CN117804480A - Method, device, equipment and medium for generating tracking route of automatic driving vehicle - Google Patents
Method, device, equipment and medium for generating tracking route of automatic driving vehicle Download PDFInfo
- Publication number
- CN117804480A CN117804480A CN202311843700.2A CN202311843700A CN117804480A CN 117804480 A CN117804480 A CN 117804480A CN 202311843700 A CN202311843700 A CN 202311843700A CN 117804480 A CN117804480 A CN 117804480A
- Authority
- CN
- China
- Prior art keywords
- track
- smooth
- target
- global
- discrete points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000009499 grossing Methods 0.000 claims abstract description 84
- 238000012545 processing Methods 0.000 claims description 45
- 230000011218 segmentation Effects 0.000 claims description 34
- 230000008859 change Effects 0.000 claims description 28
- 230000002159 abnormal effect Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 230000001133 acceleration Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000005070 sampling Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Navigation (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for generating a tracking route of an automatic driving vehicle. The method comprises the following steps: determining a running track discrete point of a target vehicle, and performing global smoothing treatment on the running track discrete point to obtain an initial global smooth track; segmenting the initial global smooth track to obtain at least two candidate segmented smooth tracks, and respectively carrying out local smoothing on the moving track discrete points corresponding to the at least two candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks; performing curvature smoothing on the joint points of every two adjacent reference segment smooth tracks to obtain a target segment smooth track; and determining a target global smooth track according to the target segment smooth track, and determining a target tracking route of the target vehicle according to the target global smooth track. The method combines global smoothing and local optimization to perform piecewise fitting on discrete points of the vehicle running track, and can generate a tracking route which is continuous, smooth and attached to the original track.
Description
Technical Field
The present invention relates to the field of autopilot technologies, and in particular, to a method, an apparatus, a device, and a medium for generating a tracking route of an autopilot vehicle.
Background
With the development of automatic driving technology, automatic driving vehicles are receiving a great deal of attention for convenience and safety advantages. The global path planning is the basis of automatic driving, and provides a safe and efficient driving path for vehicles. For an autonomous vehicle to travel safely and stably on a road, the curvature of the tracking path is required to meet the requirements of vehicle dynamics and kinematics. In the case where the road is not provided with high accuracy, a tracking path is generally generated by using discrete sampling points based on high-accuracy positioning.
In the related art, performing polynomial fitting operation on discrete points of an original running track of a vehicle for five times, judging fitting errors, calculating a vehicle control data item based on the fitting errors, and outputting a track after fitting optimization based on the vehicle control data item.
However, the method has a good effect on short-distance tracks (< 200 m), but for long-distance tracks, if the same five-degree polynomial fitting parameters are used for smoothing, the fitting track of a curve path may be distorted (the fitting degree with an actual road is poor), and the trafficability of narrow road traffic cannot be ensured.
Disclosure of Invention
The invention provides a method, a device, equipment and a medium for generating a tracking route of an automatic driving vehicle, which combine global smoothing and local optimization to perform piecewise fitting on discrete points of a running track of the vehicle, can generate a continuous, smooth and original track-fitting tracking route, and is beneficial to improving the transverse stability, running smoothness and narrow road passing capability of the vehicle.
According to an aspect of the present invention, there is provided a method of generating a tracking route of an autonomous vehicle, the method including:
determining a moving track discrete point of a target vehicle, and performing global smoothing on the moving track discrete point to obtain an initial global smooth track;
segmenting the initial global smooth track to obtain at least two candidate segmented smooth tracks, and respectively carrying out local smoothing on moving track discrete points corresponding to the at least two candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks;
performing curvature smoothing on the joint points of every two adjacent reference segment smooth tracks to obtain a target segment smooth track; wherein, every two adjacent target segments have the same curvature;
And determining a target global smooth track according to the target segment smooth track, and determining a target tracking route of the target vehicle according to the target global smooth track.
According to another aspect of the present invention, there is provided a tracking route generating device of an autonomous vehicle, including:
the global smoothing processing module is used for determining the running track discrete points of the target vehicle and carrying out global smoothing processing on the running track discrete points to obtain an initial global smoothing track;
the segmentation smoothing processing module is used for carrying out segmentation processing on the initial global smooth track to obtain at least two candidate segmentation smooth tracks, and carrying out local smoothing processing on moving track discrete points corresponding to the at least two candidate segmentation smooth tracks to obtain at least two reference segmentation smooth tracks;
the curvature smoothing processing module is used for carrying out curvature smoothing processing on the joint points of each two adjacent reference segment smoothing tracks to obtain a target segment smoothing track; wherein, every two adjacent target segments have the same curvature;
and the tracking route determining module is used for determining a target global smooth track according to the target segmentation smooth track and determining a target tracking route of the target vehicle according to the target global smooth track.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of generating a tracking path for an autonomous vehicle according to any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the tracking route generation method of an autonomous vehicle according to any of the embodiments of the present invention when executed.
According to the technical scheme, the running track discrete points of the target vehicle are determined, and global smoothing processing is carried out on the running track discrete points to obtain an initial global smooth track; segmenting the initial global smooth track to obtain at least two candidate segmented smooth tracks, and respectively carrying out local smoothing on the moving track discrete points corresponding to the at least two candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks; performing curvature smoothing on the joint points of every two adjacent reference segment smooth tracks to obtain a target segment smooth track; wherein, every two adjacent target segments have the same curvature; and determining a target global smooth track according to the target segment smooth track, and determining a target tracking route of the target vehicle according to the target global smooth track. According to the technical scheme, the global smoothing and the local optimization are combined, the discrete points of the running track of the vehicle are subjected to piecewise fitting, a continuous, smooth and original track-fitting tracking route can be generated, and the transverse stability, the running smoothness and the narrow road passing capability of the vehicle are improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for generating a tracking path of an autonomous vehicle according to a first embodiment of the present invention;
fig. 2 is a flowchart of a method for generating a tracking route of an autonomous vehicle according to a second embodiment of the present invention;
fig. 3 is a schematic diagram of a method for generating a tracking path of an autonomous vehicle according to a second embodiment of the present invention;
fig. 4 is a schematic structural view of a tracking path generating device for an autonomous vehicle according to a third embodiment of the present invention;
Fig. 5 is a schematic structural view of an electronic device implementing a method for generating a tracking route of an autonomous vehicle according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," "target," and the like in the description and claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for generating a tracking path of an autonomous vehicle according to an embodiment of the present invention, where the method may be performed by a tracking path generating device of an autonomous vehicle, and the tracking path generating device of an autonomous vehicle may be implemented in hardware and/or software, and the tracking path generating device of an autonomous vehicle may be configured in an electronic device with data processing capability. As shown in fig. 1, the method includes:
s110, determining the moving track discrete points of the target vehicle, and performing global smoothing on the moving track discrete points to obtain an initial global smooth track.
The technical scheme of the embodiment is suitable for working in a scene of generating the tracking route based on the discrete sampling points, can be suitable for the situation of having a road high-precision map and not having the road high-precision map, and can be used for carrying out sectional fitting on the discrete points of the running track of the vehicle by combining global smoothing and local optimization, so that the continuous, smooth and original track-fitting tracking route is generated, and the transverse stability, running smoothness and narrow road passing capability of the vehicle are improved.
Wherein the discrete points of the movement track can be used to characterize the tracking position of the target vehicle, and can be determined based on a high-precision map or a high-precision positioning system configured on the target vehicle. Specifically, when the high-precision map is provided, a global path discrete point (such as an apollo global path) corresponding to the target track can be directly generated according to the high-precision map, or a discrete point path of the target track can be generated by using the control points in a segmented manner to serve as a running track discrete point. The target track may be understood as a path along which the target vehicle is to track. When the road high precision is not provided, the discrete points of the running track can be determined according to the positioning data of the target vehicle running on the target track.
By way of example, taking a case without road high precision as an example, when the target vehicle runs on the target track, a series of position points of the target vehicle can be acquired as discrete points of the running track of the target vehicle by a high-precision positioning system configured on the target vehicle according to a preset sampling period. The preset sampling period can be preset according to actual application requirements.
In this embodiment, after determining the moving track discrete points of the target vehicle, global smoothing is performed on the moving track discrete points to obtain an initial global smooth track. The initial global smooth track may be a track line obtained by performing global smoothing processing on discrete points of the running track. For example, a spline interpolation method may be used to globally smooth discrete points of the running track, where the method may generate a smooth curve by connecting the discrete sample points. Specifically, a polynomial P may be used n (x)＝a n x n +a n-1 x n-1 +…+a 1 x+a 0 Fitting the discrete points of the running track, and balancing the smoothness and the change rate of the polynomial curvature by adjusting the polynomial coefficient so as to achieve the global smoothing effect, thereby obtaining the initial global smoothing track. Wherein a is 0 ,a 1 …a n-1 ,a n Is a polynomial coefficient; n is a polynomial degree and can be determined by the number N of discrete points of the running track, typically N is less than or equal to N/2, so as to ensure the smoothness of the initial global smooth track.
S120, carrying out segmentation processing on the initial global smooth track to obtain at least two candidate segmented smooth tracks, and carrying out local smoothing processing on the moving track discrete points corresponding to the at least two candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks.
The candidate piecewise smooth track may refer to a track line obtained by performing piecewise processing on the initial global smooth track. The reference piecewise smooth track may refer to a track line obtained by performing local smoothing processing on discrete points of the running track corresponding to the candidate piecewise smooth track.
In this embodiment, in order to be applicable to a long-distance path scenario, after an initial global smooth track is obtained, the initial global smooth track may be subjected to segmentation processing to obtain at least two candidate segmented smooth tracks. Optionally, the segmenting processing is performed on the initial global smooth track to obtain at least two candidate segmented smooth tracks, including: determining the course angle change rate corresponding to the moving track discrete points according to the initial global smooth track; and carrying out segmentation processing on the initial global smooth track according to the course angle change rate to obtain at least two candidate segmented smooth tracks.
Illustratively, assume that an initial global smooth trajectory obtained by global smoothing is denoted as P n (x)＝a n x n +a n-1 x n-1 +…+a 1 x+a 0 First, partial derivatives are obtained for the polynomialSubstituting the course angle corresponding to each running track discrete point into the partial derivative to obtain the partial derivative of each running track discrete point on the course angle, namely representing the course angle change rate corresponding to the running track discrete point. After the course angle change rate corresponding to each running track discrete point is obtained, the initial global smooth track can be subjected to segmentation processing based on a preset segmentation threshold value, and at least two candidate segmented smooth tracks are obtained. The preset segmentation threshold value may be a heading angle change rate reference value preset according to actual application requirements, and may be used as a segmentation basis of the initial global smooth track. It should be noted that, in this embodiment, the number of preset segment thresholds is not specifically limited, where the greater the number of preset segment thresholds, the greater the number of candidate segment smooth tracks obtained after segmentation. When the number of candidate segment smooth tracks is large, the discrete points of the running track corresponding to each candidate segment smooth track are respectively subjected to local smoothing processing, so that the method can be effective The smoothing effect of each candidate segment smoothing track is improved, so that the smoothed track is more attached to the real path, but meanwhile, the calculation force is increased, and the local smoothing efficiency is reduced. Therefore, a proper number of preset segmentation thresholds can be selected according to actual application requirements to segment the initial global smooth track, so that the smooth effect and the smooth efficiency are balanced well.
Specifically, the course angle change rate corresponding to each moving track discrete point is respectively compared with one or more preset segmentation thresholds, and a segmentation result is determined according to the comparison result. For example, assume a total of three preset segmentation thresholds Yt 1 、Yt 2 And Yt 3 Wherein Yt 1 >Yt 2 >Yt 3 Four segmentation ranges can be obtained correspondingly, and the segmentation ranges are respectively: and->And respectively judging which segmentation range the course angle change rate corresponding to each running track discrete point falls in, taking the adjacent running track discrete points corresponding to the course angle change rate belonging to the same segmentation range as target running track discrete points, wherein the initial global smooth track corresponding to the target running track discrete points is the candidate segmentation smooth track, so that the initial global smooth track can be divided into a plurality of candidate segmentation smooth tracks. It can be appreciated that, since the course angle change rates corresponding to the discrete points of the running tracks in the candidate segment smooth track are close to each other, the discrete points of the running tracks in the candidate segment smooth track divided based on the course angle change rates are in the same road scene (e.g. up to or around a curve).
After obtaining at least two candidate segment smooth tracks, the discrete points of the running track corresponding to each candidate segment smooth track can be respectively subjected to local smoothing treatment to obtain at least two reference segment smooth tracks with the same number as the candidate segment smooth tracks, so that different road conditions can be adapted, and the scene applicability and flexibility of the scheme are improved. The local smoothing process may refer to the global smoothing process, and will not be described herein.
S130, carrying out curvature smoothing processing on the joint points of each two adjacent reference segment smooth tracks to obtain the target segment smooth track.
The target segment smooth trajectory may refer to a trajectory obtained by performing curvature smoothing on the engagement points of each two adjacent reference segment smooth trajectories. Every two adjacent target segment smooth trajectories have the same curvature at the junction points. It should be noted that, after the above local smoothing process, the curvature of the smooth track of the adjacent reference segment at the junction may be different, so that the track smoothness at the junction cannot be ensured.
In this embodiment, in order to ensure smooth transition of the adjacent reference segment smooth trajectories at the junction, after obtaining at least two reference segment smooth trajectories, curvature smoothing processing is required to be performed on the junction points of each two adjacent reference segment smooth trajectories to obtain the target segment smooth trajectories, so that the curvatures of the adjacent reference segment smooth trajectories at the junction points are equal. For example, when curvature smoothing is performed, one of the adjacent reference segment smooth tracks may be fixed, and the other track may be adjusted by using a gradient descent method until the curvatures of the two reference segment smooth tracks at the junction points are equal.
S140, determining a target global smooth track according to the target segment smooth track, and determining a target tracking route of the target vehicle according to the target global smooth track.
In this embodiment, after the target segment smooth track is obtained, each target segment smooth track may be sequentially connected according to the time sequence, so as to obtain a complete target global smooth track, and the target global smooth track is determined as the target tracking route of the target vehicle.
According to the technical scheme, the running track discrete points of the target vehicle are determined, and global smoothing processing is carried out on the running track discrete points to obtain an initial global smooth track; segmenting the initial global smooth track to obtain at least two candidate segmented smooth tracks, and respectively carrying out local smoothing on the moving track discrete points corresponding to the at least two candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks; performing curvature smoothing on the joint points of every two adjacent reference segment smooth tracks to obtain a target segment smooth track; wherein, every two adjacent target segments have the same curvature; and determining a target global smooth track according to the target segment smooth track, and determining a target tracking route of the target vehicle according to the target global smooth track. According to the technical scheme, the global smoothing and the local optimization are combined, the discrete points of the running track of the vehicle are subjected to piecewise fitting, a continuous, smooth and original track-fitting tracking route can be generated, and the transverse stability, the running smoothness and the narrow road passing capability of the vehicle are improved.
In this embodiment, optionally, after determining the target global smooth track according to the target segment smooth track, the method further includes: determining road surface state information corresponding to the moving track discrete points according to the vehicle height information corresponding to the moving track discrete points; the road surface state information comprises a flat road, a pothole and a ramp.
It will be appreciated that if the road surface on which the target track is located is a flat road, the vehicle height corresponding to the discrete points of each moving track should remain stable within a certain range (there may be a slight difference in height due to measurement errors of the sensors). When there is a depression or such a ramp in the road surface where the target track is located, a large height variation is usually produced. Therefore, the road surface state information corresponding to the moving locus discrete points can be determined based on the vehicle height information.
For example, the road surface state information corresponding to the discrete points of the moving track may be determined according to the vehicle height information corresponding to the discrete points of the moving track based on a preset height threshold value. The preset height threshold may be a vehicle height reference value preset according to actual application requirements. Specifically, the preset height threshold may include a first height threshold and a second height threshold, where the first height threshold is greater than the height of the vehicle on the flat road and may be used as a basis for determining the ramp; the second height threshold value is smaller than the height of the vehicle on the flat road, and can be used as a basis for judging the pothole. If the vehicle height information corresponding to the moving track discrete points is larger than the first height threshold value, determining that the road surface state information corresponding to the moving track discrete points is a ramp; if the vehicle height information corresponding to the moving track discrete points is smaller than the second height threshold value, determining that the road surface state information corresponding to the moving track discrete points is a pothole; otherwise, the road surface state information corresponding to the moving track discrete point can be determined to be a flat road.
Correspondingly, determining the target tracking route of the target vehicle according to the target global smooth track comprises the following steps: and determining a target tracking route of the target vehicle according to the target global smooth track and the road surface state information.
In this embodiment, the road surface state information may be added as attribute information of discrete points of each running track in the target global smooth track at a corresponding position of the target global smooth track, so as to obtain a target tracking route carrying the road surface state information, so that the target vehicle can perform corresponding speed limiting operation based on the road surface state information in the target tracking route in the subsequent tracking process, thereby effectively avoiding serious jolt of the vehicle, and further contributing to improving the running smoothness of the vehicle.
In this embodiment, optionally, after determining the discrete point of the movement track of the target vehicle, the method further includes: determining abnormal track discrete points from the running track discrete points according to the vehicle running information corresponding to the running track discrete points; wherein the vehicle operation information includes speed and acceleration; removing the abnormal track discrete points from the running track discrete points to obtain updated running track discrete points; correspondingly, performing global smoothing on the discrete points of the running track to obtain an initial global smoothed track, including: and carrying out global smoothing treatment on the updated running track discrete points to obtain an initial global smooth track.
It should be noted that, due to a measurement error of the sensor or the positioning system, an abnormal track discrete point deviating from a real scene may exist in the running track discrete point, so that a subsequent smoothing process is affected, and accuracy of the target tracking route is further affected.
In this embodiment, in order to improve the accuracy of the moving track discrete points, after determining the moving track discrete points of the target vehicle, further processing is required to be performed on the moving track discrete points, and abnormal track discrete points are removed from the moving track discrete points. Firstly, vehicle running information (including speed, acceleration and the like) corresponding to discrete points of each running track can be obtained through a sensor pre-installed on a target vehicle. And then determining a quasi-stationary point (a discrete point close to a stationary state) and a distance abrupt change point from the moving track discrete points according to the vehicle moving information corresponding to the moving track discrete points and a preset vehicle moving parameter threshold value as abnormal track discrete points.
And then, determining radian mutation points from the moving track discrete points by adopting an equal radian sampling method as abnormal track discrete points, wherein the method can ensure the dispersibility of the points and does not lose representativeness. Specifically, a sampling starting point P0 in discrete points of the running track is picked up, a point P1 farthest from the P0 is searched for in an iteration mode, a point P2 farthest from the P1 is searched for in an iteration mode, a circle C is fitted by using the P0, the P1 and the P2, the center C0 of a sampling arc of the circle C is determined, and the discrete points of the running track are screened according to a preset radian threshold value At. If the radian change of the moving track discrete points is smaller than At, judging that the moving track discrete points are abnormal track discrete points; otherwise, judging the normal track discrete point.
After the abnormal track discrete points are determined, the abnormal track discrete points can be removed from the running track discrete points to obtain updated running track discrete points, so that the updated running track discrete points can be subjected to global smoothing processing to obtain initial global smooth tracks.
According to the scheme, through the arrangement, abnormal track discrete points are eliminated by carrying out abnormal track discrete points on the running track discrete points, the accuracy of the running track discrete points can be effectively improved, and the accuracy of a target tracking route can be improved.
Example two
Fig. 2 is a flowchart of a method for generating a tracking path of an autonomous vehicle according to a second embodiment of the present invention, which is optimized based on the above embodiment.
As shown in fig. 2, the method of this embodiment specifically includes the following steps:
s210, determining the moving track discrete points of the target vehicle, and performing global smoothing on the moving track discrete points to obtain an initial global smooth track.
S220, carrying out segmentation processing on the initial global smooth track to obtain at least two candidate segmented smooth tracks, and carrying out local smoothing processing on the moving track discrete points corresponding to the at least two candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks.
S230, curvature smoothing is carried out on the joint points of every two adjacent reference segment smooth tracks, and the target segment smooth track is obtained.
Wherein the smooth trajectories of each two adjacent target segments have the same curvature at the junction points.
S240, determining a target global smooth track according to the target segment smooth track.
S250, determining road surface state information corresponding to the discrete points of the running track according to the vehicle height information corresponding to the discrete points of the running track.
The road surface state information comprises a flat road, a pothole and a ramp. In addition, the specific implementation of S210 to S250 may refer to the first embodiment, and will not be described herein.
S260, determining road type information corresponding to the moving track discrete points according to the vehicle posture information corresponding to the moving track discrete points.
Wherein the road type information includes straight roads and curves. The vehicle attitude information may include heading and pitch angles. In this embodiment, first, current vehicle posture change information corresponding to a current running track discrete point may be determined according to current vehicle posture information corresponding to a current running track discrete point and previous vehicle posture information corresponding to a previous running track discrete point, then, the current vehicle posture change information is compared with a preset posture change threshold value, and road type information corresponding to the running track discrete point is determined based on a comparison result. The preset gesture change threshold may be a reference value of vehicle gesture change information preset according to actual application requirements. Specifically, the preset attitude threshold may include a preset heading angle change threshold and a preset pitch angle change threshold. Taking a preset course angle change threshold value as an example, if course angle change information in the current vehicle posture change information is larger than the preset course angle change threshold value, determining that the current running track discrete point is in a curve; otherwise, determining that the current running track discrete point is in a straight path.
S270, determining road information corresponding to the discrete points of the running track according to the road surface state information and the road type information.
In this embodiment, after obtaining the road surface state information and the road type information corresponding to the discrete points of the running track, the road surface state information and the road type information may be integrated to obtain the road information corresponding to the discrete points of the running track.
S280, determining a target tracking route of the target vehicle according to the target global smooth track and the road information.
In this embodiment, the road information may be added as attribute information of discrete points of each running track in the target global smooth track at a corresponding position of the target global smooth track, so as to obtain a target tracking route carrying the road information, so that the target vehicle can perform corresponding speed limiting operation based on the road information in the target tracking route in the subsequent tracking process, thereby effectively avoiding serious jolt of the vehicle, improving adaptability of the vehicle to different road scenes (road types), and being beneficial to further improving running smoothness of the vehicle.
Fig. 3 is a schematic diagram of a method for generating a tracking path of an autopilot vehicle according to a second embodiment of the present invention. As shown in fig. 3, data preprocessing is performed on the moving track discrete points of the target vehicle, abnormal track discrete points are removed from the moving track discrete points, global smoothing is performed on the preprocessed moving track discrete points to obtain an initial global smooth track, segmentation processing is performed on the initial global smooth track to obtain at least two candidate segmented smooth tracks, local smoothing is performed on the moving track discrete points corresponding to the candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks, curvature smoothing is performed on the engagement points of adjacent reference segmented smooth tracks to obtain target segmented smooth tracks, and each target segmented smooth track is connected into the target global smooth track in time sequence. And meanwhile, carrying out gesture analysis on the preprocessed running track discrete points, determining corresponding road surface state information and road type information, and determining the road information according to the road surface state information and the road type information. And finally, the road information is used as attribute information of the discrete points of the running track and is added to the global smooth track of the target, so that the target tracking route marked with the road information is obtained.
According to the technical scheme, after the target global smooth track is determined according to the target segmented smooth track, road surface state information corresponding to the moving track discrete points is determined according to the vehicle height information corresponding to the moving track discrete points; the road surface state information comprises a flat road, a hollow and a ramp; determining road type information corresponding to the moving track discrete points according to the vehicle posture information corresponding to the moving track discrete points; the road type information comprises straight roads and curved roads; determining road information corresponding to the discrete points of the running track according to the road surface state information and the road type information; and determining a target tracking route of the target vehicle according to the target global smooth track and the road information. According to the technical scheme, the global smoothing and the local optimization are combined to perform segment fitting on discrete points of the running track of the vehicle, so that a continuous, smooth and attached tracking route of an original track can be generated, the transverse stability, the running smoothness and the narrow road passing capability of the vehicle can be improved, the road information can be added into the target tracking route, the vehicle is effectively prevented from being severely jolted, the adaptability of the vehicle to different road scenes is improved, and the running smoothness of the vehicle is further improved.
Example III
Fig. 4 is a schematic structural diagram of a tracking route generating device for an automatic driving vehicle according to a third embodiment of the present invention, where the device may execute the tracking route generating method for an automatic driving vehicle according to any embodiment of the present invention, and the device has functional modules and beneficial effects corresponding to the executing method. As shown in fig. 4, the apparatus includes:
the global smoothing processing module 310 is configured to determine a running track discrete point of the target vehicle, and perform global smoothing processing on the running track discrete point to obtain an initial global smooth track;
the segment smoothing processing module 320 is configured to segment the initial global smoothing track to obtain at least two candidate segment smoothing tracks, and locally smooth the discrete points of the running track corresponding to the at least two candidate segment smoothing tracks to obtain at least two reference segment smoothing tracks;
the curvature smoothing module 330 is configured to perform curvature smoothing on the engagement points of each two adjacent reference segment smooth trajectories to obtain a target segment smooth trajectory; wherein, every two adjacent target segment smooth trajectories have the same curvature at the junction point;
the tracking route determining module 340 is configured to determine a target global smooth track according to the target segment smooth track, and determine a target tracking route of the target vehicle according to the target global smooth track.
Optionally, the segment smoothing module 320 is specifically configured to:
determining the course angle change rate corresponding to the moving track discrete points according to the initial global smooth track;
and carrying out segmentation processing on the initial global smooth track according to the course angle change rate to obtain at least two candidate segmented smooth tracks.
Optionally, the apparatus further includes:
the road surface state information determining module is used for determining road surface state information corresponding to the moving track discrete points according to the vehicle height information corresponding to the moving track discrete points after determining a target global smooth track according to the target segmented smooth track; wherein the road surface state information includes a flat road, a pothole, and a ramp.
Optionally, the tracking route determining module 340 is configured to:
and determining a target tracking route of the target vehicle according to the target global smooth track and the road surface state information.
Optionally, the apparatus further includes:
the road type information determining module is used for determining road type information corresponding to the moving track discrete points according to the vehicle posture information corresponding to the moving track discrete points after determining a target global smooth track according to the target segmented smooth track; wherein the road type information includes straight roads and curves.
Optionally, the tracking route determining module 340 is further configured to:
determining road information corresponding to the discrete points of the running track according to the road surface state information and the road type information;
and determining a target tracking route of the target vehicle according to the target global smooth track and the road information.
Optionally, the apparatus further includes:
the abnormal track discrete point determining module is used for determining abnormal track discrete points from the moving track discrete points according to the vehicle running information corresponding to the moving track discrete points after determining the moving track discrete points of the target vehicle; wherein the vehicle operation information includes a speed and an acceleration;
the moving track discrete point updating module is used for removing the abnormal track discrete points from the moving track discrete points to obtain updated moving track discrete points;
accordingly, the global smoothing module 310 is configured to:
and carrying out global smoothing treatment on the updated running track discrete points to obtain an initial global smooth track. .
The device for generating the tracking route of the automatic driving vehicle provided by the embodiment of the invention can execute the method for generating the tracking route of the automatic driving vehicle provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the respective methods and processes described above, such as a tracking route generation method of an autonomous vehicle.
In some embodiments, the method of generating the tracking route of the autonomous vehicle may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the above-described tracking route generation method of the autonomous vehicle may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of generating the tracking route of the autonomous vehicle in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems-on-chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of generating a tracking path for an autonomous vehicle, the method comprising:
determining a moving track discrete point of a target vehicle, and performing global smoothing on the moving track discrete point to obtain an initial global smooth track;
segmenting the initial global smooth track to obtain at least two candidate segmented smooth tracks, and respectively carrying out local smoothing on moving track discrete points corresponding to the at least two candidate segmented smooth tracks to obtain at least two reference segmented smooth tracks;
Performing curvature smoothing on the joint points of every two adjacent reference segment smooth tracks to obtain a target segment smooth track; wherein, every two adjacent target segment smooth trajectories have the same curvature at the junction point;
and determining a target global smooth track according to the target segment smooth track, and determining a target tracking route of the target vehicle according to the target global smooth track.
2. The method of claim 1, wherein segmenting the initial global smooth trajectory results in at least two candidate segmented smooth trajectories, comprising:
determining the course angle change rate corresponding to the moving track discrete points according to the initial global smooth track;
and carrying out segmentation processing on the initial global smooth track according to the course angle change rate to obtain at least two candidate segmented smooth tracks.
3. The method of claim 1, wherein after determining a target global smoothed trajectory from the target segmented smoothed trajectory, the method further comprises:
determining pavement state information corresponding to the moving track discrete points according to the vehicle height information corresponding to the moving track discrete points; wherein the road surface state information includes a flat road, a pothole, and a ramp.
4. The method of claim 3, wherein determining the target tracking route of the target vehicle from the target global smooth trajectory comprises:
and determining a target tracking route of the target vehicle according to the target global smooth track and the road surface state information.
5. A method according to claim 3, wherein after determining a target global smoothed trajectory from the target segmented smoothed trajectory, the method further comprises:
determining road type information corresponding to the moving track discrete points according to the vehicle posture information corresponding to the moving track discrete points; wherein the road type information includes straight roads and curves.
6. The method of claim 5, wherein determining the target tracking route of the target vehicle from the target global smooth trajectory comprises:
determining road information corresponding to the discrete points of the running track according to the road surface state information and the road type information;
and determining a target tracking route of the target vehicle according to the target global smooth track and the road information.
7. The method of any one of claims 1-6, wherein after determining the discrete points of the trajectory of the target vehicle, the method further comprises:
Determining abnormal track discrete points from the running track discrete points according to the vehicle running information corresponding to the running track discrete points; wherein the vehicle operation information includes a speed and an acceleration;
removing the abnormal track discrete points from the running track discrete points to obtain updated running track discrete points;
correspondingly, performing global smoothing on the moving track discrete points to obtain an initial global smoothed track, including:
and carrying out global smoothing treatment on the updated running track discrete points to obtain an initial global smooth track.
8. A tracking route generation device of an autonomous vehicle, characterized by comprising:
the global smoothing processing module is used for determining the running track discrete points of the target vehicle and carrying out global smoothing processing on the running track discrete points to obtain an initial global smoothing track;
the segmentation smoothing processing module is used for carrying out segmentation processing on the initial global smooth track to obtain at least two candidate segmentation smooth tracks, and carrying out local smoothing processing on moving track discrete points corresponding to the at least two candidate segmentation smooth tracks to obtain at least two reference segmentation smooth tracks;
The curvature smoothing processing module is used for carrying out curvature smoothing processing on the joint points of each two adjacent reference segment smoothing tracks to obtain a target segment smoothing track; wherein, every two adjacent target segments have the same curvature;
and the tracking route determining module is used for determining a target global smooth track according to the target segmentation smooth track and determining a target tracking route of the target vehicle according to the target global smooth track.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of generating a tracking path of an autonomous vehicle according to any one of claims 1 to 7.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the method of generating a tracking route for an autonomous vehicle according to any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311843700.2A CN117804480A (en) | 2023-12-28 | 2023-12-28 | Method, device, equipment and medium for generating tracking route of automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311843700.2A CN117804480A (en) | 2023-12-28 | 2023-12-28 | Method, device, equipment and medium for generating tracking route of automatic driving vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117804480A true CN117804480A (en) | 2024-04-02 |
Family
ID=90425019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311843700.2A Pending CN117804480A (en) | 2023-12-28 | 2023-12-28 | Method, device, equipment and medium for generating tracking route of automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117804480A (en) |
-
2023
- 2023-12-28 CN CN202311843700.2A patent/CN117804480A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113682318B (en) | Vehicle running control method and device | |
| CN114987546A (en) | Training method, device and equipment of trajectory prediction model and storage medium | |
| CN114771572A (en) | Automatic driving track prediction method, device, equipment and storage medium | |
| CN114987497B (en) | Method and device for fitting backward lane lines, electronic equipment and storage medium | |
| CN113978465A (en) | Lane-changing track planning method, device, equipment and storage medium | |
| CN116499487B (en) | Vehicle path planning method, device, equipment and medium | |
| CN117261880A (en) | Vehicle control method, device, equipment and storage medium | |
| CN117168488A (en) | Vehicle path planning method, device, equipment and medium | |
| CN114919661B (en) | Parking control method, device, equipment and storage medium | |
| CN114954532A (en) | Lane line determination method, device, equipment and storage medium | |
| CN117804480A (en) | Method, device, equipment and medium for generating tracking route of automatic driving vehicle | |
| CN115937449A (en) | High-precision map generation method and device, electronic equipment and storage medium | |
| CN114842305A (en) | Depth prediction model training method, depth prediction method and related device | |
| CN114771518B (en) | Lane center guide wire generation method and device, electronic equipment and medium | |
| CN117589188B (en) | Driving path planning method, driving path planning device, electronic equipment and storage medium | |
| CN114694138B (en) | Road surface detection method, device and equipment applied to intelligent driving | |
| CN115586773B (en) | Path planning method, device, equipment and medium for mobile robot | |
| CN114049615B (en) | Traffic object fusion association method and device in driving environment and edge computing equipment | |
| CN113479198B (en) | Unmanned vehicle control method and device | |
| CN117494043A (en) | Target motion trail prediction method and device, electronic equipment and medium | |
| CN116483085A (en) | Planning track determining method, device, equipment and storage medium | |
| CN118010049A (en) | Track planning method, track planning device, electronic equipment and storage medium | |
| CN116934779A (en) | Laser point cloud segmentation method and device, electronic equipment and storage medium | |
| CN116700065A (en) | Control method and device of unmanned equipment, electronic equipment and storage medium | |
| CN116168081A (en) | Traffic signal lamp determining method, angle prediction model training method and device |
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 |