CN114610044B - Mobile reference line obstacle avoidance method and system based on Lanelet frame - Google Patents
Mobile reference line obstacle avoidance method and system based on Lanelet frame Download PDFInfo
- Publication number
- CN114610044B CN114610044B CN202210386410.9A CN202210386410A CN114610044B CN 114610044 B CN114610044 B CN 114610044B CN 202210386410 A CN202210386410 A CN 202210386410A CN 114610044 B CN114610044 B CN 114610044B
- Authority
- CN
- China
- Prior art keywords
- reference line
- obstacle
- vehicle
- track
- distance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005070 sampling Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000013519 translation Methods 0.000 claims description 6
- 238000000790 scattering method Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a moving reference line obstacle avoidance method and system based on a Lanelet frame, and relates to the technical field of vehicle track planning. The method comprises the steps of: s1, generating a high-precision map based on a Lanelet frame, and taking a road center line as a default reference line; s2, obtaining obstacle coordinates; s3, calculating the moving direction and distance of the reference line according to the coordinates of the obstacle; s4, moving the reference line according to the moving direction and distance to obtain a new reference line, and setting a vehicle to track the new reference line to generate a local track so as to bypass the obstacle; s5, after the vehicle bypasses the obstacle, the reference line is restored to a default reference line. When the vehicle senses the obstacle, the reference line is moved according to the coordinates of the obstacle, the vehicle moves forward according to the moved reference line, and the obstacle avoidance method for moving the reference line is suitable for a static obstacle scene, so that the continuity of the threshold judgment method is avoided, and the obstacle can be avoided in time.
Description
Technical Field
The invention relates to the technical field of vehicle track planning, in particular to a moving reference line obstacle avoidance method and system based on a Lanelet frame.
Background
Autopilot technology has great potential in improving driving safety, comfort and efficiency, and has become a very active research direction with technical progress in the fields of sensing technology, computer technology, artificial intelligence and the like in the past decade, and has received extensive attention from academia and industry. In many fields of automatic driving, path planning is one of the important factors affecting the autonomous driving ability of an automatic driving car, and path planning is required to avoid obstacles in addition to planning a trajectory conforming to the kinematics of the car.
To realize path planning in automatic driving, a high-precision map is established first, and then path planning and path optimization are carried out according to the high-precision map information and data. For areas within a smaller area, such as school areas, scenic tours, etc., a Lanelet framework may be utilized to map, followed by low-speed planning. In local planning, it is very important for the method of avoiding the obstacle. The most commonly used obstacle avoidance method at present is to calculate the distance between the track point and the center of the obstacle, judge the deflection direction and distance of the vehicle through a threshold value, and the threshold value judgment method can generate a phenomenon of hesitation, if a small obstacle is positioned at the center of a lane, the vehicle can sometimes select a track which is wound leftwards and a track which is wound rightwards to return back and forth, and because the cost of the tracks at two sides at a certain moment is the same, the vehicle can slightly shake leftwards and rightwards, and the time is wasted.
According to the obstacle avoidance method for the unmanned vehicle in the prior art, when the main controller judges that the offset of obstacle avoidance path data and original global path data is smaller than a preset offset threshold value, the main controller calculates according to the obstacle avoidance path and vehicle running data to obtain a target speed and a target steering angle and sends the target speed and the target steering angle to a vehicle body controller; the vehicle body controller controls the running of the vehicle according to the target speed and the target steering angle; however, the threshold judgment method can generate a phenomenon of hesitation under some conditions, so that time is wasted, reliability is poor, and even obstacles cannot be avoided in time.
Disclosure of Invention
The invention provides a moving reference line obstacle avoidance method and a moving reference line obstacle avoidance system for avoiding obstacle breakage and overcoming the phenomenon of hesitation.
The technical scheme of the invention is as follows:
a mobile reference line obstacle avoidance method based on a Lanelet frame comprises the following steps:
s1, generating a high-precision map based on a Lanelet frame, and taking a road center line as a default reference line;
s2, setting a vehicle to track a default reference line to generate a local track in real time, controlling the vehicle to travel along the local track, and acquiring an obstacle coordinate after the vehicle senses a front obstacle;
s3, calculating the direction and distance of the reference line to be moved for avoiding the obstacle according to the obstacle coordinates;
s4, moving the default reference line according to the moving direction and distance to obtain a new reference line, setting a vehicle to track the new reference line to generate a local track in real time, and controlling the vehicle to travel along the local track so as to bypass the obstacle;
s5, after the vehicle bypasses the obstacle, the new reference line position is restored to a default reference line positioned on the central line of the road, the vehicle is set to track the default reference line to generate a local track in real time, and the vehicle is controlled to travel along the local track.
According to the technical scheme, the moving reference line obstacle avoidance method based on the Lanelet frame is provided, a high-precision map is generated based on the Lanelet frame, the central line of a road can be calculated by using the road coordinates of the high-precision map, the central line of the road is taken as a default reference line, when a vehicle senses an obstacle, the reference line is moved according to the coordinates of the obstacle, the vehicle tracks the moved reference line to obtain a local track, the vehicle is controlled to move forward according to the local track, the obstacle avoidance method of the moving reference line is suitable for a static obstacle scene, the continuity of the threshold judgment method is avoided, and the obstacle can be avoided in time.
Further, the local track is generated by a discrete space point scattering method, the central line of the road in the high-precision map is composed of sparse road central points, and the road central points are subjected to cubic spline interpolation to generate the road central line as a default reference line.
Further, step S3 further includes calculating a distance between the vehicle and the obstacle; and S4, judging whether the distance between the vehicle and the obstacle is smaller than or equal to a first preset distance, and moving a default reference line according to the moving direction and the distance to obtain a new reference line when the distance between the vehicle and the obstacle is smaller than or equal to the first preset distance.
Further, the specific process of calculating the moving direction and distance in step S3 is as follows:
s31, obtaining coordinates of an obstacle, and framing the obstacle with a mark frame, wherein the mark frame is a quadrilateral frame;
s32, calculating the vertical distance between each vertex of the identification frame and the reference line, taking the maximum vertical distance as the maximum vertex offset, and taking the minimum vertical distance as the minimum vertex offset;
s33, determining the moving direction and distance of the reference line according to the maximum vertex offset and the minimum vertex offset.
Further, the obstacle positions are divided into two cases, namely that all obstacle identification frames are on one side of a default reference line or that the obstacle identification frames are on the default reference line;
when the obstacle identification frame is all on one side of the reference line, the reference line translates by a distance d m The calculation process of (1) is as follows:
wherein d m Translation distance for reference line; the minimum vertex offset and the maximum vertex offset are d respectively min ,d max D if the obstacles are all to the left of the current reference line min >0,d max >0, if the obstacles are all to the right of the current reference line, d min <0,d max <0;E w For the width of the vehicle d w Is an anti-collision distance;
when the obstacle identification frame is on the reference line, the reference line translates by a distance d m The calculation process of (1) is as follows:
m=min(|d min |,| max |)
wherein d m Translation distance for reference line; the minimum vertex offset and the maximum vertex offset are d respectively min ,d max The method comprises the steps of carrying out a first treatment on the surface of the If d m <0, the reference line is shifted to the right if d m >0, the reference line is shifted to the left; e (E) w For the width of the vehicle d w Is the anti-collision distance.
Further, after the vehicle senses that the obstacle has been bypassed, the vehicle proceeds a second preset distance and then returns the new reference line to the default reference line located at the center line of the roadway in step S5.
Further, the method for scattering the points in the discrete space specifically comprises the following steps:
s21, performing speed sampling under a d/t coordinate system, and performing track sampling under an S/t coordinate system; where d is the lateral offset of the local trajectory relative to a default reference line, d >0 when offset to the left along the vehicle travel direction, d <0 when offset to the right, d=0 when on the default reference line, s representing the length of the reference line;
s22, respectively performing polynomial curve fitting on the speed sampling result and the track sampling result to obtain a series of curves, wherein a series of points are included on the curves, namely track points obtained by track planning;
s23, converting the S/d coordinate system track points into a world coordinate system;
and S24, screening out an optimal track according to comfort and dynamics constraint, and supplying the optimal track to the vehicle for running.
A lane et frame based mobile reference line obstacle avoidance system comprising: the system comprises a map generation unit, a track tracking unit, a sensing unit, a moving distance calculation unit and a reference line moving unit;
the map generating unit generates a high-precision map based on the Lanelet frame, and takes the central line of the road as a default reference line; the track tracking unit is used for setting a vehicle to track a default reference line to generate a local track in real time, controlling the vehicle to travel along the local track and acquiring an obstacle coordinate after the sensing unit of the vehicle senses a front obstacle; the moving distance calculating unit calculates the direction and distance of the reference line to be moved for avoiding the obstacle according to the obstacle coordinates; the reference line moving unit moves the default reference line according to the moving direction and distance to obtain a new reference line, and the track tracking unit sets the vehicle to track the new reference line to generate a local track in real time, and controls the vehicle to travel along the local track so as to bypass the obstacle; after the sensing unit senses that the vehicle bypasses the obstacle, the reference line moving unit restores the new reference line position to a default reference line positioned on the central line of the road, and the track tracking unit sets the vehicle to track the default reference line to generate a local track in real time and controls the vehicle to travel along the local track.
Further, the track tracking unit generates the local track by a discrete space scattering method, the central line of the road in the high-precision map is composed of sparse road central points, and the road central points are subjected to cubic spline interpolation to generate the road central line as a default reference line.
Further, the moving distance calculating unit is required to calculate the distance between the vehicle and the obstacle; and the reference line moving unit judges whether the distance between the vehicle and the obstacle is smaller than or equal to a first preset distance, and when the distance between the vehicle and the obstacle is smaller than or equal to the first preset distance, the default reference line is moved according to the moving direction and the distance to obtain a new reference line.
The invention provides a mobile reference line obstacle avoidance method and system based on a Lanelet frame, and compared with the prior art, the invention has the beneficial effects that: the road center line is used as a default reference line, when the vehicle senses an obstacle, the reference line is moved according to the obstacle coordinates, the vehicle tracks the moved reference line to obtain a local track, the vehicle is controlled to travel according to the local track, the obstacle avoidance method of the moving reference line is suitable for a static obstacle scene, the continuity of the threshold judgment method is avoided, and the obstacle can be avoided in time.
Drawings
FIG. 1 is a schematic diagram of steps of a moving reference line obstacle avoidance method based on a Lanelet frame;
FIG. 2 is a schematic view of a road centerline;
FIG. 3 is a schematic view of a reference line for obstacle movement;
FIG. 4 is a graph illustrating the amount of obstacle apex offset;
FIG. 5 is a schematic diagram of the different driving track shifts of the vehicle;
fig. 6 is a reference line coordinate schematic.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
for better illustration of the present embodiment, some parts of the drawings may be omitted, enlarged or reduced, and do not represent actual dimensions;
it will be appreciated by those skilled in the art that some well known descriptions in the figures may be omitted.
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
The positional relationship depicted in the drawings is for illustrative purposes only and is not to be construed as limiting the present patent;
example 1
A moving reference line obstacle avoidance method based on a Lanelet frame is shown in figure 1, and comprises the following steps:
s1, generating a high-precision map based on a Lanelet frame, and taking a road center line as a default reference line;
s2, setting a vehicle to track a default reference line to generate a local track in real time, controlling the vehicle to travel along the local track, and acquiring an obstacle coordinate after the vehicle senses a front obstacle;
s3, calculating the direction and distance of the reference line to be moved for avoiding the obstacle according to the obstacle coordinates;
s4, moving the default reference line according to the moving direction and distance to obtain a new reference line, setting a vehicle to track the new reference line to generate a local track in real time, and controlling the vehicle to travel along the local track so as to bypass the obstacle;
s5, after the vehicle bypasses the obstacle, the new reference line position is restored to a default reference line positioned on the central line of the road, the vehicle is set to track the default reference line to generate a local track in real time, and the vehicle is controlled to travel along the local track.
The center line of the road in step S2 is shown in fig. 2.
According to the embodiment, the high-precision map is generated based on the Lanelet frame, the central line of the road can be calculated by utilizing the road coordinates of the high-precision map, the central line of the road is taken as a default reference line, when a vehicle senses an obstacle, the reference line is moved according to the obstacle coordinates, the vehicle tracks the moved reference line to obtain a local track, the vehicle is controlled to travel and advance according to the local track, the obstacle avoidance method for moving the reference line is suitable for a static obstacle scene, the continuity of a threshold judgment method is avoided, and the obstacle can be avoided in time.
Example 2
In this embodiment, on the basis of embodiment 1, the local track is generated by performing track planning by a method of scattering points in a discrete space,
the method for scattering the points in the discrete space comprises the following steps:
s21, performing speed sampling under a d/t coordinate system, and performing track sampling under an S/t coordinate system; where d is the lateral offset of the local trajectory relative to a default reference line, d >0 when offset to the left along the vehicle travel direction, d <0 when offset to the right, d=0 when on the default reference line, s representing the length of the reference line;
s22, respectively performing polynomial curve fitting on the speed sampling result and the track sampling result to obtain a series of curves, wherein a series of points are included on the curves, namely track points obtained by track planning;
s23, converting the S/d coordinate system track points into a world coordinate system;
and S24, screening out an optimal track according to comfort and dynamics constraint, and supplying the optimal track to the vehicle for running.
In the practical application process, the discrete space scattering points are divided into speed sampling and track sampling, the speed sampling is sampling under d/t coordinate system, the track sampling is sampling under s/t coordinate system, and then polynomial curve fitting is carried out respectively. Where d is the lateral offset of the local track relative to the reference line of track tracking, d >0 on the left along the direction of travel, d <0 on the right, d=0 on the reference line, and the longitudinal distance s represents the length of the reference line;
the discrete space scattering points are fitted under an s/d coordinate system through a polynomial curve to obtain a series of curves, a series of points are included on the curves, namely track points obtained through track planning, and then the s/d coordinate system track points are converted into a world coordinate system. The center line of the road in the high-precision map consists of sparse road center points, and the road center points are subjected to cubic spline interpolation to generate the road center line as a default reference line.
The calculation method of the reference line length s comprises the following steps: according to the start point (x) 0 ,y 0 ) Endpoint (x) n ,y n ) And the rest of the reference line waypointsCalculating the accumulated reference line length s:
from all reference line waypointsLength s from reference line i Generating reference line curves using cubic spline interpolation, as shown in FIG. 6, generating x respectively i /s i And y is i /s i And obtaining a first derivative and a second derivative relation corresponding to the cubic spline curve for coordinate system conversion in local planning. And obtaining a plurality of local tracks under the world coordinate system, screening out the optimal track according to comfort and dynamics constraint, and providing the optimal track for running of the vehicle.
In this embodiment, step S3 further includes calculating a distance between the vehicle and the obstacle; and S4, judging whether the distance between the vehicle and the obstacle is smaller than or equal to a first preset distance, and moving a default reference line according to the moving direction and the distance to obtain a new reference line when the distance between the vehicle and the obstacle is smaller than or equal to the first preset distance.
Step S3, moving the reference line is shown in fig. 3, and the specific process of calculating the moving direction and distance of the reference line is as follows:
s31, obtaining coordinates of an obstacle, and framing the obstacle with a mark frame, wherein the mark frame is a quadrilateral frame;
s32, calculating the vertical distance between each vertex of the identification frame and the reference line, taking the maximum vertical distance as the maximum vertex offset, and taking the minimum vertical distance as the minimum vertex offset; the amount of displacement of the obstacle vertices is shown in fig. 4;
s33, determining the moving direction and distance of the reference line according to the maximum vertex offset and the minimum vertex offset.
The obstacle positions are divided into two cases, namely, the obstacle identification frames are all on one side of a default reference line, or the obstacle identification frames are on the default reference line;
when the obstacle identification frame is all on one side of the reference line, the reference line translates by a distance d m The calculation process of (1) is as follows:
wherein d m Translation distance for reference line; the minimum vertex offset and the maximum vertex offset are d respectively min ,d max D if the obstacles are all to the left of the current reference line min >0,d max >0, if the obstacles are all to the right of the current reference line, d min <0,d max <0;E w For the width of the vehicle d w Is the anti-collision distance.
When the obstacle identification frame is on the reference line, the reference line translates by a distance d m The calculation process of (1) is as follows:
m=min(|d min |,| max |)
wherein d m Translation distance for reference line; the minimum vertex offset and the maximum vertex offset are d respectively min ,d max The method comprises the steps of carrying out a first treatment on the surface of the If d m <0, the reference line is shifted to the right if d m >0, the reference line is shifted to the left; e (E) w For the width of the vehicle d w Is the anti-collision distance.
Step S5, after the vehicle senses that the obstacle is bypassed, the vehicle advances a second preset distance, and then the new reference line is restored to the default reference line positioned on the central line of the road. Fig. 5 is a schematic diagram of different offset situations of the vehicle, when the vehicle is offset leftwards along the running direction, the offset distance d >0, and when the vehicle is offset rightwards, d <0.
Example 3
On the basis of example 2, in this example, d is given m Defining a value range:
i.e. d m ∈[-1.5,1.5]. If this range is exceeded, it is stated that the vehicle cannot bypass the obstacle and must be parked. By setting d m The value range of the vehicle is ensured not to exceed the road range when the vehicle avoids the obstacle.
Defining the direction angle of a lane under a world coordinate system as f, and moving reference line coordinates:
wherein set C represents a set of coordinate points on a reference line before non-movement
C={(cx 0 ,cy 0 ),(cx 1 ,cy 1 ),(cx 2 ,cy 2 ),...,(cx n ,cy n )}
Set M represents a set of coordinate points on the reference line after movement
M={(mx 0 ,my 0 ),(mx 1 ,my 1 ),(mx 2 ,my 2 ),...,(mx n ,my n )}
Example 4
A lane et frame based mobile reference line obstacle avoidance system for performing the obstacle avoidance method of any of embodiments 1 to 3, comprising: the system comprises a map generation unit, a track tracking unit, a sensing unit, a moving distance calculation unit and a reference line moving unit;
the map generating unit generates a high-precision map based on the Lanelet frame, and takes the central line of the road as a default reference line; the track tracking unit is used for setting a vehicle to track a default reference line to generate a local track in real time, controlling the vehicle to travel along the local track and acquiring an obstacle coordinate after the sensing unit of the vehicle senses a front obstacle; the moving distance calculating unit calculates the direction and distance of the reference line to be moved for avoiding the obstacle according to the obstacle coordinates; the reference line moving unit moves the default reference line according to the moving direction and distance to obtain a new reference line, and the track tracking unit sets the vehicle to track the new reference line to generate a local track in real time, and controls the vehicle to travel along the local track so as to bypass the obstacle; after the sensing unit senses that the vehicle bypasses the obstacle, the reference line moving unit restores the new reference line position to a default reference line positioned on the central line of the road, and the track tracking unit sets the vehicle to track the default reference line to generate a local track in real time and controls the vehicle to travel along the local track.
In this embodiment, the track tracking unit generates the local track by using a discrete space scattering method, the center line of the road in the high-precision map is composed of sparse road center points, and the road center points are subjected to cubic spline interpolation to generate the road center line as a default reference line.
In this embodiment, the moving distance calculating unit is further required to calculate the distance between the vehicle and the obstacle; and the reference line moving unit judges whether the distance between the vehicle and the obstacle is smaller than or equal to a first preset distance, and when the distance between the vehicle and the obstacle is smaller than or equal to the first preset distance, the default reference line is moved according to the moving direction and the distance to obtain a new reference line.
The specific process of calculating the moving direction and distance by the moving distance calculating unit is as follows:
the moving distance calculating unit obtains the coordinates of the obstacle and frames the obstacle with a mark frame, wherein the mark frame is a quadrilateral frame; calculating the vertical distance between each vertex of the identification frame and the reference line, taking the maximum vertical distance as the maximum vertex offset, and taking the minimum vertical distance as the minimum vertex offset; the moving distance calculating unit determines the direction and distance of the reference line movement according to the maximum vertex offset and the minimum vertex offset.
It is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (8)
1. A mobile reference line obstacle avoidance method based on a Lanelet frame is characterized by comprising the following steps:
s1, generating a high-precision map based on a Lanelet frame, and taking a road center line as a default reference line;
s2, setting a vehicle to track a default reference line to generate a local track in real time, controlling the vehicle to travel along the local track, and acquiring an obstacle coordinate after the vehicle senses a front obstacle;
s3, according to the coordinates of the obstacle, calculating the direction and distance of the default reference line to be moved for avoiding the obstacle, wherein the method comprises the following steps:
s31, obtaining coordinates of an obstacle, and framing the obstacle with a mark frame, wherein the mark frame is a quadrilateral frame;
s32, calculating the vertical distance between each vertex of the identification frame and the reference line, taking the maximum vertical distance as the maximum vertex offset, and taking the minimum vertical distance as the minimum vertex offset;
s33, determining the moving direction and distance of the reference line according to the maximum vertex offset and the minimum vertex offset;
the obstacle positions are divided into two cases, namely, the obstacle identification frames are all on one side of a default reference line, or the obstacle identification frames are on the default reference line;
when the obstacle identification frames are all on one side of the reference line, the reference line translates by a distanceThe calculation process of (1) is as follows:
wherein,translation distance for reference line; the minimum vertex offset and the maximum vertex offset are +.>,/>If the obstacles are all to the left of the current reference line +.>,/>If the obstacles are all to the right of the current reference line, then,/>;/>For the width of the vehicle>Is an anti-collision distance;
when the obstacle identification frame is on the reference line, the reference line translates a distanceThe calculation process of (1) is as follows:
wherein,translation distance for reference line; the minimum vertex offset and the maximum vertex offset are +.>,/>The method comprises the steps of carrying out a first treatment on the surface of the If->The reference line is shifted to the right if +.>The reference line is shifted to the left; />For the width of the vehicle>Is an anti-collision distance;
s4, moving the default reference line according to the moving direction and distance to obtain a new reference line, setting a vehicle to track the new reference line to generate a local track in real time, and controlling the vehicle to travel along the local track so as to bypass the obstacle;
s5, after the vehicle bypasses the obstacle, the new reference line position is restored to a default reference line positioned on the central line of the road, the vehicle is set to track the default reference line to generate a local track in real time, and the vehicle is controlled to travel along the local track.
2. The method for avoiding the obstacle on the basis of the moving reference line of the Lanelet frame according to claim 1, wherein the local track is generated by a discrete space scattering point method, the central line of the road in the high-precision map consists of sparse central points of the road, and the central points of the road are subjected to cubic spline interpolation to generate the central line of the road as a default reference line.
3. The method of claim 1, wherein step S3 further comprises calculating a distance between the vehicle and the obstacle; and S4, judging whether the distance between the vehicle and the obstacle is smaller than or equal to a first preset distance, and moving a default reference line according to the moving direction and the distance to obtain a new reference line when the distance between the vehicle and the obstacle is smaller than or equal to the first preset distance.
4. The method of claim 2, wherein step S5 is performed after the vehicle senses that the obstacle has been bypassed, the vehicle proceeds a second predetermined distance, and then the new reference line is restored to the default reference line located at the center line of the roadway.
5. The method for avoiding the obstacle by using the moving reference line based on the Lanelet frame according to claim 2, wherein the method for scattering points in the discrete space is specifically as follows:
s21, performing speed sampling under a d/t coordinate system, and performing track sampling under an S/t coordinate system; where d is the lateral offset of the local trajectory relative to a default reference line, d >0 when offset to the left along the vehicle travel direction, d <0 when offset to the right, d=0 when on the default reference line, s representing the length of the reference line;
s22, respectively performing polynomial curve fitting on the speed sampling result and the track sampling result to obtain a series of curves, wherein a series of points are included on the curves, namely track points obtained by track planning;
s23, converting the S/d coordinate system track points into a world coordinate system;
and S24, screening out an optimal track according to comfort and dynamics constraint, and supplying the optimal track to the vehicle for running.
6. A lane et frame based moving reference line obstacle avoidance system for performing the lane et frame based moving reference line obstacle avoidance method of any one of claims 1 to 5, comprising: the system comprises a map generation unit, a track tracking unit, a sensing unit, a moving distance calculation unit and a reference line moving unit;
the map generating unit generates a high-precision map based on the Lanelet frame, and takes the central line of the road as a default reference line; the track tracking unit is used for setting a vehicle to track a default reference line to generate a local track in real time, controlling the vehicle to travel along the local track and acquiring an obstacle coordinate after the sensing unit of the vehicle senses a front obstacle; the moving distance calculating unit calculates the direction and distance of the reference line to be moved for avoiding the obstacle according to the obstacle coordinates; the reference line moving unit moves the default reference line according to the moving direction and distance to obtain a new reference line, and the track tracking unit sets the vehicle to track the new reference line to generate a local track in real time, and controls the vehicle to travel along the local track so as to bypass the obstacle; after the sensing unit senses that the vehicle bypasses the obstacle, the reference line moving unit restores the new reference line position to a default reference line positioned on the central line of the road, and the track tracking unit sets the vehicle to track the default reference line to generate a local track in real time and controls the vehicle to travel along the local track.
7. The lane let frame-based moving reference line obstacle avoidance system of claim 6, wherein the track tracking unit generates the local track by a discrete space scattering method, wherein a center line of a road in the high-precision map consists of sparse road center points, and the road center points are subjected to cubic spline interpolation to generate the road center line as a default reference line.
8. The lane let frame-based moving reference line obstacle avoidance system of claim 6 wherein the moving distance calculation unit further calculates a distance between the vehicle and the obstacle; and the reference line moving unit judges whether the distance between the vehicle and the obstacle is smaller than or equal to a first preset distance, and when the distance between the vehicle and the obstacle is smaller than or equal to the first preset distance, the default reference line is moved according to the moving direction and the distance to obtain a new reference line.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2022102790663 | 2022-03-21 | ||
CN202210279066 | 2022-03-21 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114610044A CN114610044A (en) | 2022-06-10 |
CN114610044B true CN114610044B (en) | 2024-03-22 |
Family
ID=81869899
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210386410.9A Active CN114610044B (en) | 2022-03-21 | 2022-04-13 | Mobile reference line obstacle avoidance method and system based on Lanelet frame |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114610044B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116858276B (en) * | 2023-06-14 | 2024-05-28 | 武汉大学 | Map-assisted multi-sensor fusion positioning method and computer readable medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016149110A (en) * | 2015-02-10 | 2016-08-18 | 国立大学法人金沢大学 | Vehicle travel control device |
EP3524934A1 (en) * | 2018-02-07 | 2019-08-14 | Baidu USA LLC | Systems and methods for determining a projection of an obstacle trajectory onto a reference line of an autonomous vehicle |
CN111332285A (en) * | 2018-12-19 | 2020-06-26 | 长沙智能驾驶研究院有限公司 | Method and device for vehicle to avoid obstacle, electronic equipment and storage medium |
CN112362074A (en) * | 2020-10-30 | 2021-02-12 | 重庆邮电大学 | Intelligent vehicle local path planning method under structured environment |
-
2022
- 2022-04-13 CN CN202210386410.9A patent/CN114610044B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016149110A (en) * | 2015-02-10 | 2016-08-18 | 国立大学法人金沢大学 | Vehicle travel control device |
EP3524934A1 (en) * | 2018-02-07 | 2019-08-14 | Baidu USA LLC | Systems and methods for determining a projection of an obstacle trajectory onto a reference line of an autonomous vehicle |
CN111332285A (en) * | 2018-12-19 | 2020-06-26 | 长沙智能驾驶研究院有限公司 | Method and device for vehicle to avoid obstacle, electronic equipment and storage medium |
CN112362074A (en) * | 2020-10-30 | 2021-02-12 | 重庆邮电大学 | Intelligent vehicle local path planning method under structured environment |
Also Published As
Publication number | Publication date |
---|---|
CN114610044A (en) | 2022-06-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Park et al. | Development of lateral control system for autonomous vehicle based on adaptive pure pursuit algorithm | |
Broggi et al. | The ARGO autonomous vehicle’s vision and control systems | |
WO2018055916A1 (en) | Vehicle movement control device | |
CN107831761B (en) | Path tracking control method of intelligent vehicle | |
CN113204236B (en) | Intelligent agent path tracking control method | |
GB2570887A (en) | A system for a vehicle | |
CN110036353A (en) | For the self-adaptation control method and system in the surface car of trace, especially in automatic Pilot scene | |
CN109270933A (en) | Unmanned barrier-avoiding method, device, equipment and medium based on conic section | |
US10997862B2 (en) | Vehicle travel control method and vehicle travel control device | |
CN111006667B (en) | Automatic driving track generation system under high-speed scene | |
CN113721637B (en) | Intelligent vehicle dynamic obstacle avoidance path continuous planning method and system and storage medium | |
CN111806467A (en) | Variable speed dynamic track changing planning method based on vehicle driving rule | |
Li et al. | A practical trajectory planning framework for autonomous ground vehicles driving in urban environments | |
CN108168560B (en) | Composite navigation control method for omnidirectional AGV | |
CN111830979A (en) | Trajectory optimization method and device | |
CN111896004A (en) | Narrow passage vehicle track planning method and system | |
CN114610044B (en) | Mobile reference line obstacle avoidance method and system based on Lanelet frame | |
CN109085840B (en) | Vehicle navigation control system and control method based on binocular vision | |
CN114852085A (en) | Automatic vehicle driving track planning method based on road right invasion degree | |
JP2024520376A (en) | An adaptive path following algorithm for large vehicles. | |
CN117170377A (en) | Automatic driving method and device and vehicle | |
Li et al. | Lane keeping control based on model predictive control under region of interest prediction considering vehicle motion states | |
CN115525054A (en) | Large-scale industrial park unmanned sweeper edge path tracking control method and system | |
CN109606362A (en) | It is a kind of that holding control method in feedforward lane is opened up based on road curvature | |
CN115061478A (en) | Method, system and storage medium for local obstacle avoidance and path tracking of automatic driving vehicle |
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 |