CN109871016B - Automatic driving reference line generation method and device, vehicle and server - Google Patents
Automatic driving reference line generation method and device, vehicle and server Download PDFInfo
- Publication number
- CN109871016B CN109871016B CN201910127261.2A CN201910127261A CN109871016B CN 109871016 B CN109871016 B CN 109871016B CN 201910127261 A CN201910127261 A CN 201910127261A CN 109871016 B CN109871016 B CN 109871016B
- Authority
- CN
- China
- Prior art keywords
- lane
- driving reference
- lanes
- reference line
- precision map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a driving reference line generation method, a driving reference line generation device, a vehicle and a server, wherein the method comprises the following steps: generating a smooth track curve for each lane in at least one lane based on the acquired repeated to-be-processed track data segments of each lane in at least one lane; mapping the smooth track curve of each lane in the at least one lane to a high-precision map to obtain driving reference lines of at least part of lanes in the high-precision map; and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of the lanes in the high-precision map. The problem of driving reference line smoothness is not enough and not conform to user's driving habit in the unmanned vehicle is solved.
Description
Technical Field
The invention relates to the technical field of unmanned control, in particular to a driving reference line generation method and device, a vehicle and a server.
Background
The automatic driving reference line is the basis for completing the trajectory planning of the unmanned vehicle, and the trajectory planning can generate a planning trajectory with excellent comprehensive performance based on the high-quality driving reference line. At present, the smoothness of a driving reference line for unmanned driving is insufficient, and the driving reference line is difficult to ensure continuous smoothness and conforms to the driving habit of human beings, so that the quality of a trajectory planning result is influenced, and the driving feeling of an unmanned vehicle is further influenced.
Disclosure of Invention
The embodiment of the invention provides a driving reference line generation method and device, a vehicle and a server, and aims to solve the problems that in the prior art, the driving reference line is insufficient in smoothness, continuous and smooth, and the driving reference line is difficult to ensure and conforms to the driving habits of human beings.
In a first aspect, an embodiment of the present invention provides a driving reference line generation method, including:
generating a smooth track curve for each lane in at least one lane based on the acquired repeated to-be-processed track data segments of each lane in at least one lane;
mapping the smooth track curve of each lane in the at least one lane to a high-precision map to obtain driving reference lines of at least part of lanes in the high-precision map;
and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of lanes in the high-precision map.
In one embodiment, the method further comprises:
collecting at least one piece of trajectory data of at least one vehicle; the track data comprises at least one position and a time value of each position;
acquiring N track data sections covering the same lane in the at least one track data; n is an integer greater than or equal to 1;
and when N exceeds a preset threshold value, taking the N track data sections of the same lane as repeated track data sections to be processed.
In one embodiment, the mapping the smooth trajectory curve of each of the at least one lane to the high-precision map to obtain the driving reference line of at least part of the lanes in the high-precision map includes:
mapping the smooth track curve of each lane in the at least one lane to at least part of corresponding lanes in a high-precision map;
and deleting the part, which is positioned outside the road range, in the smooth track curve to obtain the driving reference line of at least part of lanes in the high-precision map.
In one embodiment, the method further comprises:
and splicing the driving reference lines by adopting a polynomial curve fitting algorithm aiming at the bifurcate and convergent positions of the lanes in the driving reference lines of at least part of lanes in the high-precision map.
In one embodiment, the method further comprises:
aiming at least one driverless reference line lane in the high-precision map, taking the central line of the driverless reference line lane as a driving reference line to be replaced;
and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference line to be replaced of the lane without the driving reference line and the driving reference lines of at least part of lanes in the high-precision map.
In a second aspect, an embodiment of the present invention provides a driving reference line generating apparatus, where the apparatus includes:
the track processing unit is used for generating a smooth track curve aiming at each lane in at least one lane based on the acquired repeated to-be-processed track data segment of each lane in at least one lane;
the mapping unit is used for mapping the smooth track curve of each lane in the at least one lane to the high-precision map to obtain driving reference lines of at least part of lanes in the high-precision map;
and the map processing unit is used for generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of lanes in the high-precision map.
In one embodiment, the trajectory processing unit is configured to acquire at least one trajectory data of at least one vehicle; wherein, the track data comprises at least one position and a time value at each position; acquiring N track data sections covering the same lane in the at least one piece of track data; when N exceeds a preset threshold value, taking the N track data sections of the same lane as repeated track data sections to be processed; n is an integer of 1 or more.
In one embodiment, the mapping unit is configured to map the smooth trajectory curve of each of the at least one lane to a corresponding at least partial lane in a high-precision map; and deleting the part, which is positioned outside the road range, in the smooth track curve to obtain the driving reference line of at least part of lanes in the high-precision map.
In one embodiment, the map processing unit is configured to, in a driving reference line of at least a part of lanes in the high-precision map, adopt a polynomial curve fitting algorithm to splice the driving reference line with respect to a position where lanes in the driving reference line diverge and converge.
In one embodiment, the map processing unit is configured to, for at least one driverless lane in the high-precision map, take a center line of the at least one driverless lane as a driving reference line to be replaced; and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference line to be replaced of the lane without the driving reference line and the driving reference lines of at least part of lanes in the high-precision map.
In a third aspect, an embodiment of the present invention provides a vehicle, where functions of the vehicle may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.
In one possible design, the vehicle has a structure including a first processor and a first memory, the first memory is used for storing a program for supporting the device to execute the driving control method, and the first processor is configured to execute the program stored in the memory. The apparatus may also include a first communication interface for communicating with other devices or a communication network.
In a fourth aspect, an embodiment of the present invention provides a server, where functions of the server may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.
In one possible design, the server includes a second processor and a second memory, the second memory is used for storing a program for supporting the device to execute the driving control method, and the second processor is configured to execute the program stored in the memory. The apparatus may also include a second communication interface for communicating with other devices or a communication network.
In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the method described in any of the above embodiments.
One of the above technical solutions has the following advantages or beneficial effects: and after a smooth track curve is obtained through processing based on the to-be-processed track data segment capable of covering each lane in at least one lane, the smooth track curve is mapped to the high-precision map to obtain driving reference lines of partial lanes, and then the driving reference lines of all the lanes in the high-precision map are generated based on the driving reference lines of the partial lanes. Because the to-be-processed track data segments covering the lanes are acquired in advance, the reasonability of the reference lines can be ensured when the driving reference lines in the high-precision map are generated by mapping, and the driving reference lines are ensured to express the driving habits of human beings.
The foregoing summary is provided for the purpose of description only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will be readily apparent by reference to the drawings and following detailed description.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.
Fig. 1-1 shows a first flowchart of a driving reference line generation method according to an embodiment of the present invention.
Fig. 1-2 show a second flowchart of a driving reference line generation method according to an embodiment of the invention.
Fig. 1 to 3 show a flowchart three of a driving reference line generation method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram illustrating a high-precision map and a general electronic navigation map according to an embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating a scene of deleting an unnecessary part according to an embodiment of the present invention.
Fig. 4 shows a schematic diagram of a splicing scenario according to an embodiment of the present invention.
Fig. 5 shows a schematic view of a driving reference line processing scenario according to an embodiment of the invention.
Fig. 6 is a schematic diagram illustrating a structural configuration of a driving reference line generating device according to an embodiment of the present invention.
Fig. 7 shows a vehicle structural block diagram according to an embodiment of the invention.
Fig. 8 shows a block diagram of a server structure according to an embodiment of the present invention.
Detailed Description
In the following, only certain exemplary embodiments are briefly described. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.
The embodiment of the invention provides a driving control method, which comprises the steps of generating a smooth track curve corresponding to each lane according to a repeated track data section to be processed of each lane in a plurality of existing lanes; and mapping the smooth track curve to a high-precision map to obtain driving reference lines of at least part of lanes in the high-precision map, and finally obtaining the driving reference lines capable of covering all lanes of the high-precision map.
In one embodiment, as shown in fig. 1-1, there is provided a driving reference line generating method, the method including:
step 101: generating a smooth track curve for each lane in at least one lane based on the acquired repeated to-be-processed track data segment of each lane in at least one lane;
step 102: mapping the smooth track curve of each lane in the at least one lane to a high-precision map to obtain driving reference lines of at least part of lanes in the high-precision map;
step 103: and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of lanes in the high-precision map.
First, for the foregoing step 101, before execution, at least one piece of trajectory data needs to be obtained, which may specifically be:
collecting at least one piece of trajectory data of at least one vehicle; the track data comprises at least one position and a time value of each position;
acquiring repeated N track data sections covering the same lane in the at least one track data; n is an integer greater than or equal to 1;
and when N exceeds a preset threshold value, taking the N track data sections of the same lane as repeated track data sections to be processed.
Specifically, at least one piece of track data of at least one vehicle is collected, wherein the track data can comprise at least one position and a time value of each position; in addition, the track data may also include current status information.
The position can be coordinates based on a world coordinate system, and the acquisition mode can be that the position is acquired by a GPS unit in each vehicle; the acquisition interval may be set according to actual conditions, for example, may be once every 1s, or may be once every 0.5s, and may be larger or smaller, which is only by no means exhaustive in this embodiment. The status information may include the speed and/or acceleration of the vehicle at the corresponding time. For example, the trajectory data may be at least one (x, y, t), (x, y) representing geographical location information, and t being a time value when the trajectory data is acquired; alternatively, the trajectory data may be at least one (x, y, t, a), that is, in addition to the above information, the acceleration value at that time may be included, and the acceleration may be positive or negative.
The obtaining of the repeated N track data segments covering the same lane in the at least one track data may be performed by comparing according to (x, y), that is, position information, in the at least one track data, and selecting to obtain the N track data segments passing through the same lane; for example, there are 4 pieces of trajectory data, where there are 3 pieces of trajectory data for a certain lane, and there is one piece of trajectory data for the remaining lanes, respectively, and then three pieces of trajectory data for the same lane are valid trajectory data.
In addition, the preset threshold may be set according to actual situations, for example, may be 10, and certainly may also be 3, or may also be 50, and this embodiment is not exhaustive. That is, when there are 3 pieces of trajectory data passing through the same lane, a plurality of trajectory data segments overlapping the lane and repeated 3 times or more are selected as the repeated trajectory data segments to be processed.
It should be noted that, in the present embodiment, a plurality of trajectory data of a plurality of actual lanes driven by human beings are selected, and then trajectory data segments corresponding to some lanes with a large number of repetitions, that is, a large number of walks, are selected as trajectory data segments to be processed used in the present embodiment. The scene aimed at can include various types of scene intersections, turns, bifurcations, tracks in a common straight lane, and the like. The repeated track can be a track data segment with more repeated times; since only one opening on a map cannot reflect the actual situation, a certain road is passed many times and is considered to be effective.
In the step 101, a smooth trajectory curve for each lane of the at least one lane is generated, and the smooth trajectory curve reflecting the driving habits of human beings is generated by processing the trajectory data segment to be processed, using at least one sampling point of the trajectory data segment to be processed by manual driving as an input, and fitting by using a piecewise two-dimensional gaussian distribution.
The at least one sampling point may be at least one sampling point acquired when the trajectory data is acquired, and may also be at least one sampling point selected based on a preset interval, for example, 10 acquisition points exist in a trajectory data segment to be processed of a certain lane originally, when the piecewise two-dimensional gaussian distribution fitting is performed, 5 acquisition points may be selected from the acquired points as input, and finally, a corresponding smooth trajectory curve is generated through the piecewise two-dimensional gaussian distribution fitting algorithm.
In the aforementioned step 102, the mapping the smooth trajectory curve of each lane of the at least one lane to the high-precision map to obtain the driving reference line of at least part of the lanes in the high-precision map includes:
mapping the smooth track curve of each lane in the at least one lane to at least part of corresponding lanes in a high-precision map; and deleting the part outside the road range in the smooth track curve to obtain the driving reference line of at least part of lanes in the high-precision map.
In other words, in combination with the high-precision map, all the curves generated by fitting are mapped to corresponding lanes, and redundant parts outside the road range are deleted to obtain a plurality of driving reference lines. It is understood that after the curve is mapped onto the lane, there may be a portion of the curve that falls outside the road range where the lane is located; further, at least one parallel lane may exist in a road segment, for example, 4 parallel lanes may exist in a road segment, and this step may delete the redundant portion falling outside the range of the road.
In the high-precision map, smooth track curves for a plurality of lanes are mapped, wherein the mapping mode can be based on positions, for example, a plurality of elements existing in the high-precision map are also arranged by positions, and are mapped into the high-precision map according to the position relation of the smooth track curves.
From the perspective of a user, the main differences between a high-precision map and a traditional electronic map are as follows: the user of the high-precision map is an automatic driving system, and the user of the traditional electronic map is a human driver.
Referring to fig. 2, a conventional general navigation electronic map (left side in the figure) may depict roads, and some roads may be distinguished from lanes, while a high-precision map (right side in the figure) may not only depict roads, but also precisely depict how many lanes are on a road, and may actually reflect the actual patterns of lanes.
The traditional electronic map cannot completely show the details of the lane shape, and the high-precision map can show the details of the lane shape in detail and accurately in order to enable an automatic driving system to better identify the traffic condition, so that a driving scheme is made in advance, and the places are widened and narrowed and completely consistent with a real lane.
As shown in fig. 2, the high-precision map includes a plurality of lanes, for example, lanes (Lane) 1-10. At least one Lane may form a road, for example, Lane (Lane)1, Lane (Lane) 2, Lane (Lane) 3 may form a road, Lane (Lane)4, Lane (Lane) 5, Lane (Lane) 6, Lane (Lane) 7 may form another road, and other forming manners are similar and will not be described again. It should be understood that fig. 2 is only an example, and there may be more expression elements in an actual high-precision map, such as a road shoulder, a traffic light, and so on, which are not exhaustive in this embodiment.
The foregoing deletion of the portion of the smooth trajectory curve that is outside the road range can be seen from fig. 3, and it is assumed that there is a smooth trajectory curve 1 currently in the lane, but there is a portion of the curve that is outside the road coverage, as shown by the dotted line portion in the figure, and then it is deleted as an extra portion, and then the remaining portion is retained as the driving reference line for the lane.
Therefore, by adopting the scheme, the smooth track curve can be obtained by processing based on the to-be-processed track data segment capable of covering each lane in at least one lane, the smooth track curve is mapped to the high-precision map to obtain the driving reference lines of partial lanes, and the driving reference lines of all the lanes in the high-precision map are generated based on the driving reference lines of the partial lanes. Because the to-be-processed track data segments covering a plurality of lanes are acquired in advance, when the driving reference line in the high-precision map is generated through mapping, the reasonability of the reference line can be ensured, and the driving reference line expresses the driving habits of human beings, such as smoother completion of doubling, completion of turn in an intersection with a turn radius closer to human driving and the like.
In an embodiment, mapping the smooth driving curve to the high-precision map and the previous processing are the same as those described in steps 101 to 102 of the previous embodiment, and thus are not described again.
In this embodiment, a detailed description is given for the step 103, which is to generate a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of the lanes in the high-precision map.
The method comprises the steps of splicing at least partial driving reference lines of lanes, and generating complete driving reference lines for all lanes of the whole high-precision map based on the spliced driving reference lines. Specifically, referring to fig. 1-2, on the basis of steps 101-102 in fig. 1, step 103 may be divided into the following steps, which specifically include:
step 1031: splicing driving reference lines by adopting a polynomial curve fitting algorithm aiming at the positions of lane bifurcation and convergence in the driving reference lines in at least part of lanes in the high-precision map;
step 1032: and generating a complete driving reference line covering all lanes in the high-precision map based on the spliced driving reference line.
Further, finding a branched and converged place on a high-precision map; for the branched lanes, different situations may occur, for example, a left branch is collected at one time, and a right branch is taken along a route collected at another time; the middle joint parts need to be jointed; that is, a single road may have multiple walks, and different routes may be collected for the first and second passes. The paths acquired in different times have common parts and different parts, and the common parts are spliced together by utilizing a polynomial curve fitting algorithm.
For example, referring to fig. 4, it is assumed that two driving reference lines a and b are provided for a lane, respectively, where a part of the driving reference line a goes through the left lane and a part of the driving reference line b goes through the right lane, the two driving reference lines are branched, and the two driving reference lines have a common part; in addition, a driving reference line c exists, and the driving reference line c is located after the bifurcation, so that the common part of the driving reference lines a and b and the driving reference line c can be spliced, wherein the spliced part is shown by a dotted line in the figure, and finally the spliced driving reference line is obtained. The whole high-precision map can be processed based on the processing mode.
In addition, based on the foregoing solution, there may be a part of lanes where no driving reference line is obtained, and the processing of this part may be as shown in fig. 1 to 3, which specifically includes:
step 1033: aiming at least one driverless reference line lane in the high-precision map, taking the central line of the driverless reference line lane as a driving reference line to be replaced;
step 1034: and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference line to be replaced of the lane without the driving reference line and the driving reference lines of at least part of lanes in the high-precision map.
That is, in the present embodiment, the driving reference line may be incrementally generated, and the center line of the lane with the high-precision map may be replaced in the non-acquisition area. For example, referring to fig. 5, a road 1-5 is taken as an example to illustrate, where there are driving reference lines of partial lanes in the roads 1 and 2, but the remaining roads 3, 4, and 5 do not have driving reference lines, and a center line of at least one lane in the roads 3, 4, and 5 may be used as its driving reference line, which is indicated by a solid line with an arrow in the figure, and then the driving reference lines are spliced with the driving reference lines of the roads 1 and 2 to obtain a complete driving reference line.
It should be further noted that the finally obtained complete driving reference line is at lane level, that is, all lanes in the high-precision map have corresponding driving reference lines.
Further, if repeated driving track data are collected again for the lane in which the reference route is not collected originally, namely the lane in which the driving reference line is to be replaced, the original manually marked data of the lane can be replaced after collection. That is, if no human route is collected, it may be manually annotated data as a reference line, and if human route is collected, human route is adopted.
It should be understood that the processing manner for the driverless lane may be performed on the basis of step 1031 shown in fig. 1-2, that is, after the splicing of the driving reference lines is completed, as a specific implementation manner of step 1032, the extension of a part of the driverless lane is performed on the basis of the spliced driving reference lines to obtain complete driving reference lines, that is, the specific processing flow is the foregoing step 101-step 102-step 1031-step 1033-step 1034, and is not described again here;
or, the processing may also be performed after step 102 in fig. 1-1, that is, after the driving reference line of at least a part of the lane in step 102 is generated, step 103 is started to be performed, and the processing of step 103 is to use the center line of the lane without the driving reference line as the driving reference line of the lane, and the processing flow is step 101-step 102-step 1033-step 1034, which is not described again here.
The method can be executed in a processor of the vehicle, and can also be processed at the server side; wherein the server may be a server side of the high-precision map.
When the steps of the method are executed on the server side, the processing of collecting at least one piece of track data of at least one vehicle is realized, that is, the at least one vehicle is used for collecting, and the collected at least one piece of track data is sent to the server side; then, the server executes the aforementioned steps 101-102-1031-1033-1034, or the server executes the aforementioned steps 101-102-1033-1034.
Further, after the foregoing method steps are executed on the server side and a complete driving reference line is generated, the server may further: a complete driving reference line covering all lanes within the high-precision map is sent to at least one vehicle. That is, a high-precision map with a complete driving reference line can be finally placed in the unmanned vehicle, so that the vehicle can accurately control the vehicle to automatically run on a specific lane in the road.
Therefore, by adopting the scheme, the smooth track curve can be obtained by processing based on the N track data sections to be processed, which can cover each lane in at least one lane, and then the smooth track curve is mapped to the high-precision map to obtain the driving reference lines of partial lanes, and then the driving reference lines of all the lanes in the high-precision map are generated based on the driving reference lines of the partial lanes. Because the to-be-processed track data segments covering the lanes are acquired in advance, when the driving reference lines in the high-precision map are generated by mapping, the reasonability of the reference lines can be ensured, and the driving reference lines are ensured to express the driving habits of human beings, such as smoother completion of merging, completion of turn in an intersection with a turning radius closer to human driving, and the like.
It should also be noted that, because the driving reference line at the lane level can be obtained by adopting the above scheme, the driving reference line provided by the scheme provided by the embodiment is more accurate compared with at least a common navigation map.
In one embodiment, FIG. 6 illustrates a driving control device, the device comprising:
the track processing unit 61 is configured to generate a smooth track curve for each lane of the at least one lane based on the acquired repeated to-be-processed track data segment of each lane of the at least one lane;
the mapping unit 62 is configured to map the smooth trajectory curve of each lane in the at least one lane to a high-precision map, so as to obtain driving reference lines of at least part of lanes in the high-precision map;
and the map processing unit 63 is used for generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of lanes in the high-precision map.
The present embodiment is applied to a vehicle capable of automatic driving.
The track processing unit is used for acquiring at least one piece of track data of at least one vehicle; the track data comprises at least one position and a time value of each position; acquiring N track data sections covering the same lane in the at least one piece of track data; and when N exceeds a preset threshold value, taking the N track data sections of the same lane as repeated track data sections to be processed.
The mapping unit is used for mapping the smooth track curve of each lane in the at least one lane to at least part of corresponding lanes in the high-precision map; and deleting the part, which is positioned outside the at least partial lane range, in the smooth track curve to obtain the driving reference line of at least partial lanes in the high-precision map.
And the map processing unit is used for splicing the driving reference lines by adopting a polynomial curve fitting algorithm in the driving reference lines of at least part of lanes in the high-precision map according to the lane branching and merging positions in the driving reference lines.
The map processing unit is used for regarding at least one driverless reference line lane in the high-precision map, and taking the central line of the driverless reference line lane as a driving reference line to be replaced; and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference line to be replaced of the lane without the driving reference line and the driving reference lines of at least part of lanes in the high-precision map.
The functions of each module in the device according to the embodiment of the present invention may specifically refer to the corresponding descriptions in the above method, and are not described herein again.
The units may be in a vehicle or a server.
When the server is arranged, the communication unit can be further included; the communication unit is used for acquiring at least one piece of acquired track data.
Further, the communication unit may be further configured to send a complete driving reference line covering all lanes within the high-precision map to the at least one vehicle. That is, a high-precision map with a complete driving reference line can be finally placed in the unmanned vehicle, so that the vehicle can accurately control the vehicle to automatically run on a specific lane in the road.
Therefore, by adopting the scheme, the smooth track curve can be obtained by processing based on the to-be-processed track data segment capable of covering each lane in at least one lane, the smooth track curve is mapped to the high-precision map to obtain the driving reference lines of partial lanes, and the driving reference lines of all the lanes in the high-precision map are generated based on the driving reference lines of the partial lanes. Because the to-be-processed track data segments covering a plurality of lanes are acquired in advance, when the driving reference line in the high-precision map is generated through mapping, the reasonability of the reference line can be ensured, and the driving reference line expresses the driving habits of human beings, such as smoother completion of doubling, completion of turn in an intersection with a turn radius closer to human driving and the like.
Fig. 7 shows a block diagram of a vehicle according to an embodiment of the invention. As shown in fig. 7, the vehicle includes: a first memory 710 and a first processor 720, the first memory 710 having stored therein computer programs executable on the first processor 720. The first processor 720, when executing the computer program, implements the driving control method in the above-described embodiment. The number of the first memory 710 and the first processor 720 may be one or more.
The vehicle further includes:
the first communication interface 730 is used for communicating with an external device to perform data interactive transmission.
The first memory 710 may comprise high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.
If the first memory 710, the first processor 720 and the first communication interface 730 are implemented independently, the first memory 710, the first processor 720 and the first communication interface 730 can be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.
Optionally, in a specific implementation, if the first memory 710, the first processor 720 and the first communication interface 730 are integrated on a chip, the first memory 710, the first processor 720 and the first communication interface 730 may complete mutual communication through an internal interface.
Fig. 8 shows a block diagram of a server according to an embodiment of the present invention. As shown in fig. 8, the server includes: a second memory 810 and a second processor 820, the second memory 810 having stored therein computer programs operable on the second processor 820. The second processor 820 implements the driving control method in the above-described embodiment when executing the computer program. The number of the second memory 810 and the second processor 820 may be one or more.
The vehicle, or the server, further includes:
and a second communication interface 830, configured to communicate with an external device, and perform data interactive transmission.
The secondary storage 810 may comprise high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.
If the second memory 810, the second processor 820 and the second communication interface 830 are implemented independently, the second memory 810, the second processor 820 and the second communication interface 830 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 8, but that does not indicate only one bus or one type of bus.
Optionally, in a specific implementation, if the second memory 810, the second processor 820 and the second communication interface 830 are integrated on one chip, the second memory 810, the second processor 820 and the second communication interface 830 may complete mutual communication through an internal interface.
Embodiments of the present invention provide a computer-readable storage medium, which stores a computer program, and when the program is executed by a processor, the computer program implements the method described in any of the above embodiments.
In the description of the specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following technologies, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
While the invention has been described with reference to specific embodiments, 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. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A driving reference line generation method, characterized by comprising:
generating a smooth track curve for each lane in at least one lane based on the acquired repeated to-be-processed track data segments of each lane in at least one lane; the track data section to be processed is selected from a plurality of track data of a plurality of human driving actual lanes;
mapping the smooth track curve of each lane in the at least one lane to a high-precision map to obtain driving reference lines of at least part of lanes in the high-precision map;
generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of the lanes in the high-precision map;
the generating of the complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of lanes in the high-precision map comprises the following steps:
regarding at least one driverless reference line lane in the high-precision map, taking the central line of the driverless reference line lane as a driving reference line to be replaced;
and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference line to be replaced of the lane without the driving reference line and the driving reference lines of at least part of lanes in the high-precision map.
2. The method of claim 1, further comprising:
collecting at least one piece of trajectory data of at least one vehicle; wherein, the track data comprises at least one position and a time value at each position;
acquiring N track data sections covering the same lane in the at least one track data; n is an integer greater than or equal to 1;
and when N exceeds a preset threshold value, taking the N track data sections of the same lane as repeated track data sections to be processed.
3. The method of claim 1, wherein the mapping the smooth trajectory curve of each of the at least one lane to a high-precision map to obtain a driving reference line of at least a portion of the lanes in the high-precision map comprises:
mapping the smooth track curve of each lane of the at least one lane to at least part of the corresponding lane in the high-precision map;
and deleting the part, which is positioned outside the road range, in the smooth track curve to obtain the driving reference line of at least part of lanes in the high-precision map.
4. The method of claim 1, further comprising:
and splicing the driving reference lines by adopting a polynomial curve fitting algorithm aiming at the positions of lane bifurcation and convergence in the driving reference lines of at least part of lanes in the high-precision map.
5. A driving reference line generation apparatus, characterized in that the apparatus comprises:
the track processing unit is used for generating a smooth track curve aiming at each lane in at least one lane based on the acquired repeated to-be-processed track data segment of each lane in at least one lane; the track data section to be processed is selected from a plurality of track data of a plurality of human driving actual lanes;
the mapping unit is used for mapping the smooth track curve of each lane in the at least one lane to a high-precision map to obtain driving reference lines of at least part of lanes in the high-precision map;
the map processing unit is used for generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference lines of at least part of lanes in the high-precision map;
wherein the map processing unit is specifically configured to:
aiming at least one driverless reference line lane in the high-precision map, taking the central line of the driverless reference line lane as a driving reference line to be replaced;
and generating a complete driving reference line covering all lanes in the high-precision map based on the driving reference line to be replaced of the lane without the driving reference line and the driving reference lines of at least part of lanes in the high-precision map.
6. The apparatus of claim 5, wherein the trajectory processing unit is configured to collect at least one trajectory data of at least one vehicle; wherein, the track data comprises at least one position and a time value at each position; acquiring N track data sections covering the same lane in the at least one piece of track data; when N exceeds a preset threshold value, taking the N track data sections of the same lane as repeated track data sections to be processed; n is an integer of 1 or more.
7. The apparatus of claim 5, wherein the mapping unit is configured to map the smooth trajectory curve of each of the at least one lane to a corresponding at least partial lane in a high-precision map; and deleting the part, which is positioned outside the at least partial lane range, in the smooth track curve to obtain the driving reference line of at least partial lanes in the high-precision map.
8. The device according to claim 5, wherein the map processing unit is further configured to, in the driving reference line of at least a part of lanes in the high-precision map, adopt a polynomial curve fitting algorithm to splice the driving reference lines for positions where lanes in the driving reference line diverge and converge.
9. A vehicle, characterized by comprising:
one or more first processors;
a first storage device for storing one or more programs;
the one or more programs, when executed by the one or more first processors, cause the one or more first processors to implement the method of any of claims 1-4.
10. A server, comprising:
one or more second processors;
a second storage device for storing one or more programs;
the one or more programs, when executed by the one or more second processors, cause the one or more second processors to implement the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910127261.2A CN109871016B (en) | 2019-02-20 | 2019-02-20 | Automatic driving reference line generation method and device, vehicle and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910127261.2A CN109871016B (en) | 2019-02-20 | 2019-02-20 | Automatic driving reference line generation method and device, vehicle and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109871016A CN109871016A (en) | 2019-06-11 |
| CN109871016B true CN109871016B (en) | 2022-07-22 |
Family
ID=66918953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910127261.2A Active CN109871016B (en) | 2019-02-20 | 2019-02-20 | Automatic driving reference line generation method and device, vehicle and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109871016B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288675B (en) * | 2019-06-30 | 2022-05-13 | 武汉中海庭数据技术有限公司 | Lane reference line construction method and device and storage medium |
| CN110377041B (en) * | 2019-08-08 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Reference line generation method and device, terminal equipment and storage medium |
| CN110634291B (en) * | 2019-09-17 | 2020-12-29 | 武汉中海庭数据技术有限公司 | High-precision map topology automatic construction method and system based on crowdsourcing data |
| CN111177927A (en) * | 2019-12-31 | 2020-05-19 | 武汉中海庭数据技术有限公司 | Vehicle reference driving line construction method, electronic device and storage medium |
| CN116698059B (en) * | 2023-07-27 | 2023-11-28 | 宁波路特斯机器人有限公司 | Processing method, storage medium and equipment for high-precision map reference line |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010237158A (en) * | 2009-03-31 | 2010-10-21 | Xanavi Informatics Corp | Method, system for navigating car, center device and car navigation device |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101526816B1 (en) * | 2014-09-12 | 2015-06-05 | 현대자동차주식회사 | System for estimating a lane and method thereof |
| KR102113816B1 (en) * | 2016-01-05 | 2020-06-03 | 한국전자통신연구원 | System for autonomous driving service of vehicle, cloud server thereof and method thereof |
| CN105513405B (en) * | 2016-01-12 | 2018-01-09 | 北京中交兴路车联网科技有限公司 | A kind of track of vehicle analysis method and device |
| US10444763B2 (en) * | 2016-03-21 | 2019-10-15 | Ford Global Technologies, Llc | Systems, methods, and devices for fusion of predicted path attributes and drive history |
| CN106525033A (en) * | 2016-09-22 | 2017-03-22 | 深圳市元征科技股份有限公司 | Running track determination method and device thereof |
| US10579062B2 (en) * | 2017-05-31 | 2020-03-03 | Baidu Usa Llc | Scalable smooth reference path generator for autonomous driving vehicles |
| CN107462243B (en) * | 2017-08-04 | 2019-09-20 | 浙江大学 | A kind of cloud control automatic Pilot task creating method based on high-precision map |
| WO2019104581A1 (en) * | 2017-11-30 | 2019-06-06 | 深圳市大疆创新科技有限公司 | Track generating method and apparatus, and unmanned ground vehicle |
| CN108519094B (en) * | 2018-02-11 | 2022-03-25 | 华为技术有限公司 | Local path planning method and cloud processing terminal |
| CN109059944B (en) * | 2018-06-06 | 2021-08-06 | 上海国际汽车城（集团）有限公司 | Motion planning method based on driving habit learning |
-
2019
- 2019-02-20 CN CN201910127261.2A patent/CN109871016B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010237158A (en) * | 2009-03-31 | 2010-10-21 | Xanavi Informatics Corp | Method, system for navigating car, center device and car navigation device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109871016A (en) | 2019-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871016B (en) | Automatic driving reference line generation method and device, vehicle and server | |
| CN109813328B (en) | Driving path planning method and device and vehicle | |
| CN109712421B (en) | Method, apparatus and storage medium for speed planning of autonomous vehicles | |
| CN108151751B (en) | Path planning method and device based on combination of high-precision map and traditional map | |
| CN109612496B (en) | Path planning method and device and vehicle | |
| KR102324771B1 (en) | Method, device, and terminal apparatus for invoking automatic driving reference line | |
| EP2491345A1 (en) | Incremental map generation, refinement and extension with gps traces | |
| CN108801289B (en) | Induced arrow planning method and device, navigation system and storage medium | |
| WO2020125686A1 (en) | Method for generating real-time relative map, intelligent driving device and computer storage medium | |
| CN112747755B (en) | Method and device for determining road route, readable storage medium and map updating system | |
| JP5656067B2 (en) | Road node position management system, road node position management method, and road node position management program | |
| CN113494917A (en) | Map construction method and system, method for making navigation strategy and storage medium | |
| JP7121454B2 (en) | Obstacle position simulation method, device and terminal based on statistics | |
| CN107990905B (en) | Method and device for determining U-turn intersection | |
| CN110120081A (en) | A kind of method, apparatus and storage equipment of generation electronic map traffic lane line | |
| CN111199083B (en) | Method and device for reproducing accident data of unmanned vehicle | |
| CN117146844A (en) | Method, device, equipment and medium for smoothing and optimizing reference line in path planning | |
| CN111123731B (en) | Method, device, storage medium and terminal equipment for simulating automatic driving vehicle | |
| CN116700235A (en) | Dynamic full-coverage path planning method and device, cleaning equipment and storage medium | |
| CN116383321A (en) | Decision environment construction method, device, vehicle and storage medium | |
| JP5194828B2 (en) | Road network matching program, method and system | |
| CN116045999A (en) | Heterogeneous data matching method and device, vehicle and storage medium | |
| CN111143485A (en) | Track coincident section fusion method, device, system and storage medium | |
| CN116148890A (en) | High-precision map lane planning method, system, electronic equipment and storage medium | |
| CN115435800A (en) | Path planning method, device, equipment and medium based on high-precision map |
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 |