CN114264307A - Route generation method, apparatus, vehicle and storage medium - Google Patents
Route generation method, apparatus, vehicle and storage medium Download PDFInfo
- Publication number
- CN114264307A CN114264307A CN202111537656.3A CN202111537656A CN114264307A CN 114264307 A CN114264307 A CN 114264307A CN 202111537656 A CN202111537656 A CN 202111537656A CN 114264307 A CN114264307 A CN 114264307A
- Authority
- CN
- China
- Prior art keywords
- path
- sampling points
- target
- cost
- road
- 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 45
- 238000005070 sampling Methods 0.000 claims abstract description 170
- 238000001914 filtration Methods 0.000 claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 33
- 238000009499 grossing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000000739 chaotic effect Effects 0.000 description 3
- 230000009191 jumping Effects 0.000 description 3
- 230000000670 limiting effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Abstract
The application discloses a path generation method, a path generation device, a vehicle and a computer storage medium, wherein the path generation method comprises the following steps: the method comprises the steps of obtaining road information, wherein the road information comprises a reference path and a road boundary, sampling in the road boundary along the reference path to obtain a plurality of sampling points, filtering the sampling points according to vehicle parameters and a preset filtering algorithm to obtain target sampling points, evaluating the target sampling points according to a cost function to generate a target path, and determining the cost function according to the reference path and the road boundary. According to the path generation method, the sampling points are obtained by sampling the road information, filtering processing is carried out, the sampling points are evaluated by the cost function to obtain the path points serving as the target path, and the path points are connected to obtain the target path, so that the safe and reliable target track can be quickly obtained, and automatic driving is realized.
Description
Technical Field
The present application relates to the field of transportation, and in particular, to a route generation method, a route generation device, a vehicle, and a computer-readable storage medium.
Background
The automatic driving technology relies on various modules to plan a trajectory so that a vehicle can be automatically driven along the planned trajectory. However, generally, the process of planning a trajectory is complex, so that the time for planning the trajectory is long, and if a complex scene in a chaotic environment is encountered, it is easy to make it difficult to quickly implement the planned trajectory. Therefore, how to rapidly and safely realize the planning trajectory becomes a problem to be solved urgently.
Disclosure of Invention
In view of the above, the present application provides a path generation method, a path generation device, a vehicle and a computer-readable storage medium.
The application provides a path generation method, which comprises the following steps:
acquiring road information, wherein the road information comprises a reference path and a road boundary;
sampling in the road boundary along a reference path to obtain a plurality of sampling points;
filtering the sampling points according to vehicle parameters and a preset filtering algorithm to obtain target sampling points; and
and evaluating the target sampling points according to a cost function to generate a target path, wherein the cost function is determined according to the reference path and the road boundary.
In some embodiments, the filtering the sampling points according to the vehicle parameters and a preset filtering algorithm to obtain target sampling points includes:
performing collision detection on the sampling points according to the vehicle parameters, and removing the sampling points on the obstacle area to obtain preliminary sampling points;
and filtering the preliminary sampling points through the preset filtering algorithm to obtain target sampling points.
In some embodiments, the cost function includes a reference path closeness cost, a road smoothing cost, a path decision jump cost, and an obstacle closeness cost, the reference path closeness cost and the path decision jump cost being determined based on coordinates of the target sampling points and the reference path, the road smoothing cost being determined based on an interval between adjacent target sampling points along a reference path direction, the path decision jump cost being determined based on coordinates of the target sampling points, the vehicle parameters, and obstacles within the road boundary.
In some embodiments, the evaluating the target sampling points according to the cost function to generate the target path includes:
calculating a cost value of each target sampling point through the cost function;
comparing the cost values of the target sampling points in a vertical direction along a reference path;
taking the target sampling point with the minimum cost value as a path point;
and sequentially connecting the path points along a reference path direction to generate the target path.
In some embodiments, determining coordinate values of the target sampling point and the obstacle region;
and calculating the cost value of each target sampling point according to the target sampling point, the coordinate value of the obstacle area and the cost function.
In some embodiments, the reference path is a road centerline.
In some embodiments, the path generation method further comprises:
and generating a safe driving corridor according to the target path.
The present application also provides a path generation apparatus, including:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring road information which comprises a reference path and a road boundary;
the sampling module is used for sampling in the road boundary along a reference path to obtain a plurality of sampling points;
the processing module is used for filtering the sampling points according to vehicle parameters and a preset filtering algorithm to obtain target sampling points;
and the generating module is used for evaluating the target sampling points according to a cost function to generate a target path, and the cost function is generated according to the reference path and the road boundary.
The present application also provides a vehicle comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, implements the path generation method described above.
The present application also provides a non-transitory computer-readable storage medium containing a computer program which, when executed by one or more processors, implements the path generation method described above.
According to the path generation method and device, the vehicle and the computer readable storage medium, a plurality of sampling points are generated in a road boundary, screening and filtering are performed to obtain target sampling points, each target sampling point is evaluated through a cost function, the most suitable target sampling point is selected to serve as a path point, and finally the path points are sequentially connected along a reference path direction to obtain a target path. Therefore, the vehicle can quickly obtain a reliable and safe target track according to the road information even in a chaotic scene, and automatic driving is realized.
Additional aspects and advantages of embodiments of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart diagram of a path generation method of an embodiment of the invention;
FIG. 2 is a schematic diagram of a path generation apparatus according to an embodiment of the present invention;
3-5 are parking scenario diagrams of a path generation method according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart diagram of a path generation method according to an embodiment of the present invention;
FIG. 7 is a parking scenario diagram of a path generation method according to an embodiment of the present invention;
FIG. 8 is a further flow chart diagram of a path generation method according to an embodiment of the invention;
fig. 9 is a further flowchart illustrating a path generation method according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the embodiments of the present application, and are not to be construed as limiting the embodiments of the present application.
Referring to fig. 1, the present application provides a path generating method, including:
01: acquiring road information, wherein the road information comprises a reference path and a road boundary;
02: sampling in a road boundary along a reference path to obtain a plurality of sampling points;
03: filtering the sampling points according to the vehicle parameters and a preset filtering algorithm to obtain target sampling points;
04: and evaluating the target sampling points according to the cost function to generate a target path.
Correspondingly, referring to fig. 2, the present application also provides a path generating device 100, and the path generating method of the present application may be implemented by the path generating device 100.
The path generation apparatus 100 includes an acquisition module 110, a sampling module 120, a processing module 130, and a generation module 140. Step 01 may be implemented by the obtaining module 110, step 02 may be implemented by the sampling module 120, step 03 may be implemented by the processing module 130, and step 04 may be implemented by the generating module 140.
In other words, the obtaining module 110 is configured to obtain road information, where the road information includes a reference path and a road boundary. The sampling module 120 is configured to sample within a road boundary along a reference path to obtain a plurality of sampling points. The processing module 130 is configured to filter the sampling points according to the vehicle parameters and a preset filtering algorithm to obtain target sampling points. The generating module 140 is configured to evaluate the target sampling points according to the cost function to generate a target path.
The embodiment of the application also provides a vehicle. The vehicle includes a memory and a processor. The processor is used for obtaining road information, the road information comprises a reference path and a road boundary, sampling is carried out in the road boundary along the reference path to obtain a plurality of sampling points, the sampling points are filtered according to vehicle parameters and a preset filtering algorithm to obtain target sampling points, and the target sampling points are evaluated according to a cost function to generate a target path.
The vehicle may be, but is not limited to, a vehicle (e.g., a pure electric vehicle, a hybrid electric vehicle, an extended range electric vehicle, a fuel vehicle), a flying automobile, and the like. For convenience of description, the vehicle will be described by taking a vehicle as an example.
In the path generation method, the path generation device and the vehicle, a plurality of sampling points are generated in a road boundary, screening and filtering are performed to obtain target sampling points, each target sampling point is evaluated through a cost function, so that the most suitable target sampling point is selected as a path point, and finally the path points are sequentially connected along a reference path direction to obtain a target path. Therefore, the vehicle can quickly obtain a reliable and safe target track according to the road information even in a chaotic scene, and automatic driving is realized.
The path generation method of the present application can be applied to, but is not limited to, parking scenarios. For example, please refer to fig. 3-5, fig. 3-5 are schematic views of scenes generated when a vehicle is parked out of a garage and a path is planned, where fig. 3 is a schematic view of a scene in which a plurality of sampling points are obtained by sampling along a reference path in a road boundary during parking, fig. 4 is a schematic view of a scene in which target sampling points are obtained by filtering the sampling points during parking, and fig. 5 is a schematic view of a scene in which the target sampling points are evaluated according to a cost function to generate a parking path (i.e., a target path).
The reference path may be a centerline of the road. The center line of the road can be directly acquired through the high-precision map, and the left and right boundary information of the road can be acquired while the center line of the road is acquired. Of course, it is understood that in other embodiments, if the road includes multiple lanes, the center line of the road may be the center line of a certain lane, and the boundary of the road may be the boundary line of a certain lane.
Further, a Frenet coordinate system is established with reference to a reference path, wherein the reference path direction is a vertical axis(s) and a direction perpendicular to the reference path direction is a horizontal axis (l). It will be appreciated that the transverse axis, the longitudinal axis, are perpendicular to each other and the reference line is parallel to the lane line, making it easy to determine the distance the vehicle is off the center of the lane and the distance the vehicle travels along the lane line. Therefore, the expression mode can ignore the influence of the curvature of the road, so that the expression mode is more concise and intuitive, and each position on the central line and the left and right boundaries corresponds to one coordinate, thereby being convenient for calculation. Meanwhile, in order to save the computation amount, discretization processing can be carried out on the road, sampling is carried out according to the preset path length along the directions of a transverse axis and a longitudinal axis respectively, and uniformly distributed sampling points are selected, so that the sampling points can be distributed in the road boundary in an array mode, and the coordinates of the sampling points are(s)i，li). The preset path length is not limited and can be selected according to actual conditions.
Furthermore, filtering the sampling points according to the vehicle parameters and a preset filtering algorithm, and filtering the sampling points on the obstacle area, the sampling points outside the reference path in the straight line section and the like to obtain target sampling points. It can be understood that, when sampling a road in a road boundary, sampling points are distributed in the road boundary, and in the driving process of a vehicle, obstacles such as other vehicles may exist in the road, and the vehicle cannot pass through an obstacle area, so that the sampling points at the obstacle area and other vehicles which do not pass through the area need to be removed to obtain target sampling points, and the processing amount of a subsequent generated target path can be reduced, thereby increasing the processing speed.
In some embodiments, the cost function includes a reference path closeness cost, a road smoothing cost, a path decision jump cost, and an obstacle closeness cost.
The reference path closing cost is used for measuring the degree of the candidate path closing to the reference path, the larger the value of the reference path closing cost is, the farther the candidate path is from the reference path, and the smaller the value of the reference path closing cost is, the closer the candidate path is to the reference path is. The road smoothing cost is used for measuring the smooth degree of the path, the larger the value of the road smoothing cost is, the smoother the path is, and the smaller the value of the road smoothing cost is, the smoother the path is. The path decision jump cost is used for measuring the degree of the candidate path having larger path decision jump caused by the sudden appearance of the obstacle. The larger the value of the path decision jump cost is, the larger the jumping degree of the candidate path is, and the safer the vehicle runs, and the smaller the value of the path decision jump cost is, the smaller the jumping degree of the candidate path is, and the safer the vehicle runs. The obstacle approach cost is used for measuring the degree of the road approaching to the obstacle, the larger the value of the obstacle approach cost is, the closer the candidate path and the obstacle is, the smaller the value of the obstacle approach cost is, and the farther the candidate path and the obstacle are.
The reference path approaching cost and the path decision hopping cost are determined according to the coordinates of the target sampling points and the reference path, the road smoothing cost is determined according to the interval between the adjacent target sampling points along the direction of the reference path, and the path decision hopping cost is determined according to the coordinates of the target sampling points, vehicle parameters and obstacles in the road boundary.
The method comprises the steps of generating a path, and generating a path, wherein the path is divided into a plurality of target sampling points according to the target path, and the target sampling points are connected with the path points along the direction of the reference path to obtain the target path.
Therefore, the target sampling points serving as the path points can be screened out from the target sampling points through the cost function, the path points can be connected to obtain the target path, and the obtained target path can meet the requirements on safety, smoothness, accuracy and consistency.
Preferably, referring to fig. 6 and 7, in some embodiments, step 03 includes:
032: performing collision detection on the sampling points according to the vehicle parameters, and removing the sampling points on the obstacle area to obtain preliminary sampling points;
034: and filtering the preliminary sampling points through a preset filtering algorithm to obtain target sampling points.
Referring further to fig. 2, in some embodiments, step 032 can be implemented by processing module 130. Or, the processing module 130 is configured to perform collision detection on the sampling points according to the vehicle parameters, remove the sampling points located on the obstacle to obtain preliminary sampling points, and filter the preliminary sampling points through a preset filtering algorithm to obtain target sampling points.
In some embodiments, the processor is configured to perform collision detection on the sampling points according to vehicle parameters, remove the sampling points located on the obstacle to obtain preliminary sampling points, and filter the preliminary sampling points through a preset filtering algorithm to obtain target sampling points.
The vehicle parameter may be a vehicle contour related parameter, such as a vehicle width, a vehicle length, a vehicle radius, and the like. The obstacle region is a region where an obstacle exists in a road boundary. The obstacles may be either static (e.g., barricades) or dynamic (e.g., moving vehicles).
The preset filtering algorithm may be a Douglas-pock (Douglas-Peucker) algorithm, that is, in the present application, the Douglas-pock algorithm may be adopted to perform filtering processing on the preliminary sampling point, so as to obtain the target sampling point. Those skilled in the art will appreciate that the douglas-pock algorithm, also known as the larmer-douglas-pock algorithm, the iterative adaptation point algorithm, the split and merge algorithm, is an algorithm that approximates a curve as a series of points and reduces the number of points. In the application, partial sampling points in a straight line section in a road can be filtered out through a Douglas-Pock algorithm.
Referring to fig. 7, in some examples, in a scenario where the current vehicle is parked out of the garage, during the path planning process of the current vehicle, sampling is carried out within the boundary of the road in front of the current vehicle to obtain a plurality of arrays of sampling points, collision detection can be carried out on the sampling points according to the width of the current vehicle, so that the front parking area can be set as the collision area and the sampling points (gray sampling points in fig. 7) in the collision area are removed to obtain preliminary sampling points, and further, filtering the preliminary sampling points of the road in the straight line segment by a Douglas-Puck algorithm, thus, the preliminary sampling points outside the reference path (white sampling points in fig. 7) are removed, and only the preliminary sampling points of the reference path in the straight line segment are retained as target sampling points (black sampling points in fig. 7).
Therefore, on one hand, the sampling points are subjected to collision detection according to vehicle parameters, the sampling points on the obstacle regions are removed, and the generated target path can be ensured to be free of obstacles, so that the vehicle is prevented from colliding with the obstacles when running along the target path, and the running safety of the vehicle is ensured.
Preferably, referring to fig. 8, in some embodiments, step 04 further includes:
041: calculating the cost value of each target sampling point through a cost function;
042: comparing cost values of the target sampling points in the vertical direction along the reference path;
043: taking a target sampling point with the minimum cost value as a path point;
044: and sequentially connecting the path points along the reference path direction to generate a target path.
In some embodiments, substeps 042-048 may be implemented by the generation module 140. In other words, the generating module 140 is configured to calculate a cost value of each target sampling point through a cost function, and compare the cost values of the target sampling points along the vertical direction of the reference path; the generating module 140 is further configured to use the target sampling point with the smallest cost value as a path point, and sequentially connect the path points along the reference path direction to generate a target path.
In some embodiments, the processor is configured to calculate a cost value for each target sampling point by a cost function and compare the cost values of the target sampling points along the reference path in the vertical direction; the processor is also used for taking the target sampling point with the minimum cost value as a path point and sequentially connecting the path points along the reference path direction to generate a target path.
The cost function may be represented by the following formula:
ccost＝coffset+csmooth+cconsistent+cobstacle
the first term is reference path approaching cost, the second term is road smoothing cost, the third term is path decision jumping cost, and the fourth term is barrier approaching cost.
Reference path closing cost coffsetAccording to the transverse distance from the target sampling point to the reference path, the target path is close to the reference path as much as possible, and the close cost calculation formula of the reference path is as follows:
wherein liRepresenting the lateral position l of the target sampling point; lmaxThe maximum planned width, generally the half-width of the road; omegaoffsetAnd (4) centering the road for cost weighting.
Road smoothing cost csmoothLarger turns are penalized according to the longitudinal/lateral displacement ratio so that the target path tends to be smooth to ensure comfort of lateral motion. Road smoothing cost csmoothThe calculation formula of (2) is as follows:
sirepresenting the longitudinal position s of the target sampling point; omegasmoothIs a path smoothness cost weight.
Path decision hopping cost cconsistentThe method is used for preventing the candidate path from generating large path decision jump due to the sudden appearance of the obstacle according to the transverse deviation at the same longitudinal position as the last planned path. Path decision hopping cost cconsistentThe calculation formula of (2) is as follows:
wherein li0Is in the last planned path withiLongitudinal deviation corresponding to target sampling points with the same arc length s; omegaconsistentIs a path consistency cost weight.
Proximity cost of obstacle cobstacleAnd punishing the target sampling points close to the barrier according to the distance from the vehicle coverage area to the barrier polygon. Proximity cost of obstacle cobstacleThe calculation formula of (2) is as follows:
wherein d represents the minimum distance between the target sampling point and the barrier polygon; dsadeIs the minimum safe distance; omegaobstacleIs an obstacle cost weight.
Specifically, coordinate values of each target sampling point and an obstacle (if existing) in a Frenet coordinate system are obtained, and then a cost value of each target sampling point is calculated according to the coordinate values of the target sampling point and the obstacle area and a cost function. The coordinate values of the target sampling point and the obstacle area can determine the transverse distance between the target sampling point and the reference path, the transverse distance between the target sampling point and the obstacle area, the transverse distance between adjacent target sampling points and the like, and the transverse distances are substituted into the cost function, so that the size of the cost value of the target sampling point can be obtained.
Further, since the target path includes path points extending along the reference path direction, only one target sampling point can be set as a target path in each column along the reference path vertical direction (horizontal axis direction), and therefore, the cost values of the target sampling points along the reference path vertical direction are compared, the target sampling point with the smallest cost value along the reference path vertical direction is set as the path point of the target path, and finally the path points are sequentially connected along the reference path direction to generate the target path. Therefore, the target path meeting the requirements of safety, smoothness, accuracy and consistency can be obtained through the cost function.
Referring to fig. 9, in some embodiments, the path generating method further includes:
05: and generating a safe driving corridor according to the target path.
In certain embodiments, step 05 may be implemented by the generation module 140, and the generation module 140 may also be configured to generate a safe driving corridor according to the target path.
In some embodiments, the processor is configured to generate a safe driving corridor from the target path.
Therefore, when the vehicle runs along the safe driving corridor, the driving safety of the vehicle can be ensured.
The embodiment of the application also provides a computer readable storage medium. One or more non-transitory computer-readable storage media storing a computer program that, when executed by one or more processors, implements the automated build method of any of the embodiments described above. It will be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiments may be implemented by a computer program instructing relevant software. The program may be stored in a non-volatile computer readable storage medium, which when executed, may include the flows of embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), or the like.
In the description herein, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example" or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. Meanwhile, the description referring to the terms "first", "second", and the like is intended to distinguish the same kind or similar operations, and "first" and "second" have a logical context in some embodiments, and do not necessarily have a logical context in some embodiments, and need to be determined according to actual embodiments, and should not be determined only by a literal meaning.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is to be understood that the above embodiments are exemplary and not to be construed as limiting the present application, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A path generation method, comprising:
acquiring road information, wherein the road information comprises a reference path and a road boundary;
sampling in the road boundary along a reference path to obtain a plurality of sampling points;
filtering the sampling points according to vehicle parameters and a preset filtering algorithm to obtain target sampling points; and
and evaluating the target sampling points according to the cost function to generate a target path.
2. The path generation method according to claim 1, wherein the filtering the sampling points according to the vehicle parameters and a preset filtering algorithm to obtain target sampling points comprises:
performing collision detection on the sampling points according to the vehicle parameters, and removing the sampling points on the obstacle area to obtain preliminary sampling points;
and filtering the preliminary sampling points through the preset filtering algorithm to obtain target sampling points.
3. The path generation method according to claim 1, wherein the cost function includes a reference path closeness cost, a road smoothing cost, a path decision jump cost, and an obstacle closeness cost, the reference path closeness cost and the path decision jump cost being determined based on coordinates of the target sampling points and the reference path, the road smoothing cost being determined based on an interval between adjacent target sampling points in a reference path direction, the path decision jump cost being determined based on coordinates of the target sampling points, the vehicle parameter, and an obstacle within the road boundary.
4. The path generation method of claim 3, wherein evaluating the target sample points according to a cost function to generate the target path comprises:
calculating a cost value of each target sampling point through the cost function;
comparing the cost values of the target sampling points in a vertical direction along a reference path;
taking the target sampling point with the minimum cost value as a path point;
and sequentially connecting the path points along a reference path direction to generate the target path.
5. The path generation method according to claim 4, wherein said calculating a cost value for each of the target sample points by the cost function includes:
determining coordinate values of the target sampling point and the obstacle area;
and calculating the cost value of each target sampling point according to the target sampling point, the coordinates of the obstacle area and the cost function.
6. The path generation method according to claim 1, wherein the reference path is a center line of a road.
7. The path generation method according to claim 1, characterized by further comprising:
and generating a safe driving corridor according to the target path.
8. A path generation apparatus, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring road information which comprises a reference path and a road boundary;
the sampling module is used for sampling in the road boundary along a reference path to obtain a plurality of sampling points;
the processing module is used for filtering the sampling points according to vehicle parameters and a preset filtering algorithm to obtain target sampling points;
and the generating module is used for evaluating the target sampling points according to the cost function so as to generate a target path.
9. A vehicle comprising a memory and a processor, the memory having stored thereon a computer program which, when executed by the processor, implements a path generation method as claimed in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium containing a computer program, wherein the computer program, when executed by one or more processors, implements the path generation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111537656.3A CN114264307A (en) | 2021-12-15 | 2021-12-15 | Route generation method, apparatus, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111537656.3A CN114264307A (en) | 2021-12-15 | 2021-12-15 | Route generation method, apparatus, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114264307A true CN114264307A (en) | 2022-04-01 |
Family
ID=80827397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111537656.3A Pending CN114264307A (en) | 2021-12-15 | 2021-12-15 | Route generation method, apparatus, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114264307A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109521762A (en) * | 2017-09-18 | 2019-03-26 | 百度（美国）有限责任公司 | The smooth road reference line based on 2D constraint smoothing spline for automatic driving vehicle |
| CN109521763A (en) * | 2017-09-18 | 2019-03-26 | 百度（美国）有限责任公司 | The path optimization based on constraint smoothing spline for automatic driving vehicle |
| CN109947090A (en) * | 2017-12-21 | 2019-06-28 | 百度（美国）有限责任公司 | Non- chocking limit for automatic driving vehicle planning |
| KR20190095622A (en) * | 2018-01-26 | 2019-08-16 | 충북대학교 산학협력단 | Method and Apparatus for Planning Obstacle Avoiding Path |
| CN110954122A (en) * | 2019-12-09 | 2020-04-03 | 东风商用车有限公司 | Automatic driving track generation method under high-speed scene |
| US20200249037A1 (en) * | 2017-10-25 | 2020-08-06 | Guangzhou Automobile Group Co., Ltd. | Method and Device for Generating Path of Unmanned Vehicle on Construction Section |
| US20200307568A1 (en) * | 2019-03-29 | 2020-10-01 | Mazda Motor Corporation | Vehicle driving support system |
| CN111898804A (en) * | 2020-07-10 | 2020-11-06 | 东风商用车有限公司 | Road self-adaptive sampling method for local planning |
| WO2021142793A1 (en) * | 2020-01-17 | 2021-07-22 | 华为技术有限公司 | Path planning method and path planning apparatus |
| CN113448335A (en) * | 2021-07-02 | 2021-09-28 | 广州小鹏自动驾驶科技有限公司 | Path planning method and device, vehicle and readable storage medium |
| CN113483776A (en) * | 2021-07-01 | 2021-10-08 | 广州小鹏自动驾驶科技有限公司 | Path planning method and device and automobile |
| CN113759887A (en) * | 2020-06-04 | 2021-12-07 | 北京京东乾石科技有限公司 | Path planning method and device, storage medium and electronic equipment |
-
2021
- 2021-12-15 CN CN202111537656.3A patent/CN114264307A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109521762A (en) * | 2017-09-18 | 2019-03-26 | 百度（美国）有限责任公司 | The smooth road reference line based on 2D constraint smoothing spline for automatic driving vehicle |
| CN109521763A (en) * | 2017-09-18 | 2019-03-26 | 百度（美国）有限责任公司 | The path optimization based on constraint smoothing spline for automatic driving vehicle |
| US20200249037A1 (en) * | 2017-10-25 | 2020-08-06 | Guangzhou Automobile Group Co., Ltd. | Method and Device for Generating Path of Unmanned Vehicle on Construction Section |
| CN109947090A (en) * | 2017-12-21 | 2019-06-28 | 百度（美国）有限责任公司 | Non- chocking limit for automatic driving vehicle planning |
| KR20190095622A (en) * | 2018-01-26 | 2019-08-16 | 충북대학교 산학협력단 | Method and Apparatus for Planning Obstacle Avoiding Path |
| US20200307568A1 (en) * | 2019-03-29 | 2020-10-01 | Mazda Motor Corporation | Vehicle driving support system |
| CN110954122A (en) * | 2019-12-09 | 2020-04-03 | 东风商用车有限公司 | Automatic driving track generation method under high-speed scene |
| WO2021142793A1 (en) * | 2020-01-17 | 2021-07-22 | 华为技术有限公司 | Path planning method and path planning apparatus |
| CN113759887A (en) * | 2020-06-04 | 2021-12-07 | 北京京东乾石科技有限公司 | Path planning method and device, storage medium and electronic equipment |
| CN111898804A (en) * | 2020-07-10 | 2020-11-06 | 东风商用车有限公司 | Road self-adaptive sampling method for local planning |
| CN113483776A (en) * | 2021-07-01 | 2021-10-08 | 广州小鹏自动驾驶科技有限公司 | Path planning method and device and automobile |
| CN113448335A (en) * | 2021-07-02 | 2021-09-28 | 广州小鹏自动驾驶科技有限公司 | Path planning method and device, vehicle and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583151B (en) | Method and device for predicting running track of vehicle | |
| CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
| CN110687539B (en) | Parking space detection method, device, medium and equipment | |
| EP3947083A1 (en) | Extension of autonomous driving functionality to new regions | |
| CN111552284A (en) | Method, device, equipment and medium for planning local path of unmanned vehicle | |
| CN112590775B (en) | Automatic parking method and device, vehicle and storage medium | |
| CN113844451B (en) | Driving device control method and device, electronic device and storage medium | |
| CN114812566B (en) | Method and device for planning driving path of mine vehicle and computer equipment | |
| CN112829747A (en) | Driving behavior decision method and device and storage medium | |
| CN111591288B (en) | Collision detection method and device based on distance transformation graph | |
| CN111959498A (en) | Vertical parking method and device for automatically driving vehicle and vehicle | |
| CN109828573B (en) | Unmanned vehicle control method, device and storage medium | |
| CN113561992B (en) | Automatic driving vehicle track generation method, device, terminal equipment and medium | |
| CN114620071A (en) | Detour trajectory planning method, device, equipment and storage medium | |
| CN115230719A (en) | Driving track planning method and device | |
| CN116476840B (en) | Variable-lane driving method, device, equipment and storage medium | |
| CN111460879B (en) | Neural network operation method using grid generator and device using the same | |
| CN112445221B (en) | Automatic working system and regression method | |
| CN116331264A (en) | Obstacle avoidance path robust planning method and system for unknown obstacle distribution | |
| CN114264307A (en) | Route generation method, apparatus, vehicle and storage medium | |
| CN115097826A (en) | Vehicle turning track planning method and device | |
| CN115092141A (en) | Trajectory planning method and equipment applied to lane change and overtaking of automatic driving vehicle | |
| CN113753038A (en) | Trajectory prediction method and apparatus, electronic device and storage medium | |
| TWI750762B (en) | Hybrid planniing method in autonomous vehicles and system thereof | |
| CN114355921B (en) | Vehicle tracking track generation method and device, electronic equipment and storage medium |
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 |