[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN114049410A - Semantic map-based test route generation method, test method and test device - Google Patents

Semantic map-based test route generation method, test method and test device Download PDF

Info

Publication number
CN114049410A
CN114049410A CN202111156033.1A CN202111156033A CN114049410A CN 114049410 A CN114049410 A CN 114049410A CN 202111156033 A CN202111156033 A CN 202111156033A CN 114049410 A CN114049410 A CN 114049410A
Authority
CN
China
Prior art keywords
intersection
navigation point
test
map
pair
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111156033.1A
Other languages
Chinese (zh)
Other versions
CN114049410B (en
Inventor
区彦开
邹清明
韩旭
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.)
Guangzhou Weride Technology Co Ltd
Original Assignee
Guangzhou Weride 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 Guangzhou Weride Technology Co Ltd filed Critical Guangzhou Weride Technology Co Ltd
Priority to CN202111156033.1A priority Critical patent/CN114049410B/en
Publication of CN114049410A publication Critical patent/CN114049410A/en
Application granted granted Critical
Publication of CN114049410B publication Critical patent/CN114049410B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/20—Drawing from basic elements, e.g. lines or circles
    • G06T11/206—Drawing of charts or graphs
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Navigation (AREA)

Abstract

The invention discloses a semantic map-based test route generation method, a semantic map-based test method and a semantic map-based test device. The method comprises the following steps: loading a semantic map according to the test area to obtain a test map; for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached one by one to generate a plurality of navigation point pairs of each intersection; traversing a plurality of navigation point pairs of each intersection, and matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection to obtain a plurality of first matching pairs; each navigation point pair of each intersection is used as a node, and a connecting edge is added between two navigation point pairs in each first matching pair to construct a directed graph; and connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route. The method can comprehensively cover intersections in the semantic map test area to automatically generate the test route, and is beneficial to improving the test efficiency of the semantic map.

Description

Semantic map-based test route generation method, test method and test device
Technical Field
The invention relates to the technical field of road testing, in particular to a test route generation method, a test method and a test device based on a semantic map.
Background
At present, engineers mainly mark high-precision maps acquired by vehicles to generate semantic maps, design and manufacture test routes aiming at the semantic maps according to the engineers, arrange the vehicles to carry out automatic driving test, and find out potential error marks in the semantic maps, such as lane line missing marks, mark errors and the like. The mode of manually generating the test route not only consumes a large amount of manpower, but also the generated test route is difficult to completely cover the semantic map, so that the test efficiency of the semantic map is not high.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a test route generation method, a test method and a test device based on a semantic map, which can comprehensively cover intersections in a test area of the semantic map to automatically generate test routes and are beneficial to improving the test efficiency of the semantic map.
In order to solve the above technical problem, in a first aspect, an embodiment of the present invention provides a semantic map-based test route generating method, including:
loading a semantic map according to the test area to obtain a test map;
for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached one by one to generate a plurality of navigation point pairs of each intersection;
traversing a plurality of navigation point pairs of each intersection, and matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection to obtain a plurality of first matching pairs;
each navigation point pair of each intersection is used as a node, and a connecting edge is added between two navigation point pairs in each first matching pair to construct a directed graph;
and connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route.
Further, the semantic map-based test route generation method further includes:
when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, matching the navigation point pair of the current intersection with each navigation point pair of the target intersection which can reach the current intersection to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain;
and then each navigation point pair of each intersection is taken as a node, a connecting edge is added between two navigation point pairs in each first matching pair, and a connecting edge is added between two navigation point pairs in each second matching pair, so that a directed graph is constructed.
Further, for each intersection on the test map, pairing the entry navigation points of the intersection with the exit navigation points of the intersection that can be reached by the entry navigation points one by one to generate a plurality of navigation point pairs of each intersection, specifically:
for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached by the entering navigation point one by one to generate a plurality of initial navigation point pairs, and selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs.
Further, the connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route, specifically:
traversing a plurality of navigation point pairs of each intersection based on a directed graph, judging whether the navigation point pair of the current intersection does not reach the navigation point pair of another intersection after passing through the boundary of a test area, and if so, rejecting the navigation point pair of the current intersection to obtain a middle graph;
traversing a plurality of navigation point pairs of each intersection based on the intermediate graph, matching each navigation point pair of the current intersection with each navigation point pair of another intersection reached by the current intersection to obtain a plurality of third matching pairs, and adding a connecting edge between two navigation point pairs in each third matching pair to generate a complete graph;
and connecting all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
Further, after the connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route, the method further includes:
according to the speed limit information of the test map and the length of the test route, the test route is divided into a plurality of test sub-routes with the test duration being smaller than the preset test duration, and a test route set is obtained.
Further, after the semantic map is loaded according to the test area to obtain the test map, before the pairing of the entry navigation point of the intersection and the exit navigation point of the intersection that can be reached by the entry navigation point of each intersection on the test map one by one to generate a plurality of navigation point pairs of each intersection, the method further includes:
and traversing each intersection in the semantic map, and collecting the intersections in the test area in an intersection set of the test map.
In a second aspect, an embodiment of the present invention provides a semantic map-based test route generation apparatus, including:
the test map acquisition module is used for loading the semantic map according to the test area to obtain a test map;
the navigation point pair generating module is used for pairing the entering navigation points of the intersections and the leaving navigation points of the intersections which can be reached one by one for each intersection on the test map to generate a plurality of navigation point pairs of each intersection;
the navigation point pair matching module is used for traversing a plurality of navigation point pairs of each intersection, matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection, and obtaining a plurality of first matching pairs;
the directed graph construction module is used for taking each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair and constructing a directed graph;
and the test route generation module is used for connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route.
In a third aspect, an embodiment of the present invention provides a semantic map-based testing method, including:
loading a semantic map according to the test area to obtain a test map;
for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached one by one to generate a plurality of navigation point pairs of each intersection;
traversing a plurality of navigation point pairs of each intersection, and matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection to obtain a plurality of first matching pairs;
each navigation point pair of each intersection is used as a node, and a connecting edge is added between two navigation point pairs in each first matching pair to construct a directed graph;
connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route;
and sending the test route to the vehicle, enabling the vehicle to carry out automatic driving test according to the test route, and correcting the test map according to the obtained test data.
Further, the semantic map-based testing method further includes:
when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, matching the navigation point pair of the current intersection with each navigation point pair of the target intersection which can reach the current intersection to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain;
and then each navigation point pair of each intersection is taken as a node, a connecting edge is added between two navigation point pairs in each first matching pair, and a connecting edge is added between two navigation point pairs in each second matching pair, so that a directed graph is constructed.
In a fourth aspect, an embodiment of the present invention provides a semantic map-based testing apparatus, including:
the test map acquisition module is used for loading the semantic map according to the test area to obtain a test map;
the navigation point pair generating module is used for pairing the entering navigation points of the intersections and the leaving navigation points of the intersections which can be reached one by one for each intersection on the test map to generate a plurality of navigation point pairs of each intersection;
the navigation point pair matching module is used for traversing a plurality of navigation point pairs of each intersection, matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection, and obtaining a plurality of first matching pairs;
the directed graph construction module is used for taking each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair and constructing a directed graph;
the test route generation module is used for connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route;
and the automatic driving test module is used for sending a test route to the vehicle, so that the vehicle carries out automatic driving test according to the test route and corrects the test map according to the obtained test data.
The embodiment of the invention has the following beneficial effects:
the method comprises the steps of loading a semantic map according to a test area to obtain a test map, pairing an entering navigation point of an intersection with an leaving navigation point of a reachable intersection for each intersection on the test map one by one to generate a plurality of navigation point pairs of each intersection, traversing the plurality of navigation point pairs of each intersection, matching each navigation point pair of a current intersection with each navigation point pair of a next intersection reachable by the current intersection to obtain a plurality of first matching pairs, using each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, constructing a directed graph, connecting all connecting edges according to the directed graph to connect all nodes in series to generate a test route, and realizing automatic generation of the test route. Compared with the prior art, the embodiment of the invention traverses each intersection in the test area on the semantic map by using the marked semantic map, automatically generates the test route by covering the left-turn, right-turn, straight-going and turning-around directions of each intersection, can fully cover the intersections in the test area of the semantic map, and is favorable for improving the test efficiency of the semantic map.
Drawings
FIG. 1 is a schematic flow chart of a semantic map-based test route generation method according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of an exemplary intersection according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram of an exemplary intersection according to a first embodiment of the present invention;
FIG. 4 is a schematic cross-sectional view of another example of the first embodiment of the present invention;
FIG. 5 is a schematic cross-sectional view of another example of the first embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a semantic map based test route generation apparatus according to a second embodiment of the present invention;
FIG. 7 is a flowchart illustrating a semantic map based testing method according to a third embodiment of the present invention;
fig. 8 is a schematic structural diagram of a semantic map-based testing apparatus according to a fourth embodiment of the present invention.
Detailed Description
The technical solutions in the present invention will be described clearly and completely with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that, the step numbers in the text are only for convenience of explanation of the specific embodiments, and do not serve to limit the execution sequence of the steps. The method provided by the embodiment can be executed by the relevant terminal device, and the server is taken as an example for explanation below.
As shown in fig. 1, a first embodiment of the present invention provides a semantic map-based test route generation method, including steps S11 to S15:
s11, loading the semantic map according to the test area to obtain a test map;
s12, for each intersection on the test map, pairing the entry navigation points of the intersection with the exit navigation points of the intersection which can be reached by the entry navigation points one by one to generate a plurality of navigation point pairs of each intersection;
s13, traversing a plurality of navigation point pairs of each intersection, and matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection to obtain a plurality of first matching pairs;
s14, taking each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, and constructing a directed graph;
and S15, connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route.
It should be noted that the semantic map is a marked semantic map, and the semantic map is marked with a traffic direction, an intersection label, an intersection coordinate, scale information, speed limit information, and the like.
Illustratively, in step S11, the user selects a test area on the semantic map through the user terminal according to the actual test requirement, and initiates a test route generation request to the server. And the server responds to a test route generation request initiated by the user terminal, and loads the semantic map corresponding to the test area according to the marked semantic map to obtain the test map.
The server determines the test area according to the specified test points, for example, a polygonal area formed by connecting the test points is determined as the test area, or a minimum circular area containing the test points is determined as the test area.
In step S12, after the test map is obtained, intersections located in the test area are screened out according to the coordinates of each intersection on the semantic map, and all intersections on the test map are obtained. For each intersection on the test map, all the entry navigation points and all the exit navigation points of the same intersection are found, then the arrival relation between all the entry navigation points and all the exit navigation points of the intersection is determined according to the traffic direction on the semantic map, and finally the entry navigation points of the intersection and the exit navigation points of the intersection which can be reached by the entry navigation points are paired one by one to generate a plurality of navigation point pairs of the intersection, so that a plurality of navigation point pairs of each intersection are generated.
For example, as shown in fig. 2, for intersection a on the test map, all the entry navigation points a of intersection a are found01、A02、A03And all departure navigation points A of intersection A11、A12、A13Determining all the entry navigation points A according to the passing direction on the semantic map01、A02、A03And all departure navigation points A11、A12、A13Due to A01Can reach A11、A12、A13，A02Can reach A11、A12、A13，A03Can reach A11、A12、A13Thus will A01Are respectively reacted with A11、A12、A13Pairing to obtain a navigation point pair (A)01，A11)、(A01，A12)、(A01，A13) A is02Are respectively reacted with A11、A12、A13Pairing to obtain a navigation point pair (A)02，A11)、(A02，A12)、(A02，A13) A is03Are respectively reacted with A11、A12、A13Pairing to obtain a navigation point pair (A)03，A11)、(A03，A12)、(A03，A13) Thereby generating a plurality of navigation point pairs of the intersection A. And when traversing each intersection on the test map, generating a plurality of navigation point pairs of each intersection.
In step S13, traversing a plurality of navigation point pairs at each intersection, for one navigation point pair at a current intersection being traversed, extracting an exit navigation point from the navigation point pair, determining an arrival relationship between the exit navigation point and all entry navigation points at a next intersection reachable by the exit navigation point according to a traffic direction on a semantic map, finding a navigation point pair to which all entry navigation points at the next intersection reachable by the exit navigation point belong, and matching the navigation point pair with each navigation point pair at the next intersection reachable by the exit navigation point to obtain a plurality of first matching pairs.
For example, as shown in FIG. 3, when traversing to a navigation point pair of intersection A (A)01，A11) From the navigation point pair (A)01，A11) Extract the departure navigation point A11Determining departure navigation point A according to the traffic direction on the semantic map11All the entry navigation points B of the next intersection B reachable thereto01、B02、B03Due to A11Can reach B01Unreachable B02And B03Thus finding B01Belonging navigation point pair (B)01，B11)、(B01，B12)、(B01，B13) The navigation point pair (A)01，A11) Respectively corresponding to the navigation point pairs (B)01，B11)、(B01，B12)、(B01，B13) Matching to obtain three first matching pairs [ (A)01，A11)，(B01，B11)]、[(A01，A11)，(B01，B12)]、[(A01，A11)，(B01，B13)]. And when all the navigation point pairs of each intersection on the test map are traversed, obtaining a plurality of first matching pairs.
In step S14, a directed graph is constructed by using each navigation point pair of each intersection as a node and adding a connecting edge between two navigation point pairs in each first matching pair.
And the side length of a connecting edge between two navigation point pairs in the first matching pair is the distance between the two navigation point pairs. The server can calculate the distance between the two navigation point pairs according to the scale information on the test map and the length of the passing path between the two navigation point pairs on the test map.
In step S15, all the connection edges are connected according to the directed graph to connect all the nodes in series, and a test route is generated, so that the test route is automatically generated covering the left-turn, right-turn, straight-going, and turning-around directions of each intersection.
According to the embodiment, the marked semantic map is utilized to traverse each intersection in the test area on the semantic map, and the test route is automatically generated by covering the left-turn, right-turn, straight-going and turning-around directions of each intersection, so that the test route can be automatically generated by covering the intersections in the test area of the semantic map comprehensively, and the test efficiency of the semantic map is improved.
In a preferred embodiment, the semantic map-based test route generation method further includes: when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, matching the navigation point pair of the current intersection with each navigation point pair of the target intersection which can reach the current intersection to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain; and then each navigation point pair of each intersection is taken as a node, a connecting edge is added between two navigation point pairs in each first matching pair, and a connecting edge is added between two navigation point pairs in each second matching pair, so that a directed graph is constructed.
As an example, in step S13, if a navigation point pair of the traversed current intersection is a navigation point pair that passes through the boundary of the test area and reaches the next intersection, an exit navigation point is extracted from the navigation point pair, then the arrival relationship between the exit navigation point and all the entry navigation points of the target intersection that can be reached by the exit navigation point is determined according to the traffic direction on the semantic map and the preset distance outside the domain, and finally the navigation point pairs that all the entry navigation points of the target intersection that can be reached by the exit navigation point belong to are found, and the navigation point pairs are respectively matched with each navigation point pair of the target intersection that can be reached by the exit navigation point, so as to obtain a plurality of second matching pairs.
For example, as shown in FIG. 4, when traversing to a navigation point pair of intersection A (A)01，A12) Due to the navigation point pair (A)01，A12) Is a pair of navigation points (B) which passes through the boundary of the test area and reaches the intersection B03，B13) Therefore, the navigation point pair (A) needs to be confirmed again01，A12) Passing the boundary of the test area and determining whether there is a return test area, and (A) identifying the navigation point pair01，A12) Whether the length of the passing path between the point pair (A) and each intersection in the test area exceeds the distance outside the preset area or not is judged from the navigation point pair (A)01，A12) Extract the departure navigation point A12Determining the departure navigation point A according to the passing direction on the semantic map and the preset distance outside the domain12All the entry navigation points B of the target intersection B reachable therewith01、B02、B03Due to A12Can reach B03Unreachable B01And B02Thus finding B03Belonging navigation point pair (B)03，B11)、(B03，B12)、(B03，B13) The navigation point pair (A)01，A12) Respectively corresponding to the navigation point pairs (B)03，B11)、(B03，B12)、(B03，B13) Matching to obtain three first matching pairs [ (A)01，A12)，(B03，B11)]、[(A01，A12)，(B03，B12)]、[(A01，A12)，(B03，B13)]. And when all the navigation point pairs of each intersection on the test map are traversed, obtaining a plurality of second matching pairs.
In step S14, a directed graph is constructed by using each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, and adding a connecting edge between two navigation point pairs in each second matching pair.
And the side length of the connecting edge between the two navigation point pairs in the second matching pair is the distance between the two navigation point pairs. The server can calculate the distance between the two navigation point pairs according to the scale information on the test map and the length of the passing path between the two navigation point pairs on the test map.
According to the embodiment, when the navigation point of the current intersection is opposite to the navigation point reaching the next intersection through the boundary of the test area, the target intersection capable of reaching the current intersection is covered, so that the intersection in the test area on the semantic map can be completely covered, the test route can be automatically generated, and the test efficiency of the semantic map is improved.
In a preferred embodiment, for each intersection on the test map, the entering navigation points of the intersection and the leaving navigation points of the intersections that can be reached by the entering navigation points are paired one by one, and a plurality of navigation point pairs of each intersection are generated, specifically: for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached by the entering navigation point one by one to generate a plurality of initial navigation point pairs, and selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs.
Illustratively, after the test map is obtained, the intersections in the test area are screened out according to the coordinates of all intersections on the semantic map, and all intersections on the test map are obtained. For each intersection on a test map, finding all entry navigation points and all exit navigation points of the same intersection, determining the arrival relation between all the entry navigation points and all the exit navigation points of the intersection according to the traffic direction on a semantic map, pairing the entry navigation points of the intersection with the exit navigation points of the intersection which can be reached by the entry navigation points one by one to generate a plurality of initial navigation point pairs of the intersection, and finally, randomly selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs, thereby generating a plurality of navigation point pairs of each intersection.
For example, as shown in fig. 2 and 5, for intersection a on the test map, all the entry navigation points a of intersection a are found01、A02、A03And all departure navigation points A of intersection A11、A12、A13Determining all the entry navigation points A according to the passing direction on the semantic map01、A02、A03And all departure navigation points A11、A12、A13Due to A01Can reach A11、A12、A13，A02Can reach A11、A12、A13，A03Can reach A11、A12、A13Thus will A01Are respectively reacted with A11、A12、A13Pairing to obtain an initial navigation point pair (A)01，A11)、(A01，A12)、(A01，A13) A is02Are respectively reacted with A11、A12、A13Pairing to obtain an initial navigation point pair (A)02，A11)、(A02，A12)、(A02，A13) A is03Are respectively reacted with A11、A12、A13Pairing to obtain an initial navigation point pair (A)03，A11)、(A03，A12)、(A03，A13) Thus, a plurality of initial navigation point pairs of the intersection A are generated, and only the initial navigation point pairs (A) are arranged on the 'U' side of the intersection A01，A11) With initial navigation point pairs on the A '+' -edges of the intersection (A)01，A12)、(A01，A13) There is an initial navigation point pair (A) at the crossing A '+' edge02，A11)、(A03，A11) There is an initial navigation point pair (A) on the "-" side of the intersection A02，A12)、(A02，A13)、(A03，A12)、(A03，A13) Selecting an initial navigation point pair from all initial navigation point pairs on each edge of the intersection A as a navigation point pair, for example, selecting an initial navigation point pair from the 'U' edge of the intersection A (A)01，A11) Selecting an initial navigation point pair (A) from the A '+' -side of the intersection as a navigation point pair01，A12) Selecting an initial navigation point pair (A) on the A '+' side of the intersection as the navigation point pair02，A11) As a navigation point pair, selecting an initial navigation point pair (A) on the "-" side of the intersection A02，A12) And as the navigation point pairs, obtaining a plurality of navigation point pairs so as to generate a plurality of navigation point pairs of each intersection. And when traversing each intersection on the test map, generating a plurality of navigation point pairs of each intersection.
According to the embodiment, the plurality of initial navigation point pairs of each intersection are subjected to duplication elimination to obtain the plurality of navigation point pairs, so that the data volume of subsequent traversal pairing can be reduced, the processing pressure of the server is reduced, and the semantic map testing efficiency is improved.
In a preferred embodiment, the connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate the test route specifically includes: traversing a plurality of navigation point pairs of each intersection based on a directed graph, judging whether the navigation point pair of the current intersection does not reach the navigation point pair of another intersection after passing through the boundary of a test area, and if so, rejecting the navigation point pair of the current intersection to obtain a middle graph; traversing a plurality of navigation point pairs of each intersection based on the intermediate graph, matching each navigation point pair of the current intersection with each navigation point pair of another intersection reached by the current intersection to obtain a plurality of third matching pairs, and adding a connecting edge between two navigation point pairs in each third matching pair to generate a complete graph; and connecting all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
Illustratively, removing the navigation point pairs which cannot return to the test area after crossing the boundary of the test area in the directed graph to obtain a middle graph. By eliminating the navigation point pairs which cannot be returned, the interference of useless navigation point pairs can be eliminated, and the accurate test route can be generated. Considering that only a part of navigation point pairs in the intermediate graph may have connecting edges therebetween and another part of navigation point pairs have disconnection, the connecting edges of the part of navigation point pairs need to be completed to generate a complete graph, so as to connect all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
For example, in directed graph G, the classical algorithm tarjan is used to find strongly connected components (a graph in which each pair of nodes can reach each other is called a strongly connected graph. And only the nodes in the strongly connected component with the largest number of nodes are left to remove the points of which the parts can reach the map boundary and can not return to the map, so as to obtain the intermediate map. And (3) solving the shortest path of the single source for each node in the intermediate graph by using a classical algorithm dijkstra to obtain the distance between each pair of nodes, and supplementing the intermediate graph into a complete graph. In order to cover left-turn, right-turn, straight-going and turning-around directions of each intersection, a test route is automatically generated, the test route is required to cover all nodes in a complete graph, so that the problem is converted into a Traveling Salesman Problem (TSP), any intelligent algorithm (such as a genetic algorithm, an ant colony algorithm and the like) can be used for finding a shorter annular route (also called a Hamilton loop), and all the nodes are connected in series.
According to the embodiment, the navigation point pairs which cannot be returned are removed firstly, and then the connecting edges between the partially disconnected navigation point pairs are supplemented, so that intersections in the semantic map testing area can be further covered comprehensively, an accurate testing route is generated automatically, and the semantic map testing efficiency is improved.
In a preferred embodiment, after said connecting all said connecting edges according to said directed graph to connect all said nodes in series to generate a test route, further comprising: according to the speed limit information of the test map and the length of the test route, the test route is divided into a plurality of test sub-routes with the test duration being smaller than the preset test duration, and a test route set is obtained.
As an example, considering that the generated test route may be relatively long, the vehicle cannot run through the whole test route at a time to complete the test, and the driver also needs to take a time to rest, after the test route is generated, according to the speed limit information on the test map and the length of the passing path of the test route, the test route is split into a plurality of test sub-routes with the test duration being less than the preset test duration, so as to obtain a test route set.
According to the embodiment, the test route is divided into the plurality of test sub-routes, so that the test safety of the subsequent semantic map can be ensured.
In a preferred embodiment, after the semantic map is loaded according to the test area to obtain the test map, before the pairing an entry navigation point of an intersection with an exit navigation point of an intersection reachable by the entry navigation point for each intersection on the test map one by one to generate a plurality of navigation point pairs for each intersection, the method further includes: and traversing each intersection in the semantic map, and collecting the intersections in the test area in an intersection set of the test map.
Illustratively, whether each intersection on the semantic map is located in the test area is judged according to the intersection label and the intersection coordinate on the semantic map, if yes, the intersection is considered as the intersection in the test area, and the intersection is collected in the intersection set of the test map.
Based on the same inventive concept as the first embodiment, a second embodiment of the present invention provides a semantic map-based test route generation apparatus as shown in fig. 6, including: the test map obtaining module 21 is configured to load a semantic map according to the test area to obtain a test map; the navigation point pair generating module 22 is configured to pair an entering navigation point of a road junction with an exiting navigation point of the road junction reachable by the entering navigation point one by one for each road junction on the test map, and generate a plurality of navigation point pairs of each road junction; the navigation point pair matching module 23 is configured to traverse a plurality of navigation point pairs at each intersection, match each navigation point pair at the current intersection with each navigation point pair at the next intersection where the current intersection can reach, and obtain a plurality of first matching pairs; the directed graph construction module 24 is configured to use each navigation point pair of each intersection as a node, and add a connecting edge between two navigation point pairs in each first matching pair to construct a directed graph; and the test route generating module 25 is configured to connect all the connection edges according to the directed graph to connect all the nodes in series, so as to generate a test route.
In a preferred embodiment, the navigation point pair matching module 23 is further configured to match the navigation point pair of the current intersection with each navigation point pair of the target intersection that can be reached by the navigation point pair of the current intersection when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, so as to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain; the directed graph constructing module 24 is configured to construct a directed graph by using each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, and adding a connecting edge between two navigation point pairs in each second matching pair.
In a preferred embodiment, for each intersection on the test map, the entering navigation points of the intersection and the leaving navigation points of the intersections that can be reached by the entering navigation points are paired one by one, and a plurality of navigation point pairs of each intersection are generated, specifically: for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached by the entering navigation point one by one to generate a plurality of initial navigation point pairs, and selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs.
In a preferred embodiment, the connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate the test route specifically includes: traversing a plurality of navigation point pairs of each intersection based on a directed graph, judging whether the navigation point pair of the current intersection does not reach the navigation point pair of another intersection after passing through the boundary of a test area, and if so, rejecting the navigation point pair of the current intersection to obtain a middle graph; traversing a plurality of navigation point pairs of each intersection based on the intermediate graph, matching each navigation point pair of the current intersection with each navigation point pair of another intersection reached by the current intersection to obtain a plurality of third matching pairs, and adding a connecting edge between two navigation point pairs in each third matching pair to generate a complete graph; and connecting all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
In a preferred embodiment, after said connecting all said connecting edges according to said directed graph to connect all said nodes in series to generate a test route, further comprising: according to the speed limit information of the test map and the length of the test route, the test route is divided into a plurality of test sub-routes with the test duration being smaller than the preset test duration, and a test route set is obtained.
In a preferred embodiment, after the semantic map is loaded according to the test area to obtain the test map, before the pairing an entry navigation point of an intersection with an exit navigation point of an intersection reachable by the entry navigation point for each intersection on the test map one by one to generate a plurality of navigation point pairs for each intersection, the method further includes: and traversing each intersection in the semantic map, and collecting the intersections in the test area in an intersection set of the test map.
As shown in fig. 7, a third embodiment of the present invention provides a semantic map-based testing method, including steps S31 to S36:
s31, loading the semantic map according to the test area to obtain a test map;
s32, for each intersection on the test map, pairing the entry navigation points of the intersection with the exit navigation points of the intersection which can be reached by the entry navigation points one by one to generate a plurality of navigation point pairs of each intersection;
s33, traversing a plurality of navigation point pairs of each intersection, and matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection to obtain a plurality of first matching pairs;
s34, taking each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, and constructing a directed graph;
s35, connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route;
and S36, sending the test route to the vehicle, enabling the vehicle to carry out automatic driving test according to the test route, and correcting the test map according to the obtained test data.
It should be noted that the semantic map is a marked semantic map, and the semantic map is marked with a traffic direction, an intersection label, an intersection coordinate, scale information, speed limit information, and the like.
Illustratively, in step S31, the user selects a test area on the semantic map through the user terminal according to the actual test requirement, and initiates a test route generation request to the server. And the server responds to a test route generation request initiated by the user terminal, and loads the semantic map corresponding to the test area according to the marked semantic map to obtain the test map.
The server determines the test area according to the specified test points, for example, a polygonal area formed by connecting the test points is determined as the test area, or a minimum circular area containing the test points is determined as the test area.
In step S32, after the test map is obtained, intersections located in the test area are screened out according to the coordinates of each intersection on the semantic map, and all intersections on the test map are obtained. For each intersection on the test map, all the entry navigation points and all the exit navigation points of the same intersection are found, then the arrival relation between all the entry navigation points and all the exit navigation points of the intersection is determined according to the traffic direction on the semantic map, and finally the entry navigation points of the intersection and the exit navigation points of the intersection which can be reached by the entry navigation points are paired one by one to generate a plurality of navigation point pairs of the intersection, so that a plurality of navigation point pairs of each intersection are generated.
In step S33, traversing a plurality of navigation point pairs at each intersection, for one navigation point pair at a current intersection being traversed, extracting an exit navigation point from the navigation point pair, determining an arrival relationship between the exit navigation point and all entry navigation points at a next intersection reachable by the exit navigation point according to a traffic direction on a semantic map, finding a navigation point pair to which all entry navigation points at the next intersection reachable by the exit navigation point belong, and matching the navigation point pair with each navigation point pair at the next intersection reachable by the exit navigation point to obtain a plurality of first matching pairs.
In step S34, a directed graph is constructed by using each navigation point pair of each intersection as a node and adding a connecting edge between two navigation point pairs in each first matching pair.
And the side length of a connecting edge between two navigation point pairs in the first matching pair is the distance between the two navigation point pairs. The server can calculate the distance between the two navigation point pairs according to the scale information on the test map and the length of the passing path between the two navigation point pairs on the test map.
In step S35, all the connection edges are connected according to the directed graph to connect all the nodes in series, and a test route is generated, so that the test route is automatically generated covering the left-turn, right-turn, straight-going, and turning-around directions of each intersection.
In step S36, the user may mark the generated test route with an overlay test, name the corresponding name, and upload the name to the server. When the vehicle is tested, the test route is automatically captured from the server, and the captured test route is sent to the vehicle by the server. The safer may select a test route that covers the test, causing the vehicle to automatically traverse the test route. If the vehicle stops testing, the vehicle records the current running place, and the next test starts from the last test place. If the safety personnel find that the vehicle has problems in the automatic driving process, the safety personnel can report the problems to the vehicle through the user terminal, the vehicle can automatically collect test data and upload the test data to the server, so that engineers can check the uploaded test data and correct problematic places. And after the semantic map is corrected, the vehicle can perform automatic driving test again until the problem in the test area is thoroughly solved.
In the embodiment, the marked semantic map is utilized to traverse each intersection in the test area on the semantic map, and the test route is automatically generated by covering the left-turn, right-turn, straight-going and turning-around directions of each intersection, so that the vehicle can automatically drive and test according to the test route, and the test map is corrected according to the obtained test data, so that the intersection in the test area of the semantic map can be completely covered, the test route is automatically generated, and the test efficiency of the semantic map is improved.
In a preferred embodiment, the semantic map-based test route generation method further includes: when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, matching the navigation point pair of the current intersection with each navigation point pair of the target intersection which can reach the current intersection to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain; and then each navigation point pair of each intersection is taken as a node, a connecting edge is added between two navigation point pairs in each first matching pair, and a connecting edge is added between two navigation point pairs in each second matching pair, so that a directed graph is constructed.
As an example, in step S33, if a navigation point pair of the traversed current intersection is a navigation point pair that passes through the boundary of the test area and reaches the next intersection, an exit navigation point is extracted from the navigation point pair, then the arrival relationship between the exit navigation point and all the entry navigation points of the target intersection that can be reached by the exit navigation point is determined according to the traffic direction on the semantic map and the preset distance outside the domain, and finally the navigation point pairs that all the entry navigation points of the target intersection that can be reached by the exit navigation point belong to are found, and the navigation point pairs are respectively matched with each navigation point pair of the target intersection that can be reached by the exit navigation point, so as to obtain a plurality of second matching pairs.
In step S34, a directed graph is constructed by using each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, and adding a connecting edge between two navigation point pairs in each second matching pair.
And the side length of the connecting edge between the two navigation point pairs in the second matching pair is the distance between the two navigation point pairs. The server can calculate the distance between the two navigation point pairs according to the scale information on the test map and the length of the passing path between the two navigation point pairs on the test map.
According to the embodiment, when the navigation point of the current intersection is opposite to the navigation point reaching the next intersection through the boundary of the test area, the target intersection capable of reaching the current intersection is covered, so that the intersection in the test area on the semantic map can be completely covered, the test route can be automatically generated, and the test efficiency of the semantic map is improved.
In a preferred embodiment, for each intersection on the test map, the entering navigation points of the intersection and the leaving navigation points of the intersections that can be reached by the entering navigation points are paired one by one, and a plurality of navigation point pairs of each intersection are generated, specifically: for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached by the entering navigation point one by one to generate a plurality of initial navigation point pairs, and selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs.
Illustratively, after the test map is obtained, the intersections in the test area are screened out according to the coordinates of all intersections on the semantic map, and all intersections on the test map are obtained. For each intersection on a test map, finding all entry navigation points and all exit navigation points of the same intersection, determining the arrival relation between all the entry navigation points and all the exit navigation points of the intersection according to the traffic direction on a semantic map, pairing the entry navigation points of the intersection with the exit navigation points of the intersection which can be reached by the entry navigation points one by one to generate a plurality of initial navigation point pairs of the intersection, and finally, randomly selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs, thereby generating a plurality of navigation point pairs of each intersection.
According to the embodiment, the plurality of initial navigation point pairs of each intersection are subjected to duplication elimination to obtain the plurality of navigation point pairs, so that the data volume of subsequent traversal pairing can be reduced, the processing pressure of the server is reduced, and the semantic map testing efficiency is improved.
In a preferred embodiment, the connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate the test route specifically includes: traversing a plurality of navigation point pairs of each intersection based on a directed graph, judging whether the navigation point pair of the current intersection does not reach the navigation point pair of another intersection after passing through the boundary of a test area, and if so, rejecting the navigation point pair of the current intersection to obtain a middle graph; traversing a plurality of navigation point pairs of each intersection based on the intermediate graph, matching each navigation point pair of the current intersection with each navigation point pair of another intersection reached by the current intersection to obtain a plurality of third matching pairs, and adding a connecting edge between two navigation point pairs in each third matching pair to generate a complete graph; and connecting all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
Illustratively, removing the navigation point pairs which cannot return to the test area after crossing the boundary of the test area in the directed graph to obtain a middle graph. By eliminating the navigation point pairs which cannot be returned, the interference of useless navigation point pairs can be eliminated, and the accurate test route can be generated. Considering that only a part of navigation point pairs in the intermediate graph may have connecting edges therebetween and another part of navigation point pairs have disconnection, the connecting edges of the part of navigation point pairs need to be completed to generate a complete graph, so as to connect all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
For example, in directed graph G, the classical algorithm tarjan is used to find strongly connected components (a graph in which each pair of nodes can reach each other is called a strongly connected graph. And only the nodes in the strongly connected component with the largest number of nodes are left to remove the points of which the parts can reach the map boundary and can not return to the map, so as to obtain the intermediate map. And (3) solving the shortest path of the single source for each node in the intermediate graph by using a classical algorithm dijkstra to obtain the distance between each pair of nodes, and supplementing the intermediate graph into a complete graph. In order to cover left-turn, right-turn, straight-going and turning-around directions of each intersection, a test route is automatically generated, the test route is required to cover all nodes in a complete graph, so that the problem is converted into a Traveling Salesman Problem (TSP), any intelligent algorithm (such as a genetic algorithm, an ant colony algorithm and the like) can be used for finding a shorter annular route (also called a Hamilton loop), and all the nodes are connected in series.
According to the embodiment, the navigation point pairs which cannot be returned are removed firstly, and then the connecting edges between the partially disconnected navigation point pairs are supplemented, so that intersections in the semantic map testing area can be further covered comprehensively, an accurate testing route is generated automatically, and the semantic map testing efficiency is improved.
In a preferred embodiment, after said connecting all said connecting edges according to said directed graph to connect all said nodes in series to generate a test route, further comprising: according to the speed limit information of the test map and the length of the test route, the test route is divided into a plurality of test sub-routes with the test duration being smaller than the preset test duration, and a test route set is obtained.
As an example, considering that the generated test route may be relatively long, the vehicle cannot run through the whole test route at a time to complete the test, and the driver also needs to take a time to rest, after the test route is generated, according to the speed limit information on the test map and the length of the passing path of the test route, the test route is split into a plurality of test sub-routes with the test duration being less than the preset test duration, so as to obtain a test route set.
According to the embodiment, the test route is divided into the plurality of test sub-routes, so that the test safety of the subsequent semantic map can be ensured.
In a preferred embodiment, after the semantic map is loaded according to the test area to obtain the test map, before the pairing an entry navigation point of an intersection with an exit navigation point of an intersection reachable by the entry navigation point for each intersection on the test map one by one to generate a plurality of navigation point pairs for each intersection, the method further includes: and traversing each intersection in the semantic map, and collecting the intersections in the test area in an intersection set of the test map.
Illustratively, whether each intersection on the semantic map is located in the test area is judged according to the intersection label and the intersection coordinate on the semantic map, if yes, the intersection is considered as the intersection in the test area, and the intersection is collected in the intersection set of the test map.
Based on the same inventive concept as the third embodiment, a fourth embodiment of the present invention provides a semantic map-based test apparatus as shown in fig. 8, including: the test map obtaining module 41 is configured to load a semantic map according to the test area to obtain a test map; a navigation point pair generating module 42, configured to pair an entering navigation point of a road junction with an leaving navigation point of the road junction that can be reached by the entering navigation point one by one for each road junction on the test map, and generate a plurality of navigation point pairs of each road junction; a navigation point pair matching module 43, configured to traverse a plurality of navigation point pairs at each intersection, match each navigation point pair at the current intersection with each navigation point pair at the next intersection where the current intersection can reach, and obtain a plurality of first matching pairs; the directed graph construction module 44 is configured to use each navigation point pair of each intersection as a node, and add a connecting edge between two navigation point pairs in each first matching pair to construct a directed graph; a test route generation module 45, configured to connect all the connection edges according to the directed graph to connect all the nodes in series, so as to generate a test route; and an automatic driving test module 46, configured to send a test route to the vehicle, so that the vehicle performs an automatic driving test according to the test route, and corrects the test map according to the obtained test data.
In a preferred embodiment, the navigation point pair matching module 43 is further configured to match the navigation point pair of the current intersection with each navigation point pair of the target intersection that can be reached by the navigation point pair of the current intersection when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, so as to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain; the directed graph construction module 44 is configured to construct a directed graph by using each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, and adding a connecting edge between two navigation point pairs in each second matching pair.
In a preferred embodiment, for each intersection on the test map, the entering navigation points of the intersection and the leaving navigation points of the intersections that can be reached by the entering navigation points are paired one by one, and a plurality of navigation point pairs of each intersection are generated, specifically: for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached by the entering navigation point one by one to generate a plurality of initial navigation point pairs, and selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs.
In a preferred embodiment, the connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate the test route specifically includes: traversing a plurality of navigation point pairs of each intersection based on a directed graph, judging whether the navigation point pair of the current intersection does not reach the navigation point pair of another intersection after passing through the boundary of a test area, and if so, rejecting the navigation point pair of the current intersection to obtain a middle graph; traversing a plurality of navigation point pairs of each intersection based on the intermediate graph, matching each navigation point pair of the current intersection with each navigation point pair of another intersection reached by the current intersection to obtain a plurality of third matching pairs, and adding a connecting edge between two navigation point pairs in each third matching pair to generate a complete graph; and connecting all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
In a preferred embodiment, after said connecting all said connecting edges according to said directed graph to connect all said nodes in series to generate a test route, further comprising: according to the speed limit information of the test map and the length of the test route, the test route is divided into a plurality of test sub-routes with the test duration being smaller than the preset test duration, and a test route set is obtained.
In a preferred embodiment, after the semantic map is loaded according to the test area to obtain the test map, before the pairing an entry navigation point of an intersection with an exit navigation point of an intersection reachable by the entry navigation point for each intersection on the test map one by one to generate a plurality of navigation point pairs for each intersection, the method further includes: and traversing each intersection in the semantic map, and collecting the intersections in the test area in an intersection set of the test map.
In summary, the embodiment of the present invention has the following advantages:
the method comprises the steps of loading a semantic map according to a test area to obtain a test map, pairing an entering navigation point of an intersection with an leaving navigation point of a reachable intersection for each intersection on the test map one by one to generate a plurality of navigation point pairs of each intersection, traversing the plurality of navigation point pairs of each intersection, matching each navigation point pair of a current intersection with each navigation point pair of a next intersection reachable by the current intersection to obtain a plurality of first matching pairs, using each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair, constructing a directed graph, connecting all connecting edges according to the directed graph to connect all nodes in series to generate a test route, and realizing automatic generation of the test route. According to the embodiment of the invention, the marked semantic map is utilized to traverse each intersection in the test area on the semantic map, and the test route is automatically generated by covering the left-turn, right-turn, straight-going and turning-around directions of each intersection, so that the test route can be automatically generated by covering the intersections in the test area of the semantic map comprehensively, and the test efficiency of the semantic map is improved.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
It will be understood by those skilled in the art that all or part of the processes of the above embodiments may be implemented by hardware related to instructions of a computer program, and the computer program may be stored in a computer readable storage medium, and when executed, may include the processes of the above embodiments. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

Claims (10)

1. A test route generation method based on a semantic map is characterized by comprising the following steps:
loading a semantic map according to the test area to obtain a test map;
for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached one by one to generate a plurality of navigation point pairs of each intersection;
traversing a plurality of navigation point pairs of each intersection, and matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection to obtain a plurality of first matching pairs;
each navigation point pair of each intersection is used as a node, and a connecting edge is added between two navigation point pairs in each first matching pair to construct a directed graph;
and connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route.
2. The semantic map-based test route generation method of claim 1, further comprising:
when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, matching the navigation point pair of the current intersection with each navigation point pair of the target intersection which can reach the current intersection to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain;
and then each navigation point pair of each intersection is taken as a node, a connecting edge is added between two navigation point pairs in each first matching pair, and a connecting edge is added between two navigation point pairs in each second matching pair, so that a directed graph is constructed.
3. The semantic map-based test route generation method according to claim 1 or 2, wherein for each intersection on the test map, the entry navigation points of the intersection and the exit navigation points of the intersections that can be reached by the entry navigation points are paired one by one to generate a plurality of navigation point pairs of each intersection, specifically:
for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached by the entering navigation point one by one to generate a plurality of initial navigation point pairs, and selecting one initial navigation point pair from all the initial navigation point pairs on each edge of the intersection as a navigation point pair to obtain a plurality of navigation point pairs.
4. The semantic map-based test route generation method according to claim 1 or 2, wherein the test route is generated by connecting all the connection edges according to the directed graph to connect all the nodes in series, specifically:
traversing a plurality of navigation point pairs of each intersection based on a directed graph, judging whether the navigation point pair of the current intersection does not reach the navigation point pair of another intersection after passing through the boundary of a test area, and if so, rejecting the navigation point pair of the current intersection to obtain a middle graph;
traversing a plurality of navigation point pairs of each intersection based on the intermediate graph, matching each navigation point pair of the current intersection with each navigation point pair of another intersection reached by the current intersection to obtain a plurality of third matching pairs, and adding a connecting edge between two navigation point pairs in each third matching pair to generate a complete graph;
and connecting all the connecting edges according to the complete graph to connect all the nodes in series to generate a test route.
5. The semantic map-based test route generation method according to claim 1 or 2, wherein after the connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route, further comprising:
according to the speed limit information of the test map and the length of the test route, the test route is divided into a plurality of test sub-routes with the test duration being smaller than the preset test duration, and a test route set is obtained.
6. The semantic map-based test route generation method according to claim 1 or 2, wherein after the semantic map is loaded according to the test area to obtain the test map, before the step of pairing, for each intersection on the test map, an entry navigation point of the intersection with an exit navigation point of the intersection reachable by the entry navigation point, and generating a plurality of navigation point pairs for each intersection, the method further comprises:
and traversing each intersection in the semantic map, and collecting the intersections in the test area in an intersection set of the test map.
7. A semantic map-based test route generation device is characterized by comprising:
the test map acquisition module is used for loading the semantic map according to the test area to obtain a test map;
the navigation point pair generating module is used for pairing the entering navigation points of the intersections and the leaving navigation points of the intersections which can be reached one by one for each intersection on the test map to generate a plurality of navigation point pairs of each intersection;
the navigation point pair matching module is used for traversing a plurality of navigation point pairs of each intersection, matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection, and obtaining a plurality of first matching pairs;
the directed graph construction module is used for taking each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair and constructing a directed graph;
and the test route generation module is used for connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route.
8. A semantic map-based testing method is characterized by comprising the following steps:
loading a semantic map according to the test area to obtain a test map;
for each intersection on the test map, pairing an entering navigation point of the intersection with an exiting navigation point of the intersection which can be reached one by one to generate a plurality of navigation point pairs of each intersection;
traversing a plurality of navigation point pairs of each intersection, and matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection to obtain a plurality of first matching pairs;
each navigation point pair of each intersection is used as a node, and a connecting edge is added between two navigation point pairs in each first matching pair to construct a directed graph;
connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route;
and sending the test route to the vehicle, enabling the vehicle to carry out automatic driving test according to the test route, and correcting the test map according to the obtained test data.
9. The semantic map-based testing method of claim 8, further comprising:
when the navigation point pair of the current intersection reaches the navigation point pair of the next intersection through the boundary of the test area, matching the navigation point pair of the current intersection with each navigation point pair of the target intersection which can reach the current intersection to obtain a plurality of second matching pairs; the distance between the current intersection and the target intersection is smaller than the distance outside the preset domain;
and then each navigation point pair of each intersection is taken as a node, a connecting edge is added between two navigation point pairs in each first matching pair, and a connecting edge is added between two navigation point pairs in each second matching pair, so that a directed graph is constructed.
10. A semantic map based test device, comprising:
the test map acquisition module is used for loading the semantic map according to the test area to obtain a test map;
the navigation point pair generating module is used for pairing the entering navigation points of the intersections and the leaving navigation points of the intersections which can be reached one by one for each intersection on the test map to generate a plurality of navigation point pairs of each intersection;
the navigation point pair matching module is used for traversing a plurality of navigation point pairs of each intersection, matching each navigation point pair of the current intersection with each navigation point pair of the next intersection which can be reached by the current intersection, and obtaining a plurality of first matching pairs;
the directed graph construction module is used for taking each navigation point pair of each intersection as a node, adding a connecting edge between two navigation point pairs in each first matching pair and constructing a directed graph;
the test route generation module is used for connecting all the connecting edges according to the directed graph to connect all the nodes in series to generate a test route;
and the automatic driving test module is used for sending a test route to the vehicle, so that the vehicle carries out automatic driving test according to the test route and corrects the test map according to the obtained test data.
CN202111156033.1A 2021-09-29 2021-09-29 A test route generation method, test method and device based on semantic map Active CN114049410B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111156033.1A CN114049410B (en) 2021-09-29 2021-09-29 A test route generation method, test method and device based on semantic map

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111156033.1A CN114049410B (en) 2021-09-29 2021-09-29 A test route generation method, test method and device based on semantic map

Publications (2)

Publication Number Publication Date
CN114049410A true CN114049410A (en) 2022-02-15
CN114049410B CN114049410B (en) 2025-05-09

Family

ID=80204802

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111156033.1A Active CN114049410B (en) 2021-09-29 2021-09-29 A test route generation method, test method and device based on semantic map

Country Status (1)

Country Link
CN (1) CN114049410B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106403978A (en) * 2016-09-30 2017-02-15 北京百度网讯科技有限公司 Navigation route generating method and device
CN112985444A (en) * 2021-03-31 2021-06-18 上海商汤临港智能科技有限公司 Method and device for constructing navigation elements in map

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106403978A (en) * 2016-09-30 2017-02-15 北京百度网讯科技有限公司 Navigation route generating method and device
CN112985444A (en) * 2021-03-31 2021-06-18 上海商汤临港智能科技有限公司 Method and device for constructing navigation elements in map

Also Published As

Publication number Publication date
CN114049410B (en) 2025-05-09

Similar Documents

Publication Publication Date Title
US10614600B2 (en) Graph based topological map matching
CN111125293B (en) Automatic generation method and device of public transport network model and electronic equipment
CN111044058A (en) Route planning method, route planning device, computer device, and storage medium
CN105043403A (en) High precision map path planning system and method
CN101210825A (en) Map information generating systems
US20080120022A1 (en) Method and Device for Determining a Route with Points of Interest
CN110174110B (en) Map corresponding method and device, electronic equipment and computer readable medium
CN112818075B (en) Road network completion method and device, electronic equipment and readable storage medium
US8675924B2 (en) Road estimation device and method for estimating road
CN109282825B (en) Road marking method and device
US10408628B2 (en) Method and apparatus for comparing two maps with landmarks deposited therein
CN112418193B (en) Lane line identification method and system
CN110232470B (en) Method and device for determining vehicle driving path
CN111985366A (en) Road center line and pile number identification method and device
CN113448973A (en) Map data updating method, server, vehicle machine and storage medium
CN114880530A (en) Public transport route recommendation method and system based on historical driving track
CN114049410A (en) Semantic map-based test route generation method, test method and test device
US20230028461A1 (en) Identification of connection patterns on the basis of trajectory data
CN115683139B (en) A vehicle-mounted map path planning method, system, electronic device and storage medium
CN118189998A (en) Automatic driving high-precision fusion positioning test method and system
CN109270566A (en) Air navigation aid, navigation effect test method, device, equipment and medium
CN116383321A (en) Decision environment construction method, device, vehicle and storage medium
CN116295487A (en) Navigation method, navigation device, server and storage medium of POI
CN117664157A (en) Determination method, device, equipment, medium and vehicle of high-precision navigation path
TW201231927A (en) Graph based topological map matching

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant