional road in length, searching for a road edge line in the direction of the opposite-side bidirectional road by starting from a non-road edge line of the original road range of the bidirectional road to be currently matched until the road edge line of the opposite-side bidirectional road is searched; and then connecting the current road edge line of the current bidirectional road with the road edge line of the opposite-side bidirectional road with the same length end to obtain the road range of the bidirectional road.
As another alternative embodiment, under the condition that the lengths of the bidirectional road to be matched currently and the adjacent opposite-side bidirectional road are inconsistent, acquiring a current road center line of the current bidirectional road, inserting a plurality of virtual points on the current road center line at equal intervals, and then taking the inserted virtual points as normal lines, wherein the normal line of each virtual point is intersected with the road edge line of the opposite-side bidirectional road, so that a plurality of intersection points are obtained; and connecting the boundary points of the intersection points with the boundary points of the road edge line of the current bidirectional road end to end, so as to obtain the road range of the bidirectional road.
In this embodiment, by expanding the original road range of the bidirectional road into a road range formed by connecting the road edge line of the current bidirectional road and the edge line of the opposite bidirectional road end to end, under the condition that the conventional navigation path passes through both the current bidirectional road and also passes through the opposite bidirectional road, each track point passing through the adjacent bidirectional road on both sides in the conventional navigation path can be matched with the real road range of the bidirectional road, so as to avoid the occurrence of the mismatching phenomenon.
(III) urban road crossing
The road range of the type of road can be used for adopting the same road range for all high-precision road sections in the urban road intersection, namely, each road section of the urban road intersection can be contained in a rectangular frame through one rectangular frame, and the rectangular frame is used as the road range of each high-precision road section in the intersection, so that the problem of complex route in the urban road intersection can be avoided.
And S120, in the matching process, determining a high-precision road section corresponding to each track point of the traditional navigation path in the high-precision map, wherein the corresponding high-precision road section comprises a first high-precision road section which is matched with each track point in a determining way and a second high-precision road section which is possibly matched with each track point.
In this embodiment, the first high-precision road section is a high-precision road section that satisfies all of the following matching conditions, and the second high-precision road section is a high-precision road section that satisfies any one or any two of the following matching conditions, where the matching conditions include: for any one current track point, the label of the traditional navigation path corresponding to the current track point is consistent with the label information, the position information and the angle information of the high-precision road section corresponding to the current track point.
The tag information includes road class information and road type information, for example, urban road tag information, urban expressway tag information, entrance tag information, ramp tag information, and the like. The label information consistency can be that the label of the traditional navigation path corresponding to the third distance threshold range before and after the current track point is consistent with the label information of the high-precision road section corresponding to the current track point. Wherein the third distance threshold may be in the range of 80 to 120 meters. In this embodiment, the setting of the third distance threshold may be compatible with the problem that there is a certain gap between the high-precision map and the position of the entrance road section caused by the difference of the manufacturing process of the conventional navigation map.
In this embodiment, the consistency of the position information means that the track point of the traditional navigation path has an intersection point with the road range corresponding to the high-precision road section. The consistent angle information means that the angle between the direction of the high-precision road section and the driving direction of the traditional navigation path is within a preset angle range, wherein the preset angle range can be 0-30 degrees.
In the related art, for a high-precision road section possibly matched with a track point, which meets one or two matching conditions, the road section is processed according to the fact that the road section cannot be matched in the matching process, namely, the road section of the type does not have corresponding observation information in the subsequent matching process. For this type of road section, it is necessary to correct a broken road section between two successfully matched high-definition road sections by a topological relation between the roads after the matching is completed, but this way is prone to a phenomenon of road connection errors.
For example, fig. 1b is a schematic diagram of matching a conventional navigation path with a high-precision map in the related art, and as shown in fig. 1b, in the process of matching the conventional navigation path S with the high-precision road segments a1-a2-a3 in the high-precision map, the high-precision road segments a1 and a3 satisfy all the matching conditions, which may be considered as high-precision road segments for determining the matching. For the high-precision road segment a2, as shown in fig. 1b, the angle between the high-precision road segment a2 and the conventional navigation path S exceeds the preset angle range, and in this case, the high-precision road segment a2 is treated as a road segment that does not match with the conventional navigation path S in the related art, that is, as shown in fig. 1b, in fig. 2, no observation exists between the high-precision road segments a1 and a3 in the subsequent matching process, and the high-precision road segment a2 is disconnected. The related art is to connect the high-precision road segment a1 and the high-precision road segment a3 by finding a road segment that can be topologically connected between the high-precision road segments a1 and a 3. This approach is highly random and is prone to erroneous topology connections. As shown in fig. 1b, fig. 3 shows, a further section a4 is obtained which is completely different from the high-definition section a 2. Also, since the link a4 does not have any observation information, it is also difficult to give the corresponding automatic driving information about the link a4.
Similarly, in the case where the high-precision map is inconsistent with the conventional navigation map with respect to the high-precision road segment a2, for example, the conventional navigation route does not intersect with the road range of the high-precision road segment a2 but the distance therebetween is within the preset distance range (for example, 3-5 meters), or in the case where the high-precision map is inconsistent with the conventional navigation map with respect to the tag of the high-precision road segment a2, for example, the high-precision road segment a2 in the high-precision map is an urban expressway, and the conventional navigation map corresponds to an urban road, the technical solution of the related art may also exist where the above-mentioned high-precision road segment a2 cannot be matched with the conventional navigation route S.
For another example, fig. 1c is a schematic diagram of matching a conventional navigation path with a high-precision map in the related art, as shown in fig. 1c, for a route from a start point n to an end point m, since an abnormal situation such as a car accident or construction may occur in a route 4, the conventional navigation path is driven from the start point n to the end point m by avoiding the abnormal situation road section according to a route 5 shown by an arrow. The conventional navigation path can only be determined to match to the high-precision road segment FA and the high-precision road segment CE. The high-precision road segment CD and the high-precision road segment AB are second high-precision road segments that may be matched and do not participate in the subsequent path determination process. The related technology is to connect the high-precision road section FA with the high-precision road section CE directly through a topological connection mode to obtain the high-precision road section AC. In practice, no observation information exists in the high-precision road section AC, and when the topology connection is directly performed, the situation of connection errors occurs, so that an erroneous high-precision navigation path can be obtained. For example, if traveling on the high-definition link 6 shown in fig. 1c, traveling is impossible due to an abnormality in the road.
If the matching scheme provided according to the embodiment of the present invention is that in the case where there are only the straight road AC, the entrance road AB and the exit road CD in the high-precision map, the paths of the last matching success are the entrance road Fa-AB and the exit road DC-CE with respect to fig. 1c (see the following matching description for the cross road and the entrance road for a specific matching procedure). For other sections which are not successfully matched except the road sections at the entrance and the exit, the road sections need to travel according to the traditional navigation path, so that the problem that the related technology directly performs topological connection under the condition of no observation information to obtain an incorrect matched path is avoided.
In this embodiment, for the second high-precision road segment that cannot meet all the matching conditions, that is, the high-precision road segment that may be matched with the track point in the conventional navigation path, compared with the method in which the second high-precision road segment is used as the non-matching road segment without participating in the subsequent path matching in the related art, and the method directly performs the topology connection on the high-precision road segment under the condition that the observation information cannot be obtained, the embodiment retains the observation information of the high-precision road segment, so that the observation information and the topology connection relationship between the high-precision road segment and other road segments can be combined to obtain the high-precision navigation path matched with the conventional navigation path, the phenomenon of mismatching or mismatching is avoided, and the matching result of the conventional navigation path and the high-precision map can be compatible with the process error, the angle error and the precision error between the conventional navigation map and the high-precision map, so that the matching result is more accurate.
S130, screening a plurality of target high-precision road sections with continuous topological relations from the first high-precision road section and the second high-precision road section, and generating a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road sections, wherein a starting road section and an ending road section of the high-precision navigation path are both the first high-precision road section.
In this embodiment, the high-precision navigation path matched with the conventional navigation path is a continuous path starting from a certain first high-precision path section matched with the track point determination of the conventional navigation path and ending with a certain first high-precision path section matched with the track point determination of the conventional navigation path, and each high-precision path section in the continuous path section may be a first high-precision path section or a second high-precision path section.
Alternatively, when determining the high-precision navigation path, a path formed by all topologically connectable high-precision road segments (which may be the first high-precision road segment or the second high-precision road segment) between the first high-precision road segment located at the beginning and the first high-precision road segment located at the end may be used as the high-precision navigation path.
Optionally, in this embodiment, a plurality of target fine segments with a continuous topological relation may be obtained by optimizing a viterbi algorithm, which may be specifically implemented by the following steps (1) - (4):
(1) And scoring the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section, wherein the first observation score is larger than the second observation score.
In this embodiment, a correspondence relationship between different high-precision road segments and the observed score may be established, specifically, the observed value of each first high-precision road segment that is determined to be matched with the track point of the conventional navigation path may be scored as 1, for example, for a bidirectional road, if the track point of the conventional navigation path and the road range after the high-precision road segment is corrected in the matching process satisfy all the above matching conditions, the observed value of the high-precision road segment corresponding to the bidirectional road is scored as 1.
In particular, observations of all respective second high-precision road segments that may match with the trajectory points of the conventional navigation path may be scored as 0.5.
It should be noted that, for the road section of the type of the intersection, since any navigation path cannot start in the range of the intersection and end in the range of the intersection, the observed values of all the matched high-precision road sections in the intersection are calculated according to the observed score of 0.5.
(2) And respectively scoring the transition probabilities of the first high-precision road section and the second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section, wherein the second transition probability score is smaller than the first transition probability score.
In this embodiment, the second transition probability score is set smaller than the first transition probability score, so that the weight of the high-precision road segment which is determined to be matched with each track point in the whole high-precision navigation path can be increased, and the weight of the high-precision road segment which is possibly matched with each track point in the whole high-precision navigation path can be reduced, so that the accuracy of the matching result is improved.
Specifically, for any one current high-precision road segment, if the observation score of the high-precision road segment selected continuously from the current high-precision road segment is 1, and when the candidate continuous high-precision road segment and the current high-precision road segment are the same road segment, the transition probability score of the candidate continuous high-precision road segment is scored as 1+E, wherein E is a minimum value larger than 0. Optionally, E has a value of 1E -1 ~1e -10 The method comprises the steps of carrying out a first treatment on the surface of the Or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 1+2E; or,
If the observation score of the candidate continuous high-precision road section with the current high-precision road section is 1 and the candidate continuous high-precision road section is not topologically connected with the current high-precision road section, scoring the transition probability score of the candidate continuous high-precision road section as 0; or,
if the observed score of the high-precision road segment continuous with the current high-precision road segment candidate is 0.5, the transition probability score of the high-precision road segment continuous with the candidate is scored as 1.
In this embodiment, for a candidate continuous high-precision road segment with an observation score of 1, if the candidate continuous high-precision road segment is the same road segment as the current high-precision road segment, the transition probability score of the candidate continuous high-precision road segment is scored as 1+e, and if the candidate continuous high-precision road segment is the next road segment capable of being topologically connected with the current high-precision road segment, the transition probability score of the candidate continuous high-precision road segment is scored as 1+2e slightly greater than the transition score of the same road segment, so that the topologically connectable road segment and the same road segment are separated, and the process of observing and searching the next road segment is continuously continued, thereby ensuring that the head and tail positions of the road segments can be correctly matched and connected.
Further, when the transition probability of the candidate continuous high-precision road segment is 0, it is explained that the candidate continuous high-precision road segment is disconnected from the current high-precision road segment, that is, the matching result is discontinuous. This is because the high-precision map itself may not be complete, and the road network may be missing, so that discontinuities may occur in the true matching result. The embodiment scores 0 for the transition probability score of the next candidate road segment which does not have the topological connection relationship with the current high-precision road segment, and is compatible with the situation of high-precision map road network missing.
In this embodiment, for the case of discontinuity occurring in the matching path, that is, in the case where the observation score of the candidate continuous high-precision road segment of the current high-precision road segment is 1, but the transition probability score of the candidate continuous high-precision road segment is 0, the current high-precision road segment may be taken as the ending road segment of the matched path, the high-precision road segment continuous with the candidate of the current high-precision road segment may be taken as the starting road segment of the next matching path, and the determination operation of the matching path may be continued according to the modified viterbi algorithm provided in this embodiment from this road segment. Specifically, fig. 1d is a schematic diagram of a matching path according to a first embodiment of the present invention. As shown in fig. 1d, the high-precision road segments a, b and c are road segments for determining matching, and there is no topological relation between the current high-precision road segment c and the candidate continuous high-precision road segment d, namely, the transition probability score of the next candidate continuous high-precision road segment d of the current high-precision road segment c is 0, at this time, the matching path is disconnected from c, c is taken as the ending road segment of one matching path of a-b-c, and d is taken as the starting road segment of the next matching path d-e-f.
(3) And for any one current track point, starting from the first high-precision road section which can be observed by the current track point, taking the transition probability score of the first high-precision road section as a weight value, and weighting the observed score of the first high-precision road section based on the weight value to obtain the Viterbi score of the first high-precision road section. And sequentially taking the obtained Viterbi score as an observation score of the next candidate continuous high-precision road section, and continuously executing the Viterbi score calculation operation on the candidate continuous high-precision road section based on the transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the last first high-precision road section observed by the last track point is obtained by calculation, wherein the candidate continuous high-precision road section is the first high-precision road section or the second high-precision road section.
In this embodiment, the transition probability score of the high-precision road segment with the observation value of 0.5 is smaller than the transition probability score with the observation value of 1, so that the weight of the high-precision road segment which is determined to be matched with each track point in the whole high-precision navigation path can be increased, and the weight of the high-precision road segment which is possibly matched with each track point in the whole high-precision navigation path can be reduced. By scoring the transition probability score of the high-precision road segment with the observation score of 0.5 as 1, namely setting the weight value as 1, the road segment with the observation score of 0.5 is not weighted in the Viterbi calculation process, so that the strong correlation between the score of the final matching path and the number of the road segments can be avoided.
(4) And selecting the Viterbi score with the largest value from the plurality of Viterbi scores obtained by calculation, and taking a plurality of continuous high-precision road segments corresponding to the Viterbi score with the largest value as a plurality of target precision road segments with continuous topological relations.
For a starting link of the high-precision navigation path, the proportion of the first high-precision link within a first distance threshold range from the starting link before and after the starting link reaches a first proportion threshold. The first distance threshold range may be 100-300 meters, and the first ratio threshold may be 60% -80%. For the tail section of the high-precision navigation path, the proportion of the first high-precision section within a second distance threshold range from the tail section reaches a second proportion threshold. The second distance threshold range may be 100-300 meters, and the second ratio threshold may be 60% -80%. In this embodiment, the accuracy of the matching result can be further ensured by increasing the specific gravity of the high-precision road section for which the matching is determined in the front-rear range of the start road section and the end road section of the high-precision navigation path.
In this embodiment, for a high-precision road segment that cannot meet all the matching conditions, that is, for a high-precision road segment that may be matched with a track point in a conventional navigation path, the embodiment retains the observation information of the high-precision road segment, combines the observation information and the topological connection relationship between the high-precision road segment and other road segments to obtain a high-precision navigation path that is matched with the conventional navigation path, so as to avoid the phenomenon of mismatching or missed matching caused by removing the observation information that may be matched with the track point in the conventional navigation path, and enable the matching result of the conventional navigation path and the high-precision map to be compatible with the process error, the angle error and the precision error between the conventional navigation map and the high-precision map, and the matching result is more accurate. In addition, the method can simplify the screening process by adopting the mode of scoring the observation value and the transition probability value and calculating the Viterbi score, and can screen the high-precision road section continuous with the current high-precision road section efficiently.
Example two
Fig. 2a is a flowchart of a method for determining a high-precision navigation path according to a second embodiment of the present invention, where, based on the foregoing embodiment, a process of correcting observations of a cross road segment and an entrance road segment is refined, and as shown in fig. 2a, the method provided in this embodiment includes:
S200, acquiring a traditional navigation path provided by the traditional navigation map, and matching the traditional navigation path with the high-precision map.
And S210, in the matching process, determining a high-precision road section corresponding to each track point of the traditional navigation path in the high-precision map, wherein the corresponding high-precision road section comprises a first high-precision road section which is matched with each track point in a determining way and a second high-precision road section which is possibly matched with each track point.
The first high-precision road section is a high-precision road section meeting all the following matching conditions, and the second high-precision road section is a high-precision road section meeting any one or two of the following matching conditions, wherein the matching conditions comprise: for any one current track point, the label of the traditional navigation path corresponding to the current track point is consistent with the label information, the position information and the angle information of the high-precision road section corresponding to the current track point.
S220, scoring the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section.
Specifically, the observed value of each first high-precision road segment is scored as 1, and the observed value of each second high-precision road segment is scored as 0.5.
S230, identifying the transverse road sections in the traditional navigation paths according to the topological relation of the road network.
Wherein, the horizontal insertion section is: the target observation road section that can be observed by at least two continuous track points in the traditional navigation path has no topological connection relation, and the navigation road section corresponding to the at least two continuous track points in the traditional navigation path is also provided under the condition that the target observation road section is a non-road entrance road section and is also provided under the condition that the target observation road section is a non-road starting road section and a non-road ending road section.
The target observation road section observed by at least two continuous track points in the traditional navigation path has no topological connection relation, and the method comprises the following two conditions:
(1) Among two continuous track points on the conventional navigation path, one track point can observe a certain high-precision road section, and the other track point in front of the track point in the traveling direction along the conventional navigation path cannot observe the high-precision road section and cannot observe a high-precision road section continuous with the high-precision road section.
(2) In two continuous track points on the traditional navigation path, one track point can observe a certain high-precision road section, and in the running direction along the traditional navigation path, the high-precision road section which can be observed by the other track point in front of the track point running does not have topological connection relation with the high-precision road section which can be observed by the last track point.
Specifically, fig. 2b is a schematic diagram of a cross road segment according to a second embodiment of the present invention. As shown in fig. 2b, the traveling direction of the conventional navigation path 7 is the direction indicated by the arrow in fig. 2 b. The trajectory point u in the conventional navigation path can observe the high-precision road segment po in the high-precision map 8, that is, the intersection point of the trajectory point u and the road range a of the high-precision road segment po. In the case of a non-entrance road segment, the high-definition road segment that can be observed by the trajectory point u and the trajectory point v in the conventional navigation path should be continuous. As shown in fig. 2b, since the trajectory point v cannot observe the high-precision road segment po nor the high-precision road segment continuous with the high-precision road segment po, it can be explained that the road segment uv in the conventional navigation path is a lateral road segment.
S240, the observation scores of the high-precision road sections which can be observed by the track points corresponding to the transverse road sections are all corrected to be second observation scores.
If there is a track point in the cross road section that successfully matches with the high-precision road section, for example, as shown in fig. 2b, the track point u intersects with the road range of the target observation road section po, and the traveling direction of the conventional navigation path coincides with the angle of the high-precision road section, and if the two labels also coincide, for example, the high-precision road section po is a city expressway, the conventional navigation path corresponds to a city expressway, and both labels belong to a city expressway, at this time, the high-precision road section po may be determined as a high-precision road section that matches with the track point u in the cross road section, and the high-precision road section po may be scored as 1.
It should be noted that, for the cross road section shown in fig. 2b, even if the trajectory point u is successfully matched with the high-precision road section po, this is a case of a matching error. Since it is impossible to make a navigation section traverse a ramp section in an application scenario where the high-definition section is a ramp section as shown in fig. 2b, and the travel path of a normal vehicle does not end on the ramp either.
In this embodiment, the processing manner for the case of mismatching of the transverse road section is: the observation scores of the high-precision road sections which can be observed by the track points corresponding to the transverse road sections are all corrected to be second observation scores, and specifically, the observation scores of the high-precision road sections which can be observed by the transverse road sections can be corrected to be 0.5. Since both the beginning and ending sections of the high-precision navigation path are the first high-precision section, the observation score is 1. For a high-precision road segment that can be observed by the cross road segment, the problem of the cross road segment matching error is solved by correcting the observed score of the high-precision road segment to 0.5, that is, excluding the possibility that the high-precision road segment is the start point and the end point of the last matching path, for example, as shown in fig. 2b, a high-precision road segment po with the observed score of 0.5 will not be the end road segment of the matching path.
S250, according to the direction opposite to the traditional navigation path, starting to search whether an entrance road section exists from a target high-precision road section which can be observed by the track point of the transverse road section, if the entrance road section can be searched, correcting the observed scores of all the high-precision road sections between the target high-precision road section and the entrance road section to be second observed scores, and correcting the observed scores corresponding to the entrance road section to be first observed scores.
It will be appreciated by those skilled in the art that the reasons for the presence of the road cross-section in the conventional navigation path are generally due to the excessive difference in accuracy between the entrance and exit of the high-definition road section and the corresponding entrance and exit of the conventional navigation map. In this embodiment, through the cross road section, whether the entrance road section exists in the high-precision map can be searched within a set range along the opposite direction of the traditional navigation path, wherein the set range can be 700-2000 meters. If no entrance road section exists, the defect of the entrance corresponding to the traditional navigation path in the high-precision map can be indicated. If there is an entrance road segment, it may be stated that the road segments in the conventional navigation path should be matched with the entrance road segment of the high-precision map, at this time, the observed scores of all the high-precision road segments between the target precision road segment and the entrance road segment may be corrected to a second observed score, specifically, may be corrected to 0.5, that is, all the high-precision road segments between the target precision road segment and the entrance road segment may be corrected to a second high-precision road segment that may be matched, and the observed scores corresponding to the entrance road segment may be corrected to a first observed score, specifically, may be corrected to 1, that is, the entrance road segment may be corrected to a first high-precision road segment that determines the matching.
For example, fig. 2c is a schematic diagram of matching a road section at an entrance and an exit according to a second embodiment of the present invention. Fig. 2c adds the observation of inquiring the doorway segment on the basis of fig. 2 b. As shown in fig. 2c, from the target observation section po that can be observed by the lateral section, an exit section rt in the high-definition section, which differs from the positional accuracy of the exit xy in the conventional navigation map, can be found in the direction opposite to the direction indicated by the arrow. At this time, the observation score of the exit road segment is corrected to 1, that is, the exit road segment rt is regarded as a high-precision road segment that is determined to match the conventional navigation path, and the observation scores of all high-precision road segments (including the high-precision road segment rq, the high-precision road segment qp, and the high-precision road segment po) between the target observation road segment po and the entrance road segment rt are corrected to the second observation score of 0.5, that is, these road segments are determined to be high-precision road segments that are likely to match the conventional navigation path. In this way, in the subsequent determination process of the high-precision navigation path, since the start road section and the end road section of the high-precision navigation path are both high-precision road sections with an observation score of 1, after the correction of the observation score is completed, the exit road section will be used as the end road section of the matching path, and each road section that may be matched will not participate in the subsequent determination process of the high-precision navigation path.
In the embodiment, in the observation process, the observation scores of the entrance road sections and the observation scores of all high-precision road sections from the target observation road section to the entrance road section, which can be observed by the track points of the crossroad road sections, are corrected through the road topology relationship, so that the problem that the accuracy of the high-precision map and the accuracy of the entrance of the traditional navigation path is overlarge is solved, and the accuracy of the matching result is ensured.
S260, respectively scoring the transition probabilities of the first high-precision road sections and the second high-precision road sections according to the topological relation of the high-precision road sections and the observation scores corrected by the different road sections, and obtaining a first transition probability score corresponding to each first high-precision road section and a second transition probability score corresponding to each second high-precision road section.
The observation score correction is to correct whether the high-precision road section is a first high-precision road section or a second high-precision road section. For example, the observation score is corrected from 0.5 to 1, that is, the high-precision road segment is corrected from the second high-precision road segment to the first high-precision road segment, and the observation score is corrected from 1 to 0.5, that is, the high-precision road segment is corrected from the first high-precision road segment to the second high-precision road segment. In this embodiment, for the high-precision road section where the observation score is not changed, the transition probability is scored according to the current observation score when the transition probability is scored. And when the transition probability scoring is carried out on the high-precision road section with the corrected observation score, the transition probability scoring is carried out according to the corrected observation score. For a specific scoring process, reference is made to the description of the above embodiments.
S270, for any one current track point, starting from the first high-precision road section which can be observed by the current track point, taking the transition probability score of the first high-precision road section as a weight value, and weighting the observed score of the first high-precision road section based on the weight value to obtain the Viterbi score of the first high-precision road section.
And S280, sequentially taking the obtained Viterbi score as the observation score of the next candidate continuous high-precision road section, and continuously executing the Viterbi score calculation operation on the candidate continuous high-precision road section based on the transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the last first high-precision road section which can be observed by the last track point is obtained by calculation.
The observation score of each high-definition link between high-definition links with an observation score of 1 may be 1 or 0.5. In the calculation process of the Viterbi score, if the observed score of the high-precision road section which can be observed by the track point in the traditional navigation path is corrected, the calculation process of the Viterbi score is calculated according to the corrected observed score and the transition probability score obtained based on the corrected observed score.
Specifically, for any one current track point, starting from a high-precision road section with the first observation score of 1 which can be observed by the current track point, taking the transition probability score of the high-precision road section with the first observation score of 1 as a weight value, and weighting the observation score of the high-precision road section with the first observation score of 1 based on the weight value to obtain the Viterbi score of the high-precision road section with the first observation score of 1. And sequentially taking the obtained Viterbi score as the observation score of the next candidate continuous high-precision road section, and continuously executing the Viterbi score calculation operation on the candidate continuous high-precision road section based on the transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the high-precision road section with the last observation score of 1 observed by the last track point is obtained by calculation.
S290, selecting the Viterbi score with the largest value from the calculated Viterbi scores, taking a plurality of continuous high-precision road sections corresponding to the Viterbi score with the largest value as a plurality of target high-precision road sections with continuous topological relations, and generating a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road sections.
The specific implementation of steps S260 to S290 may refer to the description of the above embodiments, and will not be repeated here.
In this embodiment, during the observation process, the cross road section in the conventional navigation path is identified, and the observation score of the target observation road section that can be observed by the cross road section is corrected to 0.5, so that the possibility that the target observation road section serves as the starting point and the end point of the final matching path is eliminated, and the problem of incorrect matching of the cross road section is solved. In addition, in the observation process, the observation scores of the entrance road sections and the observation scores of all high-precision road sections from the target observation road sections to the entrance road sections, which can be observed by the track points of the crossroad road sections, are corrected through the road topology relationship, so that the problem that the accuracy difference between the high-accuracy map and the entrance road sections of the traditional navigation path is overlarge is solved, and the accuracy of the matching result is ensured.
Example III
Fig. 3 is a block diagram of a device for determining a high-precision navigation path according to a third embodiment of the present invention, where, as shown in fig. 3, the device includes: a conventional navigation path acquisition module 310, an observation module 320, and a matching module 330, wherein,
a conventional navigation path acquisition module 310 configured to acquire a conventional navigation path provided by a conventional navigation map and match the conventional navigation path with a high-precision map;
An observation module 320 configured to determine, in a matching process, a high-precision road segment corresponding to each of the track points of the conventional navigation path in a high-precision map, the corresponding high-precision road segment including a first high-precision road segment that is determined to be matched with each of the track points and a second high-precision road segment that is likely to be matched with each of the track points;
the matching module 330 is configured to screen out a plurality of target high-precision road segments with continuous topological relation from the first high-precision road segment and the second high-precision road segment, and generate a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road segments, wherein a starting road segment and an ending road segment of the high-precision navigation path are both the first high-precision road segment;
the first high-precision road section is a high-precision road section meeting all the following matching conditions, and the second high-precision road section is a high-precision road section meeting any one or two of the following matching conditions, wherein the matching conditions comprise: for any one current track point, the label information of the traditional navigation path corresponding to the current track point is consistent with the label information, the position information and the angle information of the high-precision road section corresponding to the current track point.
Optionally, the matching module 330 includes:
the observation value scoring unit is configured to score the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section, wherein the first observation score is larger than the second observation score;
the transition probability value scoring unit is configured to score transition probabilities of the first high-precision road section and the second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections, so as to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section, wherein the second transition probability score is smaller than the first transition probability score;
the Viterbi score calculating unit is configured to, for any one current track point, start from a first high-precision road section which can be observed by the current track point, take a transition probability score of the first high-precision road section as a weight value, and weight the observed score of the first high-precision road section based on the weight value to obtain a Viterbi score of the first high-precision road section; sequentially taking the obtained Viterbi score as an observation score of the next candidate continuous high-precision road section, and continuously executing Viterbi score calculation operation on the candidate continuous high-precision road section based on the transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the last first high-precision road section which can be observed by the last track point is obtained through calculation;
A target fine segment determining unit configured to select a viterbi score value having a largest value from the plurality of viterbi scores obtained by calculation, and to use a plurality of continuous high-fine segments corresponding to the viterbi score value having the largest value as a plurality of target fine segments having a continuous topological relation;
and a high-precision navigation path generation unit configured to generate a high-precision navigation path matched with the conventional navigation path according to a plurality of continuous target high-precision road segments.
Optionally, the observation scoring unit is specifically configured to:
scoring the observed value of each first high-precision road segment as 1, and scoring the observed value of each second high-precision road segment as 0.5;
correspondingly, the transition probability value scoring unit is specifically configured to:
for any one current high-precision road section, if the observation score of a high-precision road section which is continuous with the current high-precision road section is 1, and when the candidate continuous high-precision road section and the current high-precision road section are the same road section, the transition probability score of the candidate continuous high-precision road section is scored as 1+E, wherein E is a minimum value larger than 0; or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 1+2E; or,
If the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is not topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 0; or,
if the observed score of the high-precision road segment continuous with the current high-precision road segment candidate is 0.5, the transition probability score of the high-precision road segment continuous with the candidate is scored as 1.
Optionally, in the case that the observation score of the current high-precision road segment selecting the continuous high-precision road segment is 1, and the transition probability score of the candidate continuous high-precision road segment is 0:
and taking the current high-precision road section as the ending road section of the matched path, taking the high-precision road section continuous with the candidate as the starting road section of the next matched path, and continuously executing scoring operation for the transition probability score according to the topological relation of the high-precision road section and the observation scores of different road sections.
Optionally, the device provided by the embodiment of the present invention further includes:
the system comprises a cross road section identification module, a navigation module and a navigation module, wherein the cross road section identification module is configured to identify a cross road section in a traditional navigation path according to the topological relation of a road network, and the cross road section is: the method comprises the steps that a topological connection relation does not exist between a target observation road section which can be observed by at least two continuous track points in a traditional navigation path, and the navigation road section corresponding to the at least two continuous track points is arranged under the condition that the target observation road section is not a road entrance road section and is also a starting road section and an ending road section of a non-road;
The first observation score correction module is configured to correct the observation scores of the high-precision road sections which can be observed by the track points corresponding to the transverse road sections into second observation scores;
correspondingly, the transition probability value scoring unit comprises:
and the transition probability value scoring subunit is configured to score the transition probability of each first high-precision road segment and each second high-precision road segment according to the topological relation of the high-precision road segments and the observation scores corrected by different road segments.
Optionally, the device provided by the embodiment of the present invention further includes:
the second observation score correction module is specifically configured to, before scoring the transition probabilities of the first high-precision road segments and the second high-precision road segments according to the topological relation of the high-precision road segments and the observation scores after correction of different road segments, search whether an entrance road segment exists from a target observation road segment which can be observed by a track point of a cross road segment according to a direction opposite to a traditional navigation path, and if the entrance road segment can be found, correct the observation scores of all the high-precision road segments between the target observation road segment and the entrance road segment to be second observation scores and correct the observation scores corresponding to the entrance road segment to be first observation scores.
Optionally, the consistent position information means that the track point of the traditional navigation path has an intersection point with the road range corresponding to the high-precision road section;
under the condition that the traditional navigation path passes through the urban road intersection, the road range corresponding to the urban road intersection is as follows: sharing the same road range for all high-precision road sections in the urban road junction; or,
in the case where the conventional navigation path passes through a non-bidirectional road including two road edge lines, the road range corresponding to the non-bidirectional road is: the road boundaries of each high-precision road section are connected end to obtain the road boundary; or,
in the case where the conventional navigation path passes through a bidirectional road including only one road edge line, the road range corresponding to the bidirectional road is: the road edge line of the current bidirectional road and the edge line of the opposite-side bidirectional road are connected end to end, wherein the opposite-side bidirectional road is a bidirectional road adjacent to the current bidirectional road and opposite to the road direction of the current bidirectional road in the high-precision map.
Optionally, for a starting section of the high-precision navigation path, a proportion of a first high-precision section within a first distance threshold range from the starting section reaches a first proportion threshold;
For the ending road section of the high-precision navigation path, the proportion of the first high-precision road section within a second distance threshold range from the ending road section reaches a second proportion threshold.
Optionally, the fact that the label of the traditional navigation path corresponding to the current track point is consistent with the label information of the high-precision road section corresponding to the current track point means that: and the labels of the traditional navigation paths corresponding to the third distance threshold range before and after the current track point are consistent with the label information of the high-precision road section corresponding to the current track point.
The high-precision navigation path device provided by the embodiment of the invention can execute the method for determining the high-precision navigation path provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in the above embodiments may be referred to the method for determining a high-precision navigation path provided in any of the embodiments of the present invention.
Example IV
Fig. 4 is a block diagram of an electronic device according to a fourth embodiment of the present invention, as shown in fig. 4, where the electronic device includes:
a memory 510 storing executable program code;
a processor 520 coupled to the memory 510;
wherein the processor 520 invokes the executable program code stored in the memory 510 to perform the method of determining a high-precision navigation path provided by any embodiment of the present invention.
Based on the above embodiments, a further embodiment of the present invention provides a vehicle comprising an apparatus according to any of the embodiments above, or comprising an electronic device as described above.
Example five
Fig. 5 is a schematic diagram of a vehicle according to a fifth embodiment of the present invention. As shown in fig. 5, the vehicle includes a speed sensor 61, an ECU (Electronic Control Unit ) 62, a GPS (Global Positioning System, global positioning system) positioning device 63, a T-Box (Telematics Box) 64. Wherein the speed sensor 61 is used for measuring the speed of the vehicle and taking the speed of the vehicle as an empirical speed for model training; the GPS positioning device 63 is used for acquiring the current geographic position of the vehicle; T-Box64 may communicate with a server as a gateway; the ECU62 may execute the above-described determination method of the high-precision navigation path.
In addition, the vehicle may further include: V2X (Vehicle-to-Evering) module 65, radar 66 and camera 67. The V2X module 65 is used for communication with other vehicles, road side equipment, etc.; the radar 66 or the camera 67 is used for sensing road environment information in front and/or other directions to obtain original point cloud data; the radar 66 and/or camera 67 may be disposed at the front and/or rear of the vehicle body.
Based on the above method embodiments, another embodiment of the present invention provides a storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement a method for determining a high-precision navigation path according to any of the above embodiments.
Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the invention.
Those of ordinary skill in the art will appreciate that: the modules in the apparatus of the embodiments may be distributed in the apparatus of the embodiments according to the description of the embodiments, or may be located in one or more apparatuses different from the present embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (21)

1. A method for determining a high-precision navigation path, comprising:
acquiring a traditional navigation path provided by a traditional navigation map, and matching the traditional navigation path with a high-precision map;
in the matching process, determining a high-precision road section corresponding to each track point of the traditional navigation path in the high-precision map, wherein the corresponding high-precision road section comprises a first high-precision road section which is matched with each track point in a determining way and a second high-precision road section which is possibly matched with each track point;
screening a plurality of target high-precision road sections with continuous topological relations from the first high-precision road section and the second high-precision road section, and generating a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road sections, wherein a starting road section and an ending road section of the high-precision navigation path are both the first high-precision road section;
the first high-precision road section is a high-precision road section meeting all the following matching conditions, and the second high-precision road section is a high-precision road section meeting any one or two of the following matching conditions, wherein the matching conditions comprise: for any one current track point, the label information of the traditional navigation path corresponding to the current track point is consistent with the label information, the position information and the angle information of the high-precision road section corresponding to the current track point.
2. The method of claim 1, wherein the screening the plurality of destination precision segments from the first high precision segment and the second high precision segment that are topologically continuous comprises:
scoring the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section, wherein the first observation score is larger than the second observation score;
respectively scoring transition probabilities of a first high-precision road section and a second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section, wherein the second transition probability score is smaller than the first transition probability score;
for any one current track point, starting from a first high-precision road section which can be observed by the current track point, taking a transition probability score of the first high-precision road section as a weight value, and weighting the observed score of the first high-precision road section based on the weight value to obtain a Viterbi score of the first high-precision road section;
Sequentially taking the obtained Viterbi score as an observation score of the next candidate continuous high-precision road section, and continuously executing Viterbi score calculation operation on the candidate continuous high-precision road section based on the transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the last first high-precision road section which can be observed by the last track point is obtained through calculation;
and selecting the Viterbi score with the largest value from the plurality of Viterbi scores obtained by calculation, and taking a plurality of continuous high-precision road segments corresponding to the Viterbi score with the largest value as a plurality of target precision road segments with continuous topological relations.
3. The method according to claim 2, wherein scoring the observations of the first high-precision road segment and the second high-precision road segment to obtain a first observation score corresponding to the first high-precision road segment and a second observation score corresponding to the second high-precision road segment, respectively, comprises:
scoring the observed value of each first high-precision road segment as 1, and scoring the observed value of each second high-precision road segment as 0.5; in a corresponding manner,
the step of respectively scoring the transition probabilities of the first high-precision road section and the second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section comprises the following steps:
For any one current high-precision road section, if the observation score of a high-precision road section which is continuous with the current high-precision road section is 1, and when the candidate continuous high-precision road section and the current high-precision road section are the same road section, the transition probability score of the candidate continuous high-precision road section is scored as 1+E, wherein E is a minimum value larger than 0; or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 1+2E; or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is not topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 0; or,
if the observed score of the high-precision road segment continuous with the current high-precision road segment candidate is 0.5, the transition probability score of the high-precision road segment continuous with the candidate is scored as 1.
4. A method according to claim 3, wherein in case that the observed score of the high-precision road segment selected continuously from the current high-precision road segment is 1 and the transition probability score of the candidate continuous high-precision road segment is 0:
And taking the current high-precision road section as the ending road section of the matched path, taking the high-precision road section continuous with the candidate as the starting road section of the next matched path, and continuously executing scoring operation for the transition probability score according to the topological relation of the high-precision road section and the observation scores of different road sections.
5. The method according to claim 2, wherein the method further comprises:
and identifying a transverse road section in the traditional navigation path according to the topological relation of the road network, wherein the transverse road section is: the method comprises the steps that a target observation road section which can be observed by at least two continuous track points in a traditional navigation path does not have a topological connection relationship, and the navigation road section corresponding to the at least two continuous track points is arranged under the condition that the target observation road section is not a road entrance road section, a non-road starting road section and a non-road ending road section;
correcting the observation scores of the high-precision road sections which can be observed by the track points corresponding to the transverse road sections into second observation scores;
correspondingly, the scoring the transition probabilities of the first high-precision road section and the second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections respectively comprises the following steps:
And respectively scoring the transition probabilities of the first high-precision road sections and the second high-precision road sections according to the topological relation of the high-precision road sections and the observation scores corrected by different road sections.
6. The method of claim 5, wherein before scoring the transition probabilities for each first high-precision road segment and each second high-precision road segment, respectively, based on the topology of the high-precision road segments and the modified observed scores for the different road segments, the method further comprises:
and according to the direction opposite to the traditional navigation path, starting to search whether an entrance road section exists from a target observation road section which can be observed by the track point of the transverse road section, if the entrance road section can be searched, correcting the observation scores of all high-precision road sections between the target observation road section and the entrance road section to be second observation scores, and correcting the observation scores corresponding to the entrance road section to be first observation scores.
7. The method according to claim 1, wherein the consistency of the position information means that the track point of the conventional navigation path has an intersection point with a road range corresponding to the high-precision road segment;
under the condition that a traditional navigation path passes through an urban road intersection, the road range corresponding to the urban road intersection is as follows: sharing the same road range for all high-precision road sections in the urban road junction; or,
In the case where a conventional navigation path passes through a non-bidirectional road including two road edge lines, the road range corresponding to the non-bidirectional road is: the road boundaries of each high-precision road section are connected end to obtain the road boundary; or,
in the case that the conventional navigation path passes through a bidirectional road including only one road edge line, the bidirectional road corresponds to a road range of: the high-precision map is formed by connecting the road edge line of the current bidirectional road and the edge line of the opposite-side bidirectional road end to end, wherein the opposite-side bidirectional road is a bidirectional road adjacent to the current bidirectional road and opposite to the road direction of the current bidirectional road in the high-precision map.
8. The method according to claim 1, characterized in that:
for a starting road section of the high-precision navigation path, the proportion of a first high-precision road section within a first distance threshold range from the starting road section reaches a first proportion threshold;
and for the tail road section of the high-precision navigation path, the proportion of the first high-precision road section within a second distance threshold range from the tail road section reaches a second proportion threshold.
9. The method of claim 1, wherein the fact that the label of the conventional navigation path corresponding to the current track point is consistent with the label information of the high-precision road segment corresponding to the current track point means that: and the labels of the traditional navigation paths corresponding to the third distance threshold range before and after the current track point are consistent with the label information of the high-precision road section corresponding to the current track point.
10. A high-precision navigation path determining apparatus, comprising:
the traditional navigation path acquisition module is configured to acquire a traditional navigation path provided by a traditional navigation map and match the traditional navigation path with a high-precision map;
an observation module configured to determine, in a matching process, a high-precision road segment corresponding to each track point of the conventional navigation path in the high-precision map, the corresponding high-precision road segment including a first high-precision road segment that is determined to be matched with each track point and a second high-precision road segment that is likely to be matched with each track point;
the matching module is configured to screen out a plurality of target high-precision road sections with continuous topological relations from the first high-precision road section and the second high-precision road section, and generate a high-precision navigation path matched with the traditional navigation path according to the plurality of continuous target high-precision road sections, wherein a starting road section and an ending road section of the high-precision navigation path are both the first high-precision road section;
the first high-precision road section is a high-precision road section meeting all the following matching conditions, and the second high-precision road section is a high-precision road section meeting any one or two of the following matching conditions, wherein the matching conditions comprise: for any one current track point, the label information of the traditional navigation path corresponding to the current track point is consistent with the label information, the position information and the angle information of the high-precision road section corresponding to the current track point.
11. The apparatus of claim 10, wherein the matching module comprises:
the observation value scoring unit is configured to score the observation values of the first high-precision road section and the second high-precision road section respectively to obtain a first observation score corresponding to the first high-precision road section and a second observation score corresponding to the second high-precision road section, wherein the first observation score is larger than the second observation score;
the transition probability value scoring unit is configured to score transition probabilities of the first high-precision road section and the second high-precision road section according to the topological relation of the high-precision road section and the observation scores of different road sections, so as to obtain a first transition probability score corresponding to the first high-precision road section and a second transition probability score corresponding to the second high-precision road section, wherein the second transition probability score is smaller than the first transition probability score;
the Viterbi score calculating unit is configured to, for any one current track point, start from a first high-precision road section which can be observed by the current track point, take a transition probability score of the first high-precision road section as a weight value, and weight the observed score of the first high-precision road section based on the weight value to obtain a Viterbi score of the first high-precision road section; sequentially taking the obtained Viterbi score as an observation score of the next candidate continuous high-precision road section, and continuously executing Viterbi score calculation operation on the candidate continuous high-precision road section based on the transition probability score corresponding to the candidate continuous high-precision road section until the Viterbi score of the last first high-precision road section which can be observed by the last track point is obtained through calculation;
A target fine segment determining unit configured to select a viterbi score value having a largest value from the plurality of viterbi scores obtained by calculation, and to use a plurality of continuous high-fine segments corresponding to the viterbi score value having the largest value as a plurality of target fine segments having a continuous topological relation;
and a high-precision navigation path generation unit configured to generate a high-precision navigation path matched with the conventional navigation path according to a plurality of continuous target high-precision road segments.
12. The apparatus according to claim 11, wherein the observation scoring unit is specifically configured to:
scoring the observed value of each first high-precision road segment as 1, and scoring the observed value of each second high-precision road segment as 0.5; in a corresponding manner,
the transition probability value scoring unit is specifically configured to:
for any one current high-precision road section, if the observation score of a high-precision road section which is continuous with the current high-precision road section is 1, and when the candidate continuous high-precision road section and the current high-precision road section are the same road section, the transition probability score of the candidate continuous high-precision road section is scored as 1+E, wherein E is a minimum value larger than 0; or,
if the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 1+2E; or,
If the observation score of the high-precision road section continuous with the current high-precision road section candidate is 1 and the high-precision road section continuous with the candidate is not topologically connected with the current high-precision road section, scoring the transition probability score of the high-precision road section continuous with the candidate as 0; or,
if the observed score of the high-precision road segment continuous with the current high-precision road segment candidate is 0.5, the transition probability score of the high-precision road segment continuous with the candidate is scored as 1.
13. The apparatus of claim 12, wherein in the case where the current high-precision road segment selects a continuous high-precision road segment, the observed score is 1, and the transition probability score of the candidate continuous high-precision road segment is 0:
and taking the current high-precision road section as the ending road section of the matched path, taking the high-precision road section continuous with the candidate as the starting road section of the next matched path, and continuously executing scoring operation for the transition probability score according to the topological relation of the high-precision road section and the observation scores of different road sections.
14. The apparatus of claim 11, wherein the apparatus further comprises:
the transverse road section identification module is configured to identify the transverse road section in the traditional navigation path according to the topological relation of the road network, wherein the transverse road section is: the method comprises the steps that a target observation road section which can be observed by at least two continuous track points in a traditional navigation path does not have a topological connection relationship, and the navigation road section corresponding to the at least two continuous track points is arranged under the condition that the target observation road section is not a road entrance road section, a non-road starting road section and a non-road ending road section;
The first observation score correction module is configured to correct the observation scores of the high-precision road sections which can be observed by the track points corresponding to the transverse road sections into second observation scores;
correspondingly, the transition probability value scoring unit comprises:
and the transition probability value scoring subunit is configured to score the transition probability of each first high-precision road segment and each second high-precision road segment according to the topological relation of the high-precision road segments and the observation scores corrected by different road segments.
15. The apparatus of claim 14, wherein the apparatus further comprises:
the second observation score correction module is specifically configured to, before scoring the transition probabilities of each first high-precision road segment and each second high-precision road segment according to the topological relation of the high-precision road segments and the observation scores after correction of different road segments, search whether an entrance road segment exists from a target observation road segment which can be observed by a track point of the cross road segment according to a direction opposite to the traditional navigation path, and if the entrance road segment can be found, correct the observation scores of all the high-precision road segments between the target observation road segment and the entrance road segment to be second observation scores and correct the observation scores corresponding to the entrance road segment to be first observation scores.
16. The apparatus of claim 10, wherein the consistency of the location information means that a track point of a conventional navigation path has an intersection point with a road range corresponding to a high-definition road segment;
under the condition that a traditional navigation path passes through an urban road intersection, the road range corresponding to the urban road intersection is as follows: sharing the same road range for all high-precision road sections in the urban road junction; or,
in the case where a conventional navigation path passes through a non-bidirectional road including two road edge lines, the road range corresponding to the non-bidirectional road is: the road boundaries of each high-precision road section are connected end to obtain the road boundary; or,
in the case that the conventional navigation path passes through a bidirectional road including only one road edge line, the bidirectional road corresponds to a road range of: the high-precision map is formed by connecting the road edge line of the current bidirectional road and the edge line of the opposite-side bidirectional road end to end, wherein the opposite-side bidirectional road is a bidirectional road adjacent to the current bidirectional road and opposite to the road direction of the current bidirectional road in the high-precision map.
17. The apparatus of claim 10, wherein for a starting segment of the high-precision navigation path, a proportion of a first high-precision segment within a first distance threshold from the starting segment reaches a first proportional threshold;
And for the tail road section of the high-precision navigation path, the proportion of the first high-precision road section within a second distance threshold range from the tail road section reaches a second proportion threshold.
18. The apparatus of claim 10, wherein the fact that the label of the conventional navigation path corresponding to the current track point is consistent with the label information of the high-precision road segment corresponding to the current track point means that: and the labels of the traditional navigation paths corresponding to the third distance threshold range before and after the current track point are consistent with the label information of the high-precision road section corresponding to the current track point.
19. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-9.
20. A storage medium having stored thereon a computer program, which when executed by a processor, implements the method of any of claims 1-9.
21. A vehicle comprising the apparatus of any one of claims 10-18, or comprising the electronic device of claim 19.
CN202211012896.6A 2022-08-23 2022-08-23 Determination method, device, equipment, medium and vehicle of high-precision navigation path Pending CN117664157A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202211012896.6A CN117664157A (en) 2022-08-23 2022-08-23 Determination method, device, equipment, medium and vehicle of high-precision navigation path
PCT/CN2022/114698 WO2024040499A1 (en) 2022-08-23 2022-08-25 Method and apparatus for determining high-precision navigation path, and device, medium and vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211012896.6A CN117664157A (en) 2022-08-23 2022-08-23 Determination method, device, equipment, medium and vehicle of high-precision navigation path

Publications (1)

Publication Number Publication Date
CN117664157A true CN117664157A (en) 2024-03-08

Family

ID=90011988

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211012896.6A Pending CN117664157A (en) 2022-08-23 2022-08-23 Determination method, device, equipment, medium and vehicle of high-precision navigation path

Country Status (2)

Country Link
CN (1) CN117664157A (en)
WO (1) WO2024040499A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117906593A (en) * 2024-03-19 2024-04-19 广州小鹏自动驾驶科技有限公司 Map construction method, terminal device and storage medium

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005172628A (en) * 2003-12-11 2005-06-30 Nissan Motor Co Ltd Route guide device and route guide program
CN106595683B (en) * 2015-10-19 2020-07-31 阿里巴巴(中国)有限公司 Navigation method and device
CN112699708A (en) * 2019-10-22 2021-04-23 北京初速度科技有限公司 Method and device for generating lane-level topology network
CN112857378A (en) * 2019-11-26 2021-05-28 北京初速度科技有限公司 Track matching method and device
EP4113240A4 (en) * 2020-03-26 2023-05-03 Huawei Technologies Co., Ltd. Driving control method and apparatus
CN114689074B (en) * 2022-04-28 2022-11-29 阿波罗智联(北京)科技有限公司 Information processing method and navigation method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117906593A (en) * 2024-03-19 2024-04-19 广州小鹏自动驾驶科技有限公司 Map construction method, terminal device and storage medium

Also Published As

Publication number Publication date
WO2024040499A1 (en) 2024-02-29

Similar Documents

Publication Publication Date Title
EP3699048A1 (en) Travelling track prediction method and device for vehicle
CN111380539B (en) Vehicle positioning and navigation method and device and related system
CN108151751B (en) Path planning method and device based on combination of high-precision map and traditional map
CN111932887B (en) Method and equipment for generating lane-level track data
EP2012088B1 (en) Road information generating apparatus, road information generating method and road information generating program
JP4950494B2 (en) Traveling lane estimation apparatus and traveling lane estimation method
KR20200024934A (en) Lane information management method, driving control method and lane information management device
CN112747755B (en) Method and device for determining road route, readable storage medium and map updating system
Blazquez et al. Simple map-matching algorithm applied to intelligent winter maintenance vehicle data
CN113232658B (en) Vehicle positioning method and device, electronic equipment and storage medium
JPWO2020116264A1 (en) Vehicle driving support method, vehicle driving support device and automatic driving system
US11724713B2 (en) Apparatus for generating data of travel path inside intersection, program for generating data of travel path inside intersection, and storage medium
JP2021113816A (en) Output device, control method, program, and storage medium
CN112797998A (en) Vehicle lane level positioning method, corresponding program carrier, product, device and vehicle
CN117664157A (en) Determination method, device, equipment, medium and vehicle of high-precision navigation path
JP5656067B2 (en) Road node position management system, road node position management method, and road node position management program
US10697787B2 (en) Detour recommended area estimation system, detour recommended area estimation program, and navigation device
CN112633812B (en) Track segmentation method, device, equipment and storage medium for freight vehicle
CN117664156A (en) Path planning method, device, equipment, medium and vehicle
CN116383321A (en) Decision environment construction method, device, vehicle and storage medium
KR101757181B1 (en) System and method for providing lane-based traffic information
CN115143973A (en) Map information determination device, storage medium, and map information determination method
JP4957021B2 (en) VEHICLE MAP DATA CREATION DEVICE AND VEHICLE MAP DATA UPDATE DEVICE
CN114462609A (en) Floating car data track reduction method based on hidden Markov model
KR101843672B1 (en) Mapping system and mapping method

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