CN115268463A - Obstacle avoidance path planning method, vehicle and storage medium - Google Patents
Obstacle avoidance path planning method, vehicle and storage medium Download PDFInfo
- Publication number
- CN115268463A CN115268463A CN202211010509.5A CN202211010509A CN115268463A CN 115268463 A CN115268463 A CN 115268463A CN 202211010509 A CN202211010509 A CN 202211010509A CN 115268463 A CN115268463 A CN 115268463A
- Authority
- CN
- China
- Prior art keywords
- path
- obstacle avoidance
- obstacle
- vehicle
- static
- 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
- 230000003068 static effect Effects 0.000 claims abstract description 71
- 238000012216 screening Methods 0.000 claims description 21
- 238000005070 sampling Methods 0.000 claims description 20
- 238000013519 translation Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000002085 persistent effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 241000238097 Callinectes sapidus Species 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides an obstacle avoidance path planning method, a vehicle and a storage medium. The obstacle avoidance path planning method comprises the following steps: acquiring the current pose and the target pose of the vehicle; acquiring an identified static obstacle; generating an initial path containing path points according to the current pose and the target pose of the vehicle; when the generated path point in the initial path intersects with the static obstacle, translating the path point which intersects to enable the path point not to intersect with the static obstacle; and generating an obstacle avoidance path according to the translated path points. The scheme provided by the application can generate a safer obstacle avoidance planning path aiming at the static obstacles on the road, and improves the driving safety.
Description
Technical Field
The present application relates to the field of automatic driving technologies, and in particular, to an obstacle avoidance path planning method, a vehicle, and a storage medium.
Background
With the continuous development of intelligent automobile technology, intelligent automobiles generally have an automatic driving function.
In the automatic driving application scene of urban roads, crossing is a very common scene. In general, various obstacles such as static obstacles including piers and safety islands often existing in the middle of intersections, and obstacles such as water horses, railings, pits existing on roads may exist on roads, and the obstacles cause difficulty in route planning for automatic driving.
Disclosure of Invention
In order to solve or partially solve the problems in the related art, the application provides an obstacle avoidance path planning method, a vehicle and a storage medium, which can generate a safer obstacle avoidance planning path for static obstacles on a road and improve driving safety.
A first aspect of the present application provides an obstacle avoidance path planning method, including:
acquiring the current pose and the target pose of the vehicle;
acquiring an identified static obstacle;
generating an initial path containing path points according to the current pose of the vehicle and the target pose of the vehicle;
when the path point in the generated initial path intersects with the static obstacle, translating the path point which intersects to make no intersection with the static obstacle;
and generating an obstacle avoidance path according to the translated path points.
In one embodiment, the generating an initial path including path points according to the current pose of the host vehicle and the target pose of the host vehicle includes:
and generating an initial path with the current pose of the vehicle as a starting point and the target pose of the vehicle as an end point according to a preset curve, wherein discrete path points in the initial path are obtained by sampling from the initial path according to preset intervals.
In an embodiment, the predetermined curve comprises a bezier curve or a B-spline curve.
In one embodiment, when the path point in the initial path intersects with the static obstacle, translating the path point that intersects so as not to intersect with the static obstacle includes:
when the path point in the initial path intersects with the static obstacle, the path point which intersects is translated in the positive direction or the negative direction along the normal line of the initial path so as to not intersect with the static obstacle.
In an embodiment, the generating an obstacle avoidance path according to the translated path points includes:
generating at least two obstacle avoidance paths according to the path points translating in the positive direction or the negative direction;
determining path costs corresponding to the at least two obstacle avoidance paths;
and comparing the path costs corresponding to the at least two obstacle avoidance paths, and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
In an embodiment, the determining the path cost corresponding to each of the at least two obstacle avoidance paths includes:
and uniformly sampling the at least two obstacle avoidance paths, and determining the path cost corresponding to each of the at least two obstacle avoidance paths according to the sampling result.
In an embodiment, the screening, according to the comparison result, one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path includes:
and screening the obstacle avoidance path with low path cost from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
A second aspect of the present application provides a vehicle comprising:
the pose acquisition module is used for acquiring the current pose of the vehicle and the target pose of the vehicle;
the obstacle identification module is used for acquiring the identified static obstacles;
the initial path module is used for generating an initial path containing path points according to the current pose of the vehicle and the target pose of the vehicle;
the translation module is used for translating the path points which generate the intersection so as not to intersect with the static obstacle when the path points in the generated initial path intersect with the static obstacle;
and the obstacle avoidance path module is used for generating an obstacle avoidance path according to the translated path points.
In one embodiment, when the path point in the initial path intersects with the static obstacle, the translation module translates the path point which intersects in a positive direction or a negative direction along a normal line of the initial path so as not to intersect with the static obstacle.
In one embodiment, the obstacle avoidance path module includes:
the obstacle avoidance path generation submodule is used for generating at least two obstacle avoidance paths according to the path points which are translated in the positive direction or the negative direction;
and the obstacle avoidance path screening submodule is used for determining path costs corresponding to the at least two obstacle avoidance paths, comparing the path costs corresponding to the at least two obstacle avoidance paths, and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to a comparison result.
A third aspect of the present application provides a vehicle comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon executable code, which, when executed by a processor of an electronic device, causes the processor to perform the method as described above.
The technical scheme provided by the application has the following beneficial effects:
after the current pose and the target pose of the vehicle are obtained and the identified static barrier is obtained, an initial path containing path points is generated according to the current pose and the target pose of the vehicle; when the path point in the initial path intersects with the static obstacle, translating the path point which intersects to ensure that the path point does not intersect with the static obstacle; and finally, generating an obstacle avoidance path according to the translated path points. Through the processing, the planned path can be adjusted according to the intersection condition of the path point in the initial path and the static obstacle during path planning, and finally, a smooth collision-free driving path which can reach the target position and does not intersect with the obstacle, namely an obstacle avoidance path, is generated.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
Fig. 1 is a first flowchart of an obstacle avoidance path planning method shown in the present application;
fig. 2 is a second flow chart of the obstacle avoidance path planning method shown in the present application;
fig. 3 is a schematic application framework diagram of the obstacle avoidance path planning method shown in the present application;
fig. 4 is a schematic diagram of path adjustment in the obstacle avoidance path planning method shown in the present application;
FIG. 5 is a schematic illustration of a structure of a vehicle shown in the present application;
fig. 6 is another schematic structural diagram of the vehicle shown in the present application.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are illustrated in the accompanying drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
In the related art, various obstacles such as static obstacles including piers distributed in the middle of an intersection, safety islands, or other objects stationary on a road may exist on a road, and the obstacles may cause difficulty in route planning for automatic driving. The application provides an obstacle avoidance path planning method which can generate a safer obstacle avoidance planning path aiming at static obstacles on a road and improve driving safety.
The technical scheme of the application is described in detail in the following with the accompanying drawings.
Fig. 1 is a first flowchart of an obstacle avoidance path planning method according to the present application. The method may be applied to a vehicle.
Referring to fig. 1, the method includes:
s101, obtaining the current pose of the vehicle and the target pose of the vehicle.
The target pose of the vehicle can be obtained according to the high-precision map information and the navigation information of the vehicle, and the current pose of the vehicle can be obtained according to the positioning information of the vehicle.
S102, acquiring the identified static obstacle.
The application can utilize the identification technology in the related art to identify various obstacles on the road, including dynamic obstacles, static obstacles and the like, from the images or videos collected by the sensing module, wherein the static obstacles include, for example, piers, safety islands, water horses, railings, pits (also called negative obstacles) and the like.
S103, generating an initial path containing path points according to the current pose of the vehicle and the target pose of the vehicle.
The method may include generating an initial path with the current pose of the vehicle as a starting point and the target pose of the vehicle as an end point according to a preset curve, and sampling from the initial path at preset intervals to obtain discrete path points in the initial path. Wherein the predetermined curve may comprise a bezier curve or a B-spline curve.
And S104, when the path point in the generated initial path intersects with the static obstacle, translating the intersected path point to ensure that the intersected path point does not intersect with the static obstacle.
When the path point in the initial path intersects with the static obstacle, the path point which intersects can be translated in the positive direction or the negative direction along the normal of the initial path so as to avoid intersecting with the static obstacle.
And S105, generating an obstacle avoidance path according to the translated path points.
At least two obstacle avoidance paths can be generated according to the path points translating in the positive direction or the negative direction; determining path costs corresponding to the at least two obstacle avoidance paths; and comparing the path costs corresponding to the at least two obstacle avoidance paths, and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
Determining respective path costs corresponding to at least two obstacle avoidance paths includes: and uniformly sampling the at least two obstacle avoidance paths, and determining the path cost corresponding to each of the at least two obstacle avoidance paths according to the sampling result.
And screening the obstacle avoidance path with low path cost from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
After the current pose and the target pose of the vehicle are obtained and the identified static barrier is obtained, an initial path containing path points is generated according to the current pose and the target pose of the vehicle; when the path point in the initial path intersects with the static obstacle, translating the intersected path point to enable the intersected path point not to intersect with the static obstacle; and finally, generating an obstacle avoidance path according to the translated path points. Through the processing, the planned path can be adjusted according to the intersection condition of the path point in the initial path and the static obstacle when the path is planned, and finally, a smooth collision-free driving path which can reach the target position and does not intersect with the obstacle, namely an obstacle avoidance path, is generated.
Fig. 2 is a second flowchart of the obstacle avoidance path planning method shown in the present application. Fig. 3 is an application framework diagram of the obstacle avoidance path planning method shown in the present application.
The application provides an obstacle avoidance path planning method which can acquire the target pose of a vehicle based on high-precision map information and navigation information, acquire the current pose of the vehicle based on positioning information and acquire obstacle information on a road from a perception module. These obstacles may be, for example, dynamic obstacles or static obstacles, wherein the static obstacles include piers distributed in the middle of an intersection, safety islands, or other objects which are stationary on a road, etc. On the basis, the planned path is adjusted according to the intersection condition of the path point in the initial path and the static obstacle, and finally the obstacle avoidance path which does not intersect with the obstacle is obtained.
Referring to fig. 2 and 3, the method includes:
s201, acquiring the current pose and the target pose of the vehicle according to the high-precision map information, the navigation information and the positioning information.
For example, the target pose [ X _ t, y _ t, yaw _ t ] of the vehicle is obtained according to the high-precision map information and the navigation information of the vehicle and is recorded as X _ t, and the current pose [ X _ e, y _ e, yaw _ e ] of the vehicle is obtained according to the positioning information of the vehicle and is recorded as X _ e.
S202, acquiring the identified static obstacle through a sensing module.
The method and the device can acquire images or videos in front of or at the sides of the vehicle on the road through the sensing module, and identify obstacle information on the road from the images or videos acquired by the sensing module by using the identification technology in the related technology, wherein the obstacle information can include dynamic obstacles, static obstacles and the like. The static obstacle may be, for example, a bridge pier, a safety island, a water horse, a railing, a pit (also referred to as a negative obstacle) or other stationary object. The detection and identification of the obstacle may be image-based obstacle detection, lidar-based obstacle detection, or vision and lidar fusion-based obstacle detection, which is not limited in the present application.
S203, according to the Bezier curve, generating an initial path with the current pose of the vehicle as a starting point and the target pose of the vehicle as an end point, and sampling from the initial path according to preset intervals to obtain discrete path points in the initial path.
According to a Bezier curve formula in the related art, a curve path with X _ e as a starting state point and X _ t as an ending state point is generated as an initial path, and sampling is performed in the initial path at preset intervals to obtain a discrete path point sequence [ p _0, p _1. The sampling at the preset intervals may be, for example, sampling at preset arc lengths, and the preset arc lengths may be equal or unequal.
Bezier curves are mathematical curves applied to two-dimensional graphics applications. The Bezier curve can draw a smooth curve according to the coordinates of a plurality of points at any positions. A bezier curve may be cut at any point into two or any number of sub-curves, each sub-curve still being a bezier curve.
It should be noted that, in the present application, the preset curve is taken as a bezier curve as an example, but is not limited to this, and the preset curve may be another curve such as a B-spline curve. The B-spline curve is a special representation of a polynomial curve, and fitting of the vehicle travel path through the curve has a better degree of smoothness.
S204, judging whether each path point in the initial path intersects with the static obstacle, and translating the intersected path points in the positive direction or the negative direction along the normal of the initial path so as to ensure that the intersected path points do not intersect with the static obstacle.
The method judges whether each path point in the initial path intersects with the obstacle or not, and for the path points [ p _ k., p _ j ] continuously intersecting, the path points can be translated along the normal positive direction or the reverse direction of the path until the path points do not intersect with the static obstacle. The translation corresponds to [ p _ k _ l,. -, p _ j _ l ] and [ p _ k _ r, -, p _ j _ r ], respectively.
And S205, generating at least two obstacle avoidance paths according to the path points translated in the positive direction or the negative direction.
Since the k to j points have no intersection with the static obstacle (i.e. no collision), the path from 0 to k-1 points only needs to be recursively implemented in the same way, and the j +1 to n-1 points are similar. Because intersection is not generated between the obstacle avoidance system and each obstacle, translation of a path point can be performed along the positive direction or the negative direction of a normal line of the path, and both the translation and the translation are possible to the left or the right, so that at least two obstacle avoidance paths can be generated, and finally, a set of obstacle avoidance paths (travelable paths) can be obtained.
S206, determining path costs corresponding to the at least two obstacle avoidance paths, comparing the path costs corresponding to the at least two obstacle avoidance paths, and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to a comparison result.
For example, according to a sampling result obtained by uniformly sampling at least two obstacle avoidance paths, determining respective path costs corresponding to the at least two obstacle avoidance paths; comparing the path costs corresponding to the at least two obstacle avoidance paths to obtain a comparison result of the path costs; and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
And screening the obstacle avoidance path with low path cost from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
The method for sampling all obstacle avoidance paths in the present application may be, for example, equidistant and uniform sampling. According to the method and the device, cost (path Cost) corresponding to the obstacle avoidance path can be determined according to a preset algorithm formula, and a better path is selected from the obstacle avoidance path set according to a comparison result of the path Cost.
Wherein Cost (path Cost) can be determined according to the following algorithm formula:
wherein, kappa i Discrete curvature of path point, dkappa i Is the rate of change of curvature, w kappa And w dkappa For weight, n is the number of path points, and Cost represents the smoothness of the curve.
And after the Cost (path Cost) of the obstacle avoidance path is calculated according to a formula, screening the obstacle avoidance path with low path Cost as an output obstacle avoidance path. That is to say, after obtaining the obstacle avoidance path composed of different discrete point sequences from the current pose to the target position pose, the method selects the smooth obstacle avoidance path as the obstacle avoidance path for final output.
It should be noted that the above algorithm formula to calculate Cost is only for example and is not limited thereto, and other algorithm formulas to calculate Cost may be provided.
Fig. 4 is a schematic diagram of path adjustment in the obstacle avoidance path planning method shown in the present application.
Fig. 4 shows a current pose X _ e of the current vehicle, that is, the host vehicle, and a target pose X _ t of the host vehicle. The initial path generated from the bezier curve is shown as a sequence of black open dots 401 in fig. 4. Where the gray filled ellipses 402 are impassable areas, i.e., static obstacles. From this, it can be seen that two points 403 and 404 intersect with 402 (i.e., a collision occurs). The two points 403 and 404 are translated in a positive or negative direction along the normal to the curve. There are two possibilities at this time, after translation, as shown by the solid green dots 405 and the solid blue dots 406 in fig. 4, respectively. Recursively invoking the above method between the beginning and end of the solid green dot 405 and X _ e and X _ t can generate a piecewise curve that does not intersect (i.e., does not collide) with 402, as shown by the open green dot 407 and the open blue dot 408 in fig. 4. By splicing, two piecewise curves which do not intersect with 402 (i.e. have no collision) can be obtained. And then, respectively calculating Cost of an obstacle avoidance path composed of the green point sequence and an obstacle avoidance path composed of the blue point sequence, and taking a path with a smaller Cost as a final path, namely the obstacle avoidance path. As shown in fig. 4, an obstacle avoidance path formed by a sequence of blue dots is turned by a large bend, the curvature change rate dkappa is relatively small, and the final Cost value is relatively small; and an obstacle avoidance path formed by the green point sequence needs to be twisted for many times, the discrete curvature kappa is changed all the time, so that the curvature change rate dkappa is large, and the final Cost value is also large. Therefore, the Cost of the obstacle avoidance path formed by the final blue point sequence after calculation is smaller than that of the obstacle avoidance path formed by the green point sequence, and finally the obstacle avoidance path formed by the blue point sequence is selected.
In conclusion, according to the scheme of the application, under the condition that the starting position and the target position of the vehicle are given, the obstacle avoidance path which is specified from the current pose to the target pose in the free space and does not intersect with the obstacle can be quickly generated, namely the vehicle can travel, all static obstacles can be bypassed to reach the destination without collision, the comfort of the path is guaranteed, the safety is guaranteed, and the driving experience is improved.
Corresponding to the application function implementation method, the application also provides a vehicle.
Fig. 5 is a schematic view of a structure of the vehicle shown in the present application.
Referring to fig. 5, the present application provides a vehicle 500 comprising: the pose acquisition module 50, the obstacle recognition module 51, the initial path module 52, the translation module 53 and the obstacle avoidance path module 54.
And a pose acquisition module 50 for acquiring the current pose of the vehicle and the target pose of the vehicle. The pose acquisition module 50 may acquire the target pose of the vehicle according to the high-precision map information and navigation information of the vehicle, and acquire the current pose of the vehicle according to the positioning information of the vehicle.
And an obstacle identification module 51 for acquiring the identified static obstacle. The obstacle recognition module 51 may recognize various obstacles on the road, including dynamic obstacles, static obstacles, and the like, from the image or video captured by the sensing module, using a recognition technique in the related art, where the static obstacles include, for example, piers, safety islands, and the like.
An initial path module 52 is configured to generate an initial path including path points according to the current pose of the host vehicle and the target pose of the host vehicle. The initial path module 52 may generate an initial path with the current pose of the vehicle as a starting point and the target pose of the vehicle as an end point according to a preset curve, where discrete path points in the initial path are obtained by sampling from the initial path at preset intervals. Wherein the predetermined curve comprises a bezier curve or a B-spline curve.
And a translation module 53, configured to, when a waypoint in the generated initial path intersects with the static obstacle, translate the waypoint that intersects so as not to intersect with the static obstacle. When the path point in the initial path intersects with the static obstacle, the translation module 53 may translate the path point along the normal of the initial path in the positive direction or the negative direction so as not to intersect with the static obstacle.
And an obstacle avoidance path module 54, configured to generate an obstacle avoidance path according to the translated path points.
Wherein, obstacle avoidance path module 54 includes: an obstacle avoidance path generating submodule 541 and an obstacle avoidance path screening submodule 542.
An obstacle avoidance path generation sub-module 541 configured to generate at least two obstacle avoidance paths according to the path point performing the forward direction translation or the reverse direction translation;
the obstacle avoidance path screening submodule 542 is configured to determine path costs corresponding to at least two obstacle avoidance paths; and comparing the path costs corresponding to the at least two obstacle avoidance paths, and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
For example, the obstacle avoidance path screening sub-module 542 performs uniform sampling on at least two obstacle avoidance paths, and determines path costs corresponding to the at least two obstacle avoidance paths according to the sampling result; comparing the path costs corresponding to the at least two obstacle avoidance paths to obtain a comparison result of the path costs; and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result of the path costs. And screening the obstacle avoidance path with low path cost from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
According to the vehicle, after the current pose and the target pose of the vehicle are obtained and the identified static barrier is obtained, an initial path containing path points is generated according to the current pose and the target pose of the vehicle; when the path point in the initial path intersects with the static obstacle, translating the intersected path point to enable the intersected path point not to intersect with the static obstacle; and finally, generating an obstacle avoidance path according to the translated path points. Through the processing, the planned path can be adjusted according to the intersection condition of the path point in the initial path and the static obstacle during path planning, and finally, a smooth collision-free driving path which can reach the target position and does not intersect with the obstacle, namely an obstacle avoidance path, is generated.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 6 is another schematic structural diagram of the vehicle shown in the present application.
Referring to fig. 6, the vehicle 1000 includes a memory 1010 and a processor 1020.
The Processor 1020 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 1010 may include various types of storage units, such as system memory, read Only Memory (ROM), and permanent storage. The ROM may store, among other things, static data or instructions for the processor 1020 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 1010 may comprise any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, among others. In some embodiments, memory 1010 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 1010 has stored thereon executable code that, when processed by the processor 1020, may cause the processor 1020 to perform some or all of the methods described above.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) having executable code (or a computer program or computer instruction code) stored thereon, which, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the various steps of the above-described method according to the present application.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (12)
1. An obstacle avoidance path planning method is characterized by comprising the following steps:
acquiring the current pose and the target pose of the vehicle;
acquiring an identified static obstacle;
generating an initial path containing path points according to the current pose and the target pose of the vehicle;
when the generated path point in the initial path intersects with the static obstacle, translating the path point which intersects to enable the path point not to intersect with the static obstacle;
and generating an obstacle avoidance path according to the translated path points.
2. The method of claim 1, wherein generating an initial path comprising path points based on the current pose of the host vehicle and the pose of the target of the host vehicle comprises:
and generating an initial path with the current pose of the vehicle as a starting point and the target pose of the vehicle as an end point according to a preset curve, wherein discrete path points in the initial path are obtained by sampling from the initial path at preset intervals.
3. The method of claim 2, wherein:
the preset curve comprises a Bezier curve or a B-spline curve.
4. The method of claim 1, wherein translating the intersection-producing waypoints to not intersect the static obstacle when the waypoints in the generated initial path intersect the static obstacle comprises:
when the path point in the generated initial path intersects with the static obstacle, the path point which intersects is translated in the positive direction or the negative direction along the normal line of the initial path so as not to intersect with the static obstacle.
5. The method according to claim 4, wherein generating an obstacle avoidance path according to the translated path points comprises:
generating at least two obstacle avoidance paths according to the path points translating in the positive direction or the negative direction;
determining path costs corresponding to the at least two obstacle avoidance paths;
and comparing the path costs corresponding to the at least two obstacle avoidance paths, and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
6. The method of claim 5, wherein the determining the path cost corresponding to each of the at least two obstacle avoidance paths comprises:
and uniformly sampling the at least two obstacle avoidance paths, and determining the path cost corresponding to each of the at least two obstacle avoidance paths according to the sampling result.
7. The method according to claim 5, wherein the selecting one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result includes:
and screening the obstacle avoidance path with low path cost from the at least two obstacle avoidance paths as an output obstacle avoidance path according to the comparison result.
8. A vehicle, characterized by comprising:
the pose acquisition module is used for acquiring the current pose of the vehicle and the target pose of the vehicle;
the obstacle identification module is used for acquiring the identified static obstacles;
the initial path module is used for generating an initial path containing path points according to the current pose of the vehicle and the target pose of the vehicle;
the translation module is used for translating the path points which generate the intersection so as not to intersect with the static obstacle when the path points in the generated initial path intersect with the static obstacle;
and the obstacle avoidance path module is used for generating an obstacle avoidance path according to the translated path points.
9. The vehicle according to claim 8, characterized in that:
when the path point in the initial path intersects with the static obstacle, the translation module translates the path point which intersects in the positive direction or the negative direction along the normal line of the initial path so as to not intersect with the static obstacle.
10. The vehicle of claim 9, wherein the obstacle avoidance path module comprises:
the obstacle avoidance path generation submodule is used for generating at least two obstacle avoidance paths according to the path points which are translated in the positive direction or the negative direction;
and the obstacle avoidance path screening submodule is used for determining path costs corresponding to the at least two obstacle avoidance paths, comparing the path costs corresponding to the at least two obstacle avoidance paths, and screening one obstacle avoidance path from the at least two obstacle avoidance paths as an output obstacle avoidance path according to a comparison result.
11. A vehicle, characterized by comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any one of claims 1-7.
12. A computer-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211010509.5A CN115268463A (en) | 2022-08-23 | 2022-08-23 | Obstacle avoidance path planning method, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211010509.5A CN115268463A (en) | 2022-08-23 | 2022-08-23 | Obstacle avoidance path planning method, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115268463A true CN115268463A (en) | 2022-11-01 |
Family
ID=83754141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211010509.5A Pending CN115268463A (en) | 2022-08-23 | 2022-08-23 | Obstacle avoidance path planning method, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115268463A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993830A (en) * | 2023-03-21 | 2023-04-21 | 佛山隆深机器人有限公司 | Path planning method and device based on obstacle avoidance and robot |
-
2022
- 2022-08-23 CN CN202211010509.5A patent/CN115268463A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993830A (en) * | 2023-03-21 | 2023-04-21 | 佛山隆深机器人有限公司 | Path planning method and device based on obstacle avoidance and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3699048A1 (en) | Travelling track prediction method and device for vehicle | |
| WO2021226921A1 (en) | Method and system of data processing for autonomous driving | |
| US11157753B2 (en) | Road line detection device and road line detection method | |
| US20210174113A1 (en) | Method for limiting object detection area in a mobile system equipped with a rotation sensor or a position sensor with an image sensor, and apparatus for performing the same | |
| US8676494B2 (en) | Multi-dimensional road representation | |
| CN113112524B (en) | Track prediction method and device for moving object in automatic driving and computing equipment | |
| CN115268463A (en) | Obstacle avoidance path planning method, vehicle and storage medium | |
| CN115042788A (en) | Traffic intersection passing method and device, electronic equipment and storage medium | |
| US11922701B2 (en) | Method and system for creating a semantic representation of the environment of a vehicle | |
| CN108154119B (en) | Automatic driving processing method and device based on self-adaptive tracking frame segmentation | |
| CN113320547A (en) | Path detection method and device and automobile | |
| CN115856979B (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN115950441B (en) | Fusion positioning method and device for automatic driving vehicle and electronic equipment | |
| CN116309628A (en) | Lane line recognition method and device, electronic equipment and computer readable storage medium | |
| CN115620277A (en) | Monocular 3D environment sensing method and device, electronic equipment and storage medium | |
| CN115097826A (en) | Vehicle turning track planning method and device | |
| CN110962856B (en) | Method and device for determining area of vehicle where environmental target is located | |
| WO2015098526A1 (en) | Traffic lane identification device and traffic lane identification method | |
| CN116448140A (en) | Navigation line generation method and related device based on road edge detection | |
| CN113538546B (en) | Target detection method, device and equipment for automatic driving | |
| CN116295392A (en) | Method and device for quickly determining effective driving area, electronic equipment and storage medium | |
| EP3957548A1 (en) | System and mehtod for avoiding collision based on vision | |
| US20230400328A1 (en) | Map creation/self-location estimation device | |
| CN118149839A (en) | High-precision map rendering method and device and electronic equipment | |
| CN116129383A (en) | Method and device for detecting drivable area, 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 |