CN108445886B - Automatic driving vehicle lane change planning method and system based on Gaussian equation - Google Patents
Automatic driving vehicle lane change planning method and system based on Gaussian equation Download PDFInfo
- Publication number
- CN108445886B CN108445886B CN201810381104.XA CN201810381104A CN108445886B CN 108445886 B CN108445886 B CN 108445886B CN 201810381104 A CN201810381104 A CN 201810381104A CN 108445886 B CN108445886 B CN 108445886B
- Authority
- CN
- China
- Prior art keywords
- gaussian
- translation
- obstacle
- planning
- coordinate
- 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 63
- 230000008859 change Effects 0.000 title claims abstract description 44
- 238000013519 translation Methods 0.000 claims abstract description 53
- 238000013461 design Methods 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005315 distribution function Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims 6
- 230000011218 segmentation Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 4
- 230000035772 mutation Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a method and a system for planning lane change of an automatic driving vehicle based on a Gaussian equation, wherein the method comprises the following steps: step 1: defining a local waypoint format; step 2: calculating the center of the obstacle, namely the longitudinal length; and step 3: planning function design and calculating translation quantity delta h of each road point; and 4. step 4. And marking the translation quantity delta h to the abscissa variation quantity delta x of the corresponding road point. The method comprises the steps of moving a Gaussian origin from a local origin of coordinates of a vehicle body to a central point of an obstacle by calculating coordinates of the central point of the obstacle and longitudinal depth of the obstacle, and simultaneously carrying out Gaussian function segmentation by utilizing the longitudinal depth of the obstacle to obtain translation percentage corresponding to each road point; and marking the transverse variation of each road point in the planning by using the global coordinate, and ensuring the consistency of the path when the channel changing condition is not changed.
Description
Technical Field
The invention relates to the technical field of computer vision and image processing, in particular to a method and a system for planning lane change of an automatic driving vehicle based on a Gaussian equation.
Background
The automatic driving technology is mature day by day, and the path planning is the guarantee of unmanned car intelligent degree. At present, most of unmanned vehicles adopt a track translation method, the method is simple and efficient, but has the problem of track step change, and the problem easily causes the unsmooth transverse control of the unmanned vehicles, so that the poor driving experience is caused; meanwhile, if the lane changing condition is not changed during the lane changing planning, in order to ensure the consistency of the navigation path, the unmanned vehicles should reduce the planning as much as possible. In order to solve the problems, the invention provides a track changing track planning method combining track translation and Gaussian low-pass filtering, wherein a Gaussian origin is moved from a local origin of coordinates of a vehicle body to a central point of an obstacle by calculating the coordinates of the central point of the obstacle and the longitudinal depth of the obstacle, and simultaneously, the longitudinal depth of the obstacle is utilized to perform Gaussian function segmentation to obtain the translation percentage corresponding to each road point; and marking the transverse variation of each road point in the planning by using the global coordinate, and ensuring the consistency of the path when the channel changing condition is not changed. The invention solves the problem of track mutation on the track changing source, and can plan a track changing path, a lane keeping path and a path returning to the original track. In addition, based on the characteristics of the Gaussian function, the road changing path adjustment only needs to adjust the cut-off frequency of the Gaussian function, and the method is simple and efficient.
The invention patent with application number CN201710497273.5 discloses a lane change control method and device for an automatically driven vehicle, wherein when changing lanes, a travelable area is determined according to the distance between an obstacle and the vehicle and the current road condition, and when an adjusted guide track is located in the travelable area, steering is prepared, so that steering wheel shake caused by repeated attempts of lane change is avoided. According to the method, path translation is required to be carried out in each period in the lane changing process until the lane changing is finished, so that the planned track is influenced by vehicle body motion change, sensor errors and the like in the lane changing process, and the relevance of the planned path is weak.
The invention patent with the application number of CN1O5329238A discloses an automatic driving automobile lane changing control method based on monocular vision, and the method is characterized in that a camera is arranged on the roof of the automatic driving automobile and used for collecting lane line images; processing and identifying the image of the lane line through an image processing module to obtain a fitted lane line; and calculating the steering wheel angle increment through the upper computer module, and outputting a motor control signal to the execution unit. The method has higher requirements on the acquisition device, can only acquire lane information by using a camera, and has insufficient adaptability due to the lane changing method based on monocular visual image processing.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for planning lane change of an automatic driving vehicle based on a Gaussian equation, wherein a Gaussian origin is moved from a local origin of coordinates of a vehicle body to a central point of an obstacle by calculating the coordinates of the central point of the obstacle and the longitudinal depth of the obstacle, and simultaneously, the longitudinal depth of the obstacle is utilized to carry out Gaussian function segmentation to obtain the translation percentage corresponding to each road point; and marking the transverse variation of each road point in the planning by using the global coordinate, and ensuring the consistency of the path when the channel changing condition is not changed.
The invention provides a lane change planning method for an automatic driving vehicle based on a Gaussian equation, which comprises the following steps:
step 1: defining a local waypoint format;
step 2: calculating the center of the obstacle, namely the longitudinal length;
and step 3: planning function design and calculating translation quantity delta h of each road point;
and 4, step 4: and marking the translation quantity delta h to the abscissa variation quantity delta x of the corresponding road point.
Preferably, each of the waypoints is composed of global coordinates (X, Y) and local coordinates (X, Y) and an abscissa change amount Δ X.
In any of the above aspects, the global coordinates are preferably a coordinate system in consideration of the position of the vehicle, the obstacle, the map, or the like, and the origin of coordinates is not changed.
In any of the above schemes, preferably, the local coordinate is a rectangular coordinate system in which the vehicle head is an origin, the vehicle moving direction is a longitudinal axis, and a direction perpendicular to the moving direction is a transverse axis, and the origin of coordinates changes in real time with the vehicle body.
In any of the above schemes, preferably, the step 2 is to calculate the longitudinal depth s of the obstacle, i.e. the local coordinates (j, i) of the center of the obstacle.
In any of the above schemes, preferably, the step 3 includes taking the longitudinal distance of the path as an argument, and taking a translation percentage h (y) corresponding to each distance obtained according to a gaussian low-pass filtering function, where the translation percentage h (y) is calculated by the formula
Wherein D is0The measure of the extent of the bits with respect to the center, y is the distance from the center of the frequency rectangle.
In any of the above schemes, preferably, the calculation formula of the translation amount Δ h of each of the waypoints is
△h＝h×H(y)
Wherein h is the maximum translation distance value.
In any of the above solutions, preferably, the step 3 includes considering the longitudinal length of the obstacle to ensure the safety of lane keeping after lane changing, and obtaining the following translation distribution function
Wherein, T is a longitudinal distance value range and is symmetrical about the center point of the barrier.
In any of the above solutions, it is preferable that step 4 includes correcting new local coordinates by Δ x in the global.
In any of the above solutions, preferably, the gaussian low-pass filter function is
Where μ is the value of the probability density function of the normal distribution, σ2Is the variance.
In any of the above embodiments, it is preferred that a random variable X obeys the distribution of the function f (X, μ, σ), denoted as XN (μ, σ)2)。
In any of the above schemes, preferably, based on the characteristics of gaussian probability distribution, the gaussian function may perform the evolution of the frequency domain filter function, so as to obtain the following formula:
where D (u, v) is the distance from the center of the frequency rectangle, and σ is a measure of the extent of the center.
In any of the above embodiments, preferably, σ ═ D is given0To obtain a Gaussian low-pass filter
Wherein D is0Is the cut-off frequency.
A second object of the present invention is to provide a lane change planning system for an autonomous vehicle based on gaussian equation, comprising the following modules:
the waypoint defining module: for defining a local waypoint format;
a calculation module: the system is used for calculating the center of the obstacle, namely the longitudinal length, planning function design and calculating the translation quantity delta h of each road point;
a marking module: and the horizontal coordinate variation quantity Deltax is used for marking the translation quantity Deltah to the corresponding road point. Preferably, each of the waypoints is composed of global coordinates (X, Y) and local coordinates (X, Y) and an abscissa change amount Δ X.
In any of the above aspects, the global coordinates are preferably a coordinate system in consideration of the position of the vehicle, the obstacle, the map, or the like, and the origin of coordinates is not changed.
In any of the above schemes, preferably, the local coordinate is a rectangular coordinate system in which the vehicle head is an origin, the vehicle moving direction is a longitudinal axis, and a direction perpendicular to the moving direction is a transverse axis, and the origin of coordinates changes in real time with the vehicle body.
In any of the above schemes, preferably, the calculation module is configured to calculate a longitudinal depth s of the obstacle, i.e., a local coordinate (j, i) of a center of the obstacle.
In any of the foregoing schemes, preferably, the calculating module is further configured to take the longitudinal distance of the path as an argument, and take a translation percentage h (y) corresponding to each distance obtained according to a gaussian low-pass filtering function, where the translation percentage h (y) is calculated by using a formula of
Wherein D is0The measure of the extent of the bits with respect to the center, y is the distance from the center of the frequency rectangle.
In any of the above schemes, preferably, the calculation formula of the translation amount Δ h of each of the waypoints is
△h＝h×H(y)
Wherein h is the maximum translation distance value.
In any of the above solutions, preferably, the step 3 includes considering the longitudinal length of the obstacle to ensure the safety of lane keeping after lane changing, and obtaining the following translation distribution function
Wherein, T is a longitudinal distance value range and is symmetrical about the center point of the barrier.
In any of the above solutions, it is preferable that the marking module is configured to correct new local coordinates by Δ x in the global context.
In any of the above solutions, preferably, the gaussian low-pass filter function is
Where μ is the value of the probability density function of the normal distribution, σ2Is the variance.
In any of the above arrangements, it is preferred that a random variable X obeys the distribution of the function f (X, μ, σ), denoted X N (μ, σ)2)。
In any of the above schemes, preferably, based on the characteristics of gaussian probability distribution, the gaussian function may perform the evolution of the frequency domain filter function, so as to obtain the following formula:
where D (u, v) is the distance from the center of the frequency rectangle, and σ is a measure of the extent of the center.
In any of the above embodiments, preference is given toLet σ be D0To obtain a Gaussian low-pass filter
Wherein D is0Is the cut-off frequency.
The invention provides a Gaussian equation-based planning method for changing lanes of an automatic driving vehicle, which solves the problem of track mutation on a lane changing source, can plan a path for changing the lanes, a lane keeping path and a path for returning to an original track, and is simple and efficient because the path for changing the lanes is adjusted only by adjusting the cut-off frequency of the Gaussian function based on the characteristics of the Gaussian function.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of a Gaussian equation based lane change planning method for an autonomous vehicle in accordance with the present invention.
Fig. 1A is a distribution diagram of gaussian low-pass filter functions with different cut-off frequencies according to the embodiment shown in fig. 1 of the automatic driving vehicle lane change planning method based on the gaussian equation.
FIG. 1B is a diagram of azimuth angles of a single route under regular terrain according to the embodiment shown in FIG. 1 of the method for planning lane change of an autonomous vehicle based on Gaussian equations according to the present invention.
Fig. 1C is a flowchart of a method for planning route point indexing in a lane change process according to the embodiment shown in fig. 1 of the automatic driving vehicle lane change planning method based on the gaussian equation in accordance with the present invention.
Fig. 1D is a diagram of an example of unmanned vehicle trajectory planning according to the embodiment shown in fig. 1 for the automatic driven vehicle lane change planning method based on the gaussian equation in accordance with the present invention.
FIG. 2 is a block diagram of a preferred embodiment of a Gaussian equation based lane change planning system for an autonomous vehicle in accordance with the present invention.
Fig. 3 is a probability distribution diagram of a proposed planning algorithm according to another preferred embodiment of the automatic driving vehicle lane change planning method based on the gaussian equation.
Detailed Description
The invention is further illustrated with reference to the figures and the specific examples.
Example one
The automatic driving technology is mature day by day, and the path planning is the guarantee of unmanned car intelligent degree. At present, most of unmanned vehicles adopt a track translation method, the method is simple and efficient, but has the problem of track step change, and the problem easily causes the unsmooth transverse control of the unmanned vehicles, so that the poor driving experience is caused; meanwhile, if the lane changing condition is not changed during the lane changing planning, in order to ensure the consistency of the navigation path, the unmanned vehicles should reduce the planning as much as possible. In order to solve the problems, the invention provides a track changing track planning method combining track translation and Gaussian low-pass filtering, wherein a Gaussian origin is moved from a local origin of coordinates of a vehicle body to a central point of an obstacle by calculating the coordinates of the central point of the obstacle and the longitudinal depth of the obstacle, and simultaneously, the longitudinal depth of the obstacle is utilized to perform Gaussian function segmentation to obtain the translation percentage corresponding to each road point; and marking the transverse variation of each road point in the planning by using the global coordinate, and ensuring the consistency of the path when the channel changing condition is not changed. The invention solves the problem of track mutation on the track changing source, and can plan a track changing path, a lane keeping path and a path returning to the original track. In addition, based on the characteristics of the Gaussian function, the road changing path adjustment only needs to adjust the cut-off frequency of the Gaussian function, and the method is simple and efficient.
As shown in fig. 1 and 2, step 100 is performed, and the waypoint definition module 200 defines a local waypoint format. The waypoint structure is shown in table 1, each waypoint is composed of global coordinates (X, Y), local coordinates (X, Y) and abscissa variation Δ X, and the local path is composed of a plurality of waypoints, as shown in fig. 1A. The local coordinate system is a rectangular coordinate system which takes the vehicle head as an original point, the motion direction of the vehicle as a longitudinal axis and the direction vertical to the motion direction as a transverse axis, and the original point of the coordinate changes along with the vehicle body in real time as shown in jMi in fig. 1A; global coordinates are coordinate systems that take into account the location of the vehicle, obstacle, map, etc., with the origin of coordinates unchanged, such as yOx in fig. 1A. The method has the advantages that the unmanned vehicle is guided to automatically drive in real time through the local coordinate domination effect, planning road point marking is conducted through the global coordinate domination effect when the obstacles do not change, and for the unmanned vehicle, the same lane changing only needs to be planned once through the processing mode, so that real-time secondary planning in the lane changing process is avoided.
| Global coordinate | Global coordinate | Local coordinates | Local coordinates | Amount of change of abscissa |
| X | Y | x | y | △x |
TABLE 1 local waypoint structure
In step 110, the calculation module 210 calculates the center of the obstacle, i.e., the longitudinal length. As shown in fig. 1A, the obstacle longitudinal depth s and the obstacle center local coordinates (j, i) are calculated.
And executing the step 120, calculating a planning function design of the module 210, and calculating a translation amount Δ h of each waypoint. The function of this function is to take the longitudinal distance of the path as an argument, taking the translation percentage corresponding to each distance obtained according to the gaussian low-pass filtering function.
Multiplying the percentage of lateral translation on the original path by the maximum translation distance value yields the amount of translation for each waypoint, as shown in equation 2.
△h＝h×H(y) (2)
The gaussian low-pass filtering is characterized in that the function probability distribution is smoothly and symmetrically decreased towards two sides by taking a point 0 as a center. Based on the above, in order to plan the lane change path and the return path, the gaussian function is gradually decreased towards two sides, and the gaussian coordinate origin needs to be moved from the local coordinate origin of the vehicle body to the center point of the obstacle. Meanwhile, in order to ensure the safety of lane keeping after lane changing, the longitudinal length of the obstacle needs to be considered, and as shown in s. in fig. 1A, the translation percentage should account for 100% of the translation amount within the range covered by the length of the obstacle, so the following translation distribution function can be obtained, as shown in formula 3.
Wherein, T is a longitudinal distance value range and is symmetrical about the center point of the barrier. The probability distribution function of equation 3 is shown in fig. 1B. In fig. 1B, the vertical axes of the different cut-off frequency curves have different degrees of decrease, which provides conditions for planning paths with different curvatures in different situations. Meanwhile, a function section with a longitudinal axis value of 1 is maintained on both sides of the origin, which is a position where the amount of translation is maintained at 100% at the time of lane keeping. The abscissa in fig. 1B is dm.
Step 130 is executed, and the marking module 220 marks the translation amount Δ h to the abscissa variation amount Δ x of the corresponding waypoint. Therefore, the unmanned vehicle can find the global coordinate corresponding to each road point in the lane changing process, and the new local coordinate is corrected through the global coordinate. Because the global coordinate of each waypoint is unchanged, the method ensures that only once planning is carried out when the lane changing condition is unchanged, and ensures the smoothness of the lane changing of the unmanned vehicle. As shown in fig. 1C, in the step 131, when the current local waypoint is obtained in the lane change process, first, a one-to-one correspondence point between the global coordinate under the first planning and the current global coordinate is indexed. Step 132 is executed to modify the horizontal coordinate translation amount of the current local coordinate according to the horizontal coordinate variation amount under the global coordinate of the first planning, and finally the current navigation path is obtained. And step 133, the unmanned vehicle automatically drives in real time according to the navigation path.
The lane change planning implementation of the invention can be completed through the four steps, and the implementation result is shown in fig. 1D. The unmanned vehicle meets the barrier on the driving route and has the condition of changing the lane to the right, at the moment, the unmanned vehicle can obtain 4 alternative paths according to the lane changing planning method provided by the invention, each path comprises a lane changing road section, a lane keeping road section and a road section returning to the original track, and the cut-off frequencies of Gaussian low-pass functions of different paths are different. FIG. 1D is a graphical representation of the effectiveness and advantages of the present invention.
Example two
Gaussian low pass filter function
The mean of the probability density function of normal distribution is mu, and the variance is sigma2(or standard deviation) is an example of a gaussian function:
if a random variable X obeys this distribution, we write X: n (mu, sigma)2). Based on the characteristics of gaussian probability distribution, the gaussian function can perform the evolution of the frequency domain filtering function, such as:
where D (u, v) is the distance from the center of the frequency rectangle, and σ is a measure of the extent of the center. By making σ equal to D0A gaussian low pass filter can be obtained:
wherein D is0Is the cut-off frequency, the probability distribution of H (u, v) for different cut-off frequencies is shown in fig. 2.
EXAMPLE III
The common lane changing method for the automatic driving vehicle comprises the following steps: the current local path is directly translated left and right by a fixed distance based on the position of the obstacle, and a new path obtained after translation is a path-changing path, such as a planned path 0 in fig. 2. The road changing path planned by the method does not consider the movement track of the unmanned vehicle in the future, is lack of planning of returning to the original path after changing the path, and ignores the danger judgment of the unmanned vehicle in the process of reaching the planned track.
The method is mainly characterized in that a smooth planning curve is obtained on the basis of translation lane changing, namely, the future movement track of the unmanned vehicle is considered, and the planning of the original track is returned after lane changing is added.
Example four
Compared with other similar prior art, the technical characteristics of the application are as follows:
1. the technical circuit is different from the conventional circuit. The method and the device perform track changing track planning by adding the Gaussian low-pass function on the basis of track translation, and the planned track not only comprises a track changing track, but also comprises a lane keeping track and a track of a lane returning original path.
2. Different driving comfort methods are solved when changing lanes. And the track is smoothed by directly utilizing a Gaussian function, so that the problem of poor driving comfort caused by sudden change of the lane change angle is solved from the source.
3. The number of plans varies. And local path planning is performed only once under the condition of meeting the lane change condition, and the path transverse transformation quantity obtained by planning is marked to the global coordinate, so that the new periodic path only needs to index the variation quantity of the local coordinate through the global coordinate in the lane change process, and the consistency of the lane change path is ensured.
4. There is no particular requirement for the sensors, whether radar, navigation, images, etc., as long as a road guide line can be provided, and the applicability is broader.
5. The technical nature is different. The method is carried out on the basis of meeting the lane changing condition, namely, the lane changing path planning is carried out after the lane changing condition is met, and the selection of the lane changing condition is not involved;
6. the lane change control method is different, and the final result of the method is the lane change path, not the lane change control quantity.
7. The coverage is different. The method is based on a planned track of a safety zone, namely the maximum translation track of the method is the lane width, and the lane keeping section is the longitudinal depth of an obstacle.
For a better understanding of the present invention, the foregoing detailed description has been given in conjunction with specific embodiments thereof, but not with the intention of limiting the invention thereto. Any simple modifications of the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention. In the present specification, each embodiment is described with emphasis on differences from other embodiments, and the same or similar parts between the respective embodiments may be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Claims (9)
1. An automatic driving vehicle lane change planning method based on a Gaussian equation comprises the following steps:
step 1: defining a local waypoint format;
step 2: calculating the center of the obstacle, namely the longitudinal length;
and step 3: planning function design and calculating translation amount of each road point
(ii) a Taking the longitudinal distance of the path as an independent variable, and taking the translation percentage corresponding to each distance obtained according to a Gaussian low-pass filtering function
Percent translation of
Is calculated by the formula
Wherein the content of the first and second substances,
is a measure of the extent of the center,
is the distance from the center of the frequency rectangle;
the Gaussian low-pass filter function is
Wherein the content of the first and second substances,
is a normally distributed function value of the probability density,
is the variance;
and 4, step 4: the translation amount is adjusted
Amount of change of abscissa marked to corresponding waypoint
The method comprises the following substeps:
step 41: indexing one-to-one corresponding points of the global coordinates below the first planning and the current global coordinates;
step 42: and modifying the horizontal coordinate translation amount of the current local coordinate according to the horizontal coordinate variation amount under the global coordinate planned for the first time, and finally obtaining the current navigation path.
2. The gaussian equation-based lane change planning method for autonomous vehicles as recited in claim 1, wherein: each route point is defined by global coordinates
And local coordinates
And amount of change of abscissa
And (4) forming.
3. The gaussian equation-based lane change planning method for autonomous vehicles as claimed in claim 2, wherein: the global coordinate is a coordinate system considering positions of the vehicle, the obstacle and the map, and the origin of the coordinate does not change.
4. The gaussian-equation-based lane-change planning method for autonomous vehicles according to claim 3, wherein: the local coordinate system is a rectangular coordinate system which takes the vehicle head as an original point, the motion direction of the vehicle as a longitudinal axis and the direction vertical to the motion direction as a transverse axis, and the original point of the coordinate changes along with the vehicle body in real time.
5. The gaussian-equation-based lane-change planning method for autonomous vehicles according to claim 4, wherein: step 2 is to calculate the longitudinal depth of the obstacle
I.e. the local coordinates of the center of the obstacle
。
6. The gaussian equation-based lane change planning method for autonomous vehicles as recited in claim 1, wherein: translation amount of each of the waypoints
Is calculated by the formula
Wherein the content of the first and second substances,
the maximum translation distance value.
7. The gaussian-equation-based lane-change planning method for autonomous vehicles according to claim 6, wherein: the step 3 comprises considering the longitudinal length of the obstacle to ensure the safety of lane keeping after lane changing and obtaining the following translation distribution function
Wherein the content of the first and second substances,
is a longitudinal distance value range, which is symmetrical about the center point of the obstacle.
8. The gaussian-equation-based lane-change planning method for autonomous vehicles as recited in claim 7, wherein: said step 4 comprises passing through said global coordinates
To correct the new local coordinates.
9. An autonomous vehicle lane change planning system based on the gaussian equation includes the following modules:
the waypoint defining module: for defining a local waypoint format;
a calculation module: used for calculating the center of the obstacle, namely the longitudinal length, planning the function design and calculating the translation amount of each road point
(ii) a And the translation percentage corresponding to each distance obtained according to the Gaussian low-pass filter function is taken as the independent variable of the longitudinal distance of the path
Percent translation of
Is calculated by the formula
Wherein the content of the first and second substances,
is a measure of the extent of the center,
is the distance from the center of the frequency rectangle;
the Gaussian low-pass filter function is
Wherein the content of the first and second substances,
is a normally distributed function value of the probability density,
is the variance;
a marking module: for translating the amount of translation
Amount of change of abscissa marked to corresponding waypoint
The marking method comprises the following substeps:
step 41: indexing one-to-one corresponding points of the global coordinates below the first planning and the current global coordinates;
step 42: and modifying the horizontal coordinate translation amount of the current local coordinate according to the horizontal coordinate variation amount under the global coordinate planned for the first time, and finally obtaining the current navigation path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810381104.XA CN108445886B (en) | 2018-04-25 | 2018-04-25 | Automatic driving vehicle lane change planning method and system based on Gaussian equation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810381104.XA CN108445886B (en) | 2018-04-25 | 2018-04-25 | Automatic driving vehicle lane change planning method and system based on Gaussian equation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108445886A CN108445886A (en) | 2018-08-24 |
| CN108445886B true CN108445886B (en) | 2021-09-21 |
Family
ID=63201053
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810381104.XA Active CN108445886B (en) | 2018-04-25 | 2018-04-25 | Automatic driving vehicle lane change planning method and system based on Gaussian equation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108445886B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110333727A (en) * | 2019-08-01 | 2019-10-15 | 上海钛米机器人科技有限公司 | Robot path planning method, device, equipment and medium |
| CN110362096B (en) * | 2019-08-13 | 2021-05-18 | 东北大学 | Unmanned vehicle dynamic trajectory planning method based on local optimality |
| CN111123952B (en) * | 2019-12-31 | 2021-12-31 | 华为技术有限公司 | Trajectory planning method and device |
| CN113515111B (en) * | 2020-03-25 | 2023-08-25 | 宇通客车股份有限公司 | Vehicle obstacle avoidance path planning method and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591332B (en) * | 2011-01-13 | 2014-08-13 | 同济大学 | Device and method for local path planning of pilotless automobile |
| CN106598053B (en) * | 2016-12-19 | 2018-01-02 | 驭势科技（北京）有限公司 | A kind of automatic driving vehicle transverse movement control object system of selection |
| CN107121980B (en) * | 2017-03-17 | 2019-07-09 | 北京理工大学 | A kind of automatic driving vehicle paths planning method based on virtual constraint |
| CN106843235B (en) * | 2017-03-31 | 2019-04-12 | 深圳市靖洲科技有限公司 | A kind of Artificial Potential Field path planning towards no person bicycle |
| CN106873600A (en) * | 2017-03-31 | 2017-06-20 | 深圳市靖洲科技有限公司 | It is a kind of towards the local obstacle-avoiding route planning method without person bicycle |
| CN107817790B (en) * | 2017-09-05 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and device for calculating curvature of vehicle track |
-
2018
- 2018-04-25 CN CN201810381104.XA patent/CN108445886B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108445886A (en) | 2018-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108445886B (en) | Automatic driving vehicle lane change planning method and system based on Gaussian equation | |
| CN109649393B (en) | Path planning method and device for automatically driving lane change | |
| CN106515722B (en) | A kind of method for planning track of vertically parking | |
| CN113359757B (en) | Unmanned vehicle path planning and trajectory tracking method | |
| CN109927716B (en) | Autonomous vertical parking method based on high-precision map | |
| DE102019102944B4 (en) | Systems and methods for a low feed forward vehicle control strategy | |
| CN109084798B (en) | Path planning method for issuing control points with road attributes through network | |
| CN110861642A (en) | Vehicle lateral motion control | |
| CN109324620A (en) | The dynamic trajectory planing method for carrying out avoidance based on lane line parallel offset and overtaking other vehicles | |
| CN113916246A (en) | Unmanned obstacle avoidance path planning method and system | |
| CN110617828B (en) | Method and system for generating dynamic target line during automatic driving of vehicle and vehicle | |
| CN112612287A (en) | System, method, medium and device for planning local path of automatic driving automobile | |
| WO2020135772A1 (en) | Generation method and generation system for dynamic target line during automatic driving of vehicle, and vehicle | |
| CN110553660A (en) | unmanned vehicle trajectory planning method based on A-star algorithm and artificial potential field | |
| DE102019134050A1 (en) | VEHICLE PATH PROCESSING | |
| US20190180117A1 (en) | Roadside object recognition apparatus | |
| DE102020102717A1 (en) | METHODS AND SYSTEMS FOR CONTROLLING THE LATERAL POSITION OF THE VEHICLE VIA AN INTERSECTION | |
| CN111896004A (en) | Narrow passage vehicle track planning method and system | |
| CN113525509B (en) | Steering control method and device for articulated vehicle | |
| CN112937606A (en) | Anti-collision path planning and control method and system for tracking automatic driving vehicle | |
| CN116118780A (en) | Vehicle obstacle avoidance track planning method, system, vehicle and storage medium | |
| CN111137298A (en) | Vehicle automatic driving method, device, system and storage medium | |
| DE102020105657A1 (en) | Methods and systems for the mapping and localization of a vehicle | |
| CN115993825A (en) | Unmanned vehicle cluster control system based on air-ground cooperation | |
| CN113887276A (en) | Image-based forward main target detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |